{"id":"ed2fbd7e-c203-49f0-811a-42e62f7df237","entityType":"agent","slug":"clawhub-athola-nm-imbue-vow-enforcement","name":"vow-enforcement","canonicalUrl":"https://www.xpersona.co/agent/clawhub-athola-nm-imbue-vow-enforcement","canonicalPath":"/agent/clawhub-athola-nm-imbue-vow-enforcement","generatedAt":"2026-10-11T23:19:19.379Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T19:48:25.049Z","emptyReason":null},"description":"Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers Skill: vow-enforcement Owner: athola Summary: Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:13:38.587Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:34:58.005Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:51:41.555Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:00:38.244Z | user Release v1.9.14 v1.9.13 | 2026-06-27T1","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-imbue-vow-enforcement","sourceUrl":"https://clawhub.ai/athola/nm-imbue-vow-enforcement","homepage":"https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/athola/nm-imbue-vow-enforcement","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers Skill: vow-enforcement Owner: athola Summary: Classifies and enforces constra"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T19:48:25.049Z","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":"2026-10-11T19:48:25.049Z","emptyReason":null},"stars":null,"forks":null,"downloads":1001,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.9.19","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T19:48:25.037Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T19:48:25.049Z","lastCrawledAt":"2026-10-11T19:48:25.037Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T19:48:25.037Z","lastVerifiedAt":null,"highlights":[{"version":"1.9.19","createdAt":"2026-08-26T13:13:38.587Z","changelog":"Release v1.9.19","fileCount":3,"zipByteSize":5619},{"version":"1.9.17","createdAt":"2026-07-30T05:34:58.005Z","changelog":"Release v1.9.17","fileCount":3,"zipByteSize":5709},{"version":"1.9.16","createdAt":"2026-07-14T19:51:41.555Z","changelog":"Release v1.9.16","fileCount":3,"zipByteSize":5721},{"version":"1.9.14","createdAt":"2026-06-30T18:00:38.244Z","changelog":"Release v1.9.14","fileCount":3,"zipByteSize":5599},{"version":"1.9.13","createdAt":"2026-06-27T16:19:17.077Z","changelog":"Release v1.9.13","fileCount":3,"zipByteSize":5539},{"version":"1.9.12","createdAt":"2026-06-19T03:13:32.500Z","changelog":"Release v1.9.12","fileCount":3,"zipByteSize":5644},{"version":"1.0.0","createdAt":"2026-06-18T14:08:47.212Z","changelog":"- Initial release of the vow-enforcement skill, ported from claude-night-market/imbue. - Classifies constraints as soft vows, hard vows, or Nen Court (external validator) layers. - Documents protocol for choosing, monitoring, and upgrading enforcement mechanisms. - Provides example validator scripts for key constraints, with standardized JSON interface and exit codes. - Details integration guidance, graduation/demotion criteria, and user override flow for enforcement actions.","fileCount":3,"zipByteSize":5669}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-imbue-vow-enforcement","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-imbue-vow-enforcement/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T23:19:19.376Z"}},"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-imbue-vow-enforcement/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-imbue-vow-enforcement/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":"2026-10-11T19:48:25.049Z","emptyReason":null},"readme":"Skill: vow-enforcement\n\nOwner: athola\n\nSummary: Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\n\nTags: latest:1.9.19\n\nVersion history:\n\nv1.9.19 | 2026-08-26T13:13:38.587Z | user\n\nRelease v1.9.19\n\nv1.9.17 | 2026-07-30T05:34:58.005Z | user\n\nRelease v1.9.17\n\nv1.9.16 | 2026-07-14T19:51:41.555Z | user\n\nRelease v1.9.16\n\nv1.9.14 | 2026-06-30T18:00:38.244Z | user\n\nRelease v1.9.14\n\nv1.9.13 | 2026-06-27T16:19:17.077Z | user\n\nRelease v1.9.13\n\nv1.9.12 | 2026-06-19T03:13:32.500Z | user\n\nRelease v1.9.12\n\nