{"id":"07ba9719-6df4-4e38-93d0-1afa7c8cf1b1","entityType":"agent","slug":"clawhub-athola-nm-attune-war-room-checkpoint","name":"war-room-checkpoint","canonicalUrl":"https://www.xpersona.co/agent/clawhub-athola-nm-attune-war-room-checkpoint","canonicalPath":"/agent/clawhub-athola-nm-attune-war-room-checkpoint","generatedAt":"2026-10-10T05:03:02.580Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T03:44:22.844Z","emptyReason":null},"description":"Assesses decision reversibility and risk at critical checkpoints Skill: war-room-checkpoint Owner: athola Summary: Assesses decision reversibility and risk at critical checkpoints Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:07:42.292Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:30:48.443Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:47:45.180Z | user Release v1.9.16 v1.9.15 | 2026-07-04T21:21:31.989Z | user Release v1.9.15 v1.9.14 | 2026-06-30T17:52:11.309Z |","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.7K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-attune-war-room-checkpoint","sourceUrl":"https://clawhub.ai/athola/nm-attune-war-room-checkpoint","homepage":"https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/athola/nm-attune-war-room-checkpoint","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":40,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Assesses decision reversibility and risk at critical checkpoints Skill: war-room-checkpoint Owner: athola Summary: Assesses decision reversibility and risk at c"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T03:44:22.844Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T03:44:22.844Z","emptyReason":null},"stars":null,"forks":null,"downloads":1720,"packageName":null,"latestVersion":"1.9.19","tractionLabel":"1.7K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T03:44:22.844Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T03:44:22.844Z","lastCrawledAt":"2026-10-10T03:44:22.844Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T03:44:22.844Z","lastVerifiedAt":null,"highlights":[{"version":"1.9.19","createdAt":"2026-08-26T13:07:42.292Z","changelog":"Release v1.9.19","fileCount":3,"zipByteSize":5458},{"version":"1.9.17","createdAt":"2026-07-30T05:30:48.443Z","changelog":"Release v1.9.17","fileCount":3,"zipByteSize":5652},{"version":"1.9.16","createdAt":"2026-07-14T19:47:45.180Z","changelog":"Release v1.9.16","fileCount":3,"zipByteSize":5437},{"version":"1.9.15","createdAt":"2026-07-04T21:21:31.989Z","changelog":"Release v1.9.15","fileCount":3,"zipByteSize":5432},{"version":"1.9.14","createdAt":"2026-06-30T17:52:11.309Z","changelog":"Release v1.9.14","fileCount":3,"zipByteSize":5552},{"version":"1.9.13","createdAt":"2026-06-27T16:16:34.611Z","changelog":"Release v1.9.13","fileCount":3,"zipByteSize":5291},{"version":"1.9.12","createdAt":"2026-06-19T03:10:08.014Z","changelog":"Release v1.9.12","fileCount":3,"zipByteSize":5532},{"version":"1.0.3","createdAt":"2026-06-07T21:23:47.902Z","changelog":"Release v1.9.11","fileCount":3,"zipByteSize":5399}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-attune-war-room-checkpoint","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T05:03:02.578Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-attune-war-room-checkpoint/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-10T03:44:22.844Z","emptyReason":null},"readme":"Skill: war-room-checkpoint\n\nOwner: athola\n\nSummary: Assesses decision reversibility and risk at critical checkpoints\n\nTags: latest:1.9.19\n\nVersion history:\n\nv1.9.19 | 2026-08-26T13:07:42.292Z | user\n\nRelease v1.9.19\n\nv1.9.17 | 2026-07-30T05:30:48.443Z | user\n\nRelease v1.9.17\n\nv1.9.16 | 2026-07-14T19:47:45.180Z | user\n\nRelease v1.9.16\n\nv1.9.15 | 2026-07-04T21:21:31.989Z | user\n\nRelease v1.9.15\n\nv1.9.14 | 2026-06-30T17:52:11.309Z | user\n\nRelease v1.9.14\n\nv1.9.13 | 2026-06-27T16:16:34.611Z | user\n\nRelease v1.9.13\n\nv1.9.12 | 2026-06-19T03:10:08.014Z | user\n\nRelease v1.9.12\n\nv1.0.3 | 2026-06-07T21:23:47.902Z | user\n\nRelease v1.9.11\n\nv1.0.2 | 2026-05-09T02:16:03.873Z | user\n\nRelease v1.9.5\n\nv1.0.1 | 2026-05-06T14:16:04.169Z | user\n\nRelease v1.9.4\n\nv1.0.0 | 2026-04-10T10:01:44.147Z | auto\n\nWar Room Checkpoint Skill Initial Release\n\n- Provides inline assessment to evaluate decision reversibility and risk at key command checkpoints.\n- Calculates Reversibility Score (RS) and recommends escalation level: express, lightweight, full council, or delphi.\n- Returns structured response (with recommendation, rationale, and confidence) for calling commands.\n- Supports customizable profile thresholds and command-specific risk adjustments.\n- Persists detailed checkpoints and session audit trails for compliance and integrity verification.\n- Designed for seamless integration; handles failures gracefully without blocking workflow.\n\nArchive index:\n\nArchive v1.9.19: 3 files, 5458 bytes\n\nFiles: skill-card.md (1957b), SKILL.md (9689b), _meta.json (149b)\n\nFile v1.9.19:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.9.19:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.19\",\n  \"publishedAt\": 1787749662292\n}\n\nFile v1.9.19:skill-card.md\n\n## Description:\n\nAssesses decision reversibility and risk at critical checkpoints.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[athola](https://clawhub.ai/user/athola)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineering teams use this skill as an embedded checkpoint in issue work, PR review, architecture review, and fix workflows. It assesses reversibility, chooses whether to escalate to War Room deliberation, and returns a recommendation or escalation mode.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Checkpoint audit files may be retained locally under ~/.claude.\n\nMitigation: Review retention expectations before installation and periodically review or delete stored audit logs for sensitive projects.\n\nRisk: Calling workflows may continue if checkpoint invocation fails.\n\nMitigation: For regulated or highly sensitive projects, configure calling commands to fail closed or prompt the user when checkpoint assessment is unavailable.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint)\n- [Configured homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Markdown, Guidance, Configuration]\n\n**Output Format:** [Markdown checkpoint response with structured assessment fields]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes reversibility score, escalation mode, recommendation or orders, confidence, and user confirmation flag.]\n\n## Skill Version(s):\n\n1.9.19 (source: server release metadata; artifact frontmatter states 1.9.8)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.9.17: 3 files, 5652 bytes\n\nFiles: skill-card.md (2436b), SKILL.md (9689b), _meta.json (149b)\n\nFile v1.9.17:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.9.17:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.17\",\n  \"publishedAt\": 1785389448443\n}\n\nFile v1.9.17:skill-card.md\n\n## Description: <br>\nAssesses decision reversibility and risk at critical checkpoints. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineering agents use this skill during issue work, pull request review, architecture review, and PR fixes to decide whether a high-stakes branch can proceed with a quick recommendation or should escalate to War Room deliberation. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Local audit files may include file paths, issue numbers, decisions, and rationale under ~/.claude. <br>\nMitigation: Confirm this logging is acceptable before installation and narrow, disable, or redirect audit logging in sensitive repositories when the surrounding plugin supports it. <br>\nRisk: Overbroad triggers may invoke the checkpoint in workflows where escalation assessment is unnecessary. <br>\nMitigation: Review trigger configuration and keep checkpoint use limited to high-stakes branches, dependency conflicts, architecture changes, or similarly consequential decisions. <br>\nRisk: The skill's recommendations can influence automated workflow control flow. <br>\nMitigation: Require human confirmation when confidence is low or when the response marks requires_user_confirmation as true. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint) <br>\n- [Attune plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Guidance, Markdown, Configuration] <br>\n**Output Format:** [Markdown with structured response fields and YAML-style examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include a reversibility score, selected escalation mode, recommendation or orders, confidence, and user-confirmation status.] <br>\n\n## Skill Version(s): <br>\n1.9.17 (source: server release metadata; artifact frontmatter reports 1.9.8) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.16: 3 files, 5437 bytes\n\nFiles: skill-card.md (1989b), SKILL.md (9689b), _meta.json (149b)\n\nFile v1.9.16:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.9.16:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.16\",\n  \"publishedAt\": 1784058465180\n}\n\nFile v1.9.16:skill-card.md\n\n## Description: <br>\nAssesses decision reversibility and risk at critical checkpoints. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineering teams use this skill when command workflows reach high-stakes branches and need a structured checkpoint for reversibility, escalation, confidence, and user-confirmation decisions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Checkpoint and War Room audit logs may persist workflow context, including affected file paths, rationale, confidence, and escalation history, under the user's home directory. <br>\nMitigation: Use only in workspaces where local audit records are acceptable, and review or periodically clean the documented ~/.claude/memory-palace/strategeion paths on shared machines. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint) <br>\n- [Attune plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n- [Publisher profile](https://clawhub.ai/user/athola) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Markdown, Configuration, Guidance] <br>\n**Output Format:** [Markdown with structured checkpoint response fields and YAML-style examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include reversibility score, escalation mode, recommendation or orders, confidence, and user-confirmation status.] <br>\n\n## Skill Version(s): <br>\n1.9.16 (source: ClawHub release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.15: 3 files, 5432 bytes\n\nFiles: skill-card.md (1931b), SKILL.md (9689b), _meta.json (149b)\n\nFile v1.9.15:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.9.15:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.15\",\n  \"publishedAt\": 1783200091989\n}\n\nFile v1.9.15:skill-card.md\n\n## Description: <br>\nAssesses decision reversibility and risk at critical checkpoints. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent workflow authors use this skill to assess whether high-stakes command decisions should proceed with an express recommendation or escalate to War Room deliberation. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Decision context can be recorded in local audit logs. <br>\nMitigation: Review files under ~/.claude/memory-palace periodically and avoid passing sensitive secrets into decision context. <br>\nRisk: Generic checkpoint triggers may activate in situations the user did not intend. <br>\nMitigation: Use narrower invocation patterns when generic triggers cause unexpected activation. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint) <br>\n- [Night Market Attune homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, configuration, guidance] <br>\n**Output Format:** [Markdown with structured YAML-style response examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs can include reversibility score, escalation mode, recommendation or orders, confidence, confirmation requirement, and audit-trail identifiers.] <br>\n\n## Skill Version(s): <br>\n1.9.15 (source: ClawHub release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.14: 3 files, 5552 bytes\n\nFiles: skill-card.md (2219b), SKILL.md (9689b), _meta.json (149b)\n\nFile v1.9.14:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.9.14:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.14\",\n  \"publishedAt\": 1782841931309\n}\n\nFile v1.9.14:skill-card.md\n\n## Description: <br>\nAssesses decision reversibility and risk at critical checkpoints. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineering teams use this skill indirectly from issue, review, architecture, and fix workflows to score decision reversibility and decide whether to continue with a quick recommendation or escalate to War Room deliberation. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Checkpoint and War Room workflows may write local audit metadata, including project filenames, rationale, or decision history, under ~/.claude/memory-palace. <br>\nMitigation: Install or configure the related War Room plugin only where local decision audit trails are acceptable; avoid it for projects where this metadata should not be persisted locally. <br>\nRisk: A checkpoint recommendation could be incorrect or insufficient for a high-stakes decision. <br>\nMitigation: Review the checkpoint output before acting, and require user confirmation when confidence is low or the selected mode escalates beyond express handling. <br>\n\n\n## Reference(s): <br>\n- [Attune plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown checkpoint response with structured YAML-style fields] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Includes reversibility score, escalation mode, recommendation or orders, confidence, and user-confirmation flag.] <br>\n\n## Skill Version(s): <br>\n1.9.14 (source: server release metadata; artifact frontmatter reports 1.9.8) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.13: 3 files, 5291 bytes\n\nFiles: skill-card.md (1641b), SKILL.md (9689b), _meta.json (149b)\n\nFile v1.9.13:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.9.13:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.13\",\n  \"publishedAt\": 1782576994611\n}\n\nFile v1.9.13:skill-card.md\n\n## Description: <br>\nAssesses decision reversibility and risk at critical checkpoints. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent workflow authors use this embedded checkpoint skill to assess reversibility, risk, and escalation needs before continuing high-stakes implementation or review decisions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Local checkpoint and decision records may include project details. <br>\nMitigation: Use the skill in a protected workspace, review configured storage paths, and periodically delete or redact audit records that should not be retained. <br>\n\n\n## Reference(s): <br>\n- [Attune plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance] <br>\n**Output Format:** [Markdown with structured checkpoint fields] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Includes a reversibility score, selected escalation mode, recommendation or orders, confidence, and user confirmation flag.] <br>\n\n## Skill Version(s): <br>\n1.9.13 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.12: 3 files, 5532 bytes\n\nFiles: skill-card.md (2250b), SKILL.md (9689b), _meta.json (149b)\n\nFile v1.9.12:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.9.12:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.12\",\n  \"publishedAt\": 1781838608014\n}\n\nFile v1.9.12:skill-card.md\n\n## Description: <br>\nAssesses decision reversibility and risk at critical checkpoints. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent workflow maintainers use this embedded checkpoint to score decision reversibility, decide whether to escalate to War Room deliberation, and return a recommendation or escalation result to the calling command. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may persist review context, sensitive filenames, security-review details, or confidential decision history under local ~/.claude/memory-palace/strategeion paths. <br>\nMitigation: Install only when local workflow decision logging is acceptable, and review or periodically clean the documented local audit-log paths for sensitive projects. <br>\nRisk: Checkpoint recommendations or escalation decisions could be incorrect or misleading for high-stakes workflow branches. <br>\nMitigation: Review checkpoint output before acting, scan the skill before deployment, and require confirmation when the response indicates low confidence or escalation. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/nm-attune-war-room-checkpoint) <br>\n- [OpenClaw homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Markdown, Guidance, Configuration] <br>\n**Output Format:** [Markdown checkpoint response with structured fields] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Includes reversibility score, selected mode, escalation decision, recommendation or orders, confidence, and confirmation requirement.] <br>\n\n## Skill Version(s): <br>\n1.9.12 (source: server release metadata; artifact frontmatter lists 1.9.8) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.3: 3 files, 5399 bytes\n\nFiles: skill-card.md (1925b), SKILL.md (9689b), _meta.json (148b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1780867427902\n}\n\nFile v1.0.3:skill-card.md\n\n## Description: <br>\nAssesses decision reversibility and risk at critical checkpoints. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineering agents use this skill at high-stakes workflow branch points to score reversibility, choose express or escalated decision modes, and return recommendations or war-room orders. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may persist sensitive decision and review context to predictable local files. <br>\nMitigation: Review the skill instructions before installing, use it only where local checkpoint and audit files are acceptable, and delete or disable those logs when persistent records are not wanted. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/nm-attune-war-room-checkpoint) <br>\n- [ClawHub publisher profile](https://clawhub.ai/user/athola) <br>\n- [Clawdis homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown checkpoint response with structured assessment fields] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include reversibility score, selected mode, escalation status, recommendations or orders, confidence, and user-confirmation status.] <br>\n\n## Skill Version(s): <br>\n1.0.3 (source: server release evidence; artifact frontmatter version 1.9.8) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.2: 3 files, 5436 bytes\n\nFiles: skill-card.md (2080b), SKILL.md (9681b), _meta.json (148b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: |\n  Assess decision reversibility and risk at critical checkpoints to determine whether full War Room escalation is warranted\nversion: 1.9.5\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1778292963873\n}\n\nFile v1.0.2:skill-card.md\n\n## Description: <br>\nAssess decision reversibility and risk at critical checkpoints to determine whether full War Room escalation is warranted. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent workflows use this skill to assess whether a decision point is reversible enough for a quick recommendation or should escalate to a War Room review. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Checkpoint and War Room audit records may contain repository or project details under ~/.claude. <br>\nMitigation: Review or purge those local audit files on sensitive repositories, and install only when local audit retention is acceptable. <br>\nRisk: The checkpoint can recommend continuing or escalating based on inferred reversibility and confidence scores. <br>\nMitigation: Review high-impact recommendations before acting, especially when confidence is low or user confirmation is requested. <br>\n\n\n## Reference(s): <br>\n- [ClawHub release page](https://clawhub.ai/athola/nm-attune-war-room-checkpoint) <br>\n- [Night Market Attune plugin](https://github.com/athola/claude-night-market/tree/master/plugins/attune) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Markdown, Guidance] <br>\n**Output Format:** [Markdown with structured checkpoint fields] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include escalation status, selected mode, reversibility score, recommendation or orders, confidence, and user-confirmation status.] <br>\n\n## Skill Version(s): <br>\n1.0.2 (source: server release metadata; artifact frontmatter reports 1.9.5) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.1: 2 files, 4304 bytes\n\nFiles: SKILL.md (9681b), _meta.json (148b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: war-room-checkpoint\ndescription: |\n  Assess decision reversibility and risk at critical checkpoints to determine whether full War Room escalation is warranted\nversion: 1.9.4\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock-In | Does this crystallize immediately? |\n| Blast Radius | How many components/people affected? |\n| Information Loss | Does this close off future options? |\n| Reputation Impact | Is this visible externally? |\n\nScore each 1-5, calculate RS = Sum / 25.\n\n### Step 3: Mode Selection\n\nApply profile thresholds to determine mode:\n\n```\nif RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\"\n```\n\n### Step 4: Response Generation\n\n#### Express Mode (RS <= threshold)\n\nReturn immediately with recommendation:\n\n```yaml\nresponse:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false\n```\n\n#### Escalate Mode (RS > threshold)\n\nInvoke full War Room and return results:\n\n```yaml\nresponse:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}\n```\n\n## Confidence Calculation\n\nFor escalated decisions, calculate confidence for auto-continue:\n\n```\nconfidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)\n```\n\n## Profile Thresholds\n\n| Profile | Express | Lightweight | Full Council | Use Case |\n|---------|---------|-------------|--------------|----------|\n| default | 0.40 | 0.60 | 0.80 | Balanced |\n| startup | 0.55 | 0.75 | 0.90 | Move fast |\n| regulated | 0.25 | 0.45 | 0.65 | Compliance |\n| fast | 0.50 | 0.70 | 0.90 | Speed priority |\n| cautious | 0.30 | 0.50 | 0.70 | Higher stakes |\n\n### Command-Specific Adjustments\n\n| Command | Adjustment | Rationale |\n|---------|-----------|-----------|\n| do-issue (3+ issues) | -0.10 | Higher risk with multiple issues |\n| pr-review (strict mode) | -0.15 | Strict mode = higher scrutiny |\n| architecture-review | -0.05 | Architecture inherently consequential |\n\n## Output Format\n\n### For Calling Command\n\nReturn a structured response that the calling command can act on:\n\n```markdown\n## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}\n```\n\n## Integration Notes\n\n### Calling Commands Should\n\n1. Check checkpoint response's `requires_user_confirmation`\n2. If true: present confirmation prompt and wait\n3. If false: continue with `orders` or `recommendation`\n4. Log checkpoint to audit trail\n\n### Failure Handling\n\nIf checkpoint invocation fails:\n- Log warning with context\n- Continue command execution without checkpoint\n- Do NOT block the user's workflow\n\n## Audit Trail\n\nCheckpoints are logged to:\n```\n~/.claude/memory-palace/strategeion/checkpoints/{date}/{checkpoint-id}.json\n```\n\nEach file contains a `CheckpointEntry` with: `checkpoint_id`, `session_id`, `phase`,\n`action`, `reversibility_score`, `dimensions`, `confidence`, `files_affected`, and\n`requires_user_confirmation`.\n\nAfter a war room session completes and `persist_session()` is called, an audit report\nis written automatically to:\n```\n~/.claude/memory-palace/strategeion/war-table/{session-id}/audit-report.json\n```\n\nThe report consolidates: all checkpoints for the session, the expert panel, voting\nsummary with unanimity score, escalation history, final decision and rationale, and\na Merkle-DAG integrity verification block. The verification recomputes every node\nhash against the stored values so any tampering with deliberation content is\ndetectable.\n\nUse `AuditTrailManager` from `scripts.war_room.audit_trail` to query checkpoints or\ngenerate reports programmatically:\n\n```python\nfrom scripts.war_room.audit_trail import AuditTrailManager\nmanager = AuditTrailManager()\ncheckpoints = manager.get_checkpoints(\"war-room-20260303-100000\")\naudited = manager.list_audited_sessions()\n```\n\n## Examples\n\n### Example 1: Low RS (Express)\n\n**Input**:\n```yaml\nsource_command: \"do-issue\"\ndecision_needed: \"Execution order for issues #101, #102\"\nissues_involved: [101, 102]\nfiles_affected: [\"src/utils/helper.py\", \"tests/test_helper.py\"]\n```\n\n**Assessment**:\n- Reversal Cost: 1 (can revert commits)\n- Time Lock-In: 1 (no deadline)\n- Blast Radius: 1 (single utility module)\n- Information Loss: 1 (all options preserved)\n- Reputation Impact: 1 (internal)\n\n**RS**: 0.20 (Type 2)\n\n**Response**:\n```yaml\nshould_escalate: false\nselected_mode: \"express\"\nrecommendation: \"Execute in parallel - no dependencies detected\"\nconfidence: 0.95\nrequires_user_confirmation: false\n```\n\n### Example 2: High RS (Escalate)\n\n**Input**:\n```yaml\nsource_command: \"pr-review\"\ndecision_needed: \"Review verdict for PR #456\"\nblocking_items:\n  - {type: \"architecture\", description: \"New service without ADR\"}\n  - {type: \"breaking\", description: \"API contract change\"}\n  - {type: \"security\", description: \"Auth flow modification\"}\n  - {type: \"scope\", description: \"Unrelated payment refactor\"}\nfiles_affected: [\"src/auth/\", \"src/api/\", \"src/payment/\", \"src/services/new/\"]\n```\n\n**Assessment**:\n- Reversal Cost: 4 (multi-service impact)\n- Time Lock-In: 3 (PR deadline pressure)\n- Blast Radius: 4 (cross-team impact)\n- Information Loss: 3 (some paths closing)\n- Reputation Impact: 2 (internal review)\n\n**RS**: 0.64 (Type 1A)\n\n**Response**:\n```yaml\nshould_escalate: true\nselected_mode: \"full_council\"\nwar_room_session_id: \"war-room-20260125-143025\"\norders:\n  - \"Split PR: auth changes separate from payment refactor\"\n  - \"Require ADR for new service before merge\"\n  - \"API change: add migration path, not blocking\"\nconfidence: 0.75\nrequires_user_confirmation: true\n```\n\n## Related Skills\n\n- `Skill(attune:war-room)` - Full War Room deliberation\n- `Skill(attune:war-room)/modules/reversibility-assessment.md` - RS framework\n\n## Related Commands\n\n- `/attune:war-room` - Standalone War Room invocation\n- `/do-issue` - Issue implementation (uses this checkpoint)\n- `/pr-review` - PR review (uses this checkpoint)\n- `/architecture-review` - Architecture review (uses this checkpoint)\n- `/fix-pr` - PR fix (uses this checkpoint)\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1778076964169\n}","readmeExcerpt":"Skill: war-room-checkpoint Owner: athola Summary: Assesses decision reversibility and risk at critical checkpoints Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:07:42.292Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:30:48.443Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:47:45.180Z | user Release v1.9.16 v1.9.15 | 2026-07-04T21:21:31.989Z | user Release v1.9.15 v1.9.14 | 2026-06-30T17:52:11.309Z |","codeSnippets":[],"executableExamples":[{"language":"markdown","snippet":"Skill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\""},{"language":"text","snippet":"if RS <= profile.express_ceiling:\n    mode = \"express\"\nelif RS <= profile.lightweight_ceiling:\n    mode = \"lightweight\"\nelif RS <= profile.full_council_ceiling:\n    mode = \"full_council\"\nelse:\n    mode = \"delphi\""},{"language":"yaml","snippet":"response:\n  should_escalate: false\n  selected_mode: \"express\"\n  reversibility_score: {rs}\n  decision_type: \"Type 2\"\n  recommendation: \"{quick_recommendation}\"\n  rationale: \"{brief_explanation}\"\n  confidence: 0.9\n  requires_user_confirmation: false"},{"language":"yaml","snippet":"response:\n  should_escalate: true\n  selected_mode: \"{lightweight|full_council|delphi}\"\n  reversibility_score: {rs}\n  decision_type: \"{Type 1B|1A|1A+}\"\n  war_room_session_id: \"{session_id}\"\n  orders: [\"{order_1}\", \"{order_2}\"]\n  rationale: \"{war_room_rationale}\"\n  confidence: {calculated_confidence}\n  requires_user_confirmation: {true_if_confidence_low}"},{"language":"text","snippet":"confidence = 1.0\n- 0.10 * dissenting_view_count\n- 0.20 if voting_margin < 0.3\n- 0.15 if RS > 0.80\n- 0.10 if novel_domain\n- 0.10 if compound_decision\n+ 0.20 if unanimous (cap at 1.0)\n\nrequires_user_confirmation = (confidence <= 0.8)"},{"language":"markdown","snippet":"## Checkpoint Response\n\n**Source**: {source_command}\n**Decision**: {decision_needed}\n\n### Assessment\n- **RS**: {reversibility_score} ({decision_type})\n- **Mode**: {selected_mode}\n- **Escalated**: {yes|no}\n\n### Recommendation\n{recommendation_or_orders}\n\n### Control Flow\n- **Confidence**: {confidence}\n- **Auto-continue**: {yes|no}\n{user_prompt_if_needed}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: war-room-checkpoint\ndescription: Assesses decision reversibility and risk at critical checkpoints\nversion: 1.9.8\ntriggers:\n  - checkpoint\n  - embedded\n  - escalation\n  - reversibility\n  - inline\n  - a workflow reaches a high-stakes branch needing escalation check\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/attune\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.attune:war-room\"]}}}\nsource: claude-night-market\nsource_plugin: attune\n---\n\n> **Night Market Skill** — ported from [claude-night-market/attune](https://github.com/athola/claude-night-market/tree/master/plugins/attune). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# War Room Checkpoint Skill\n\nLightweight inline assessment for determining whether a decision point within a command warrants War Room escalation.\n\n## Table of Contents\n\n1. [Purpose](#purpose)\n2. [When Commands Should Invoke This](#when-commands-should-invoke-this)\n3. [Invocation Pattern](#invocation-pattern)\n4. [Checkpoint Flow](#checkpoint-flow)\n5. [Confidence Calculation](#confidence-calculation)\n6. [Profile Thresholds](#profile-thresholds)\n7. [Output Format](#output-format)\n8. [Examples](#examples)\n\n## Verification\n\nRun `make test-checkpoint` to verify checkpoint logic works correctly after changes.\n\n## Purpose\n\nThis skill is **not invoked directly by users**. It is called by other commands (e.g., `/do-issue`, `/pr-review`) at critical decision points to:\n\n1. Calculate Reversibility Score (RS) for the current context\n2. Determine if full War Room deliberation is needed\n3. Return either a quick recommendation (express) or escalate to full War Room\n\n## When Commands Should Invoke This\n\n| Command | Trigger Conditions |\n|---------|-------------------|\n| `/do-issue` | 3+ issues, dependency conflicts, overlapping files |\n| `/pr-review` | >3 blocking issues, architecture changes, ADR violations |\n| `/architecture-review` | ADR violations, high coupling, boundary violations |\n| `/fix-pr` | Major scope, conflicting reviewer feedback |\n\n## Invocation Pattern\n\n```markdown\nSkill(attune:war-room-checkpoint) with context:\n  - source_command: \"{calling_command}\"\n  - decision_needed: \"{human_readable_question}\"\n  - files_affected: [{list_of_files}]\n  - issues_involved: [{issue_numbers}] (if applicable)\n  - blocking_items: [{type, description}] (if applicable)\n  - conflict_description: \"{summary}\" (if applicable)\n  - profile: \"default\" | \"startup\" | \"regulated\" | \"fast\" | \"cautious\"\n```\n\n## Checkpoint Flow\n\n### Step 1: Context Analysis\n\nAnalyze the provided context to extract:\n- Scope of change (files, modules, services affected)\n- Stakeholders impacted\n- Conflict indicators\n- Time pressure signals\n\n### Step 2: Reversibility Assessment\n\nCalculate RS using the 5-dimension framework:\n\n| Dimension | Assessment Question |\n|-----------|-------------------|\n| Reversal Cost | How hard to undo this decision? |\n| Time Lock"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-attune-war-room-checkpoint\",\n  \"version\": \"1.9.19\",\n  \"publishedAt\": 1787749662292\n}"},{"path":"skill-card.md","content":"## Description:\n\nAssesses decision reversibility and risk at critical checkpoints.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[athola](https://clawhub.ai/user/athola)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineering teams use this skill as an embedded checkpoint in issue work, PR review, architecture review, and fix workflows. It assesses reversibility, chooses whether to escalate to War Room deliberation, and returns a recommendation or escalation mode.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Checkpoint audit files may be retained locally under ~/.claude.\n\nMitigation: Review retention expectations before installation and periodically review or delete stored audit logs for sensitive projects.\n\nRisk: Calling workflows may continue if checkpoint invocation fails.\n\nMitigation: For regulated or highly sensitive projects, configure calling commands to fail closed or prompt the user when checkpoint assessment is unavailable.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-attune-war-room-checkpoint)\n- [Configured homepage](https://github.com/athola/claude-night-market/tree/master/plugins/attune)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Markdown, Guidance, Configuration]\n\n**Output Format:** [Markdown checkpoint response with structured assessment fields]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes reversibility score, escalation mode, recommendation or orders, confidence, and user confirmation flag.]\n\n## Skill Version(s):\n\n1.9.19 (source: server release metadata; artifact frontmatter states 1.9.8)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Assesses decision reversibility and risk at critical checkpoints Skill: war-room-checkpoint Owner: athola Summary: Assesses decision reversibility and risk at critical checkpoints Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:07:42.292Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:30:48.443Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:47:45.180Z | user Release v1.9.16 v1.9.15 | 2026-07-04T21:21:31.989Z | user Release v1.9.15 v1.9.14 | 2026-06-30T17:52:11.309Z |","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":941,"uniquenessScore":56,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T03:44:22.844Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T03:44:22.844Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:03:02.580Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}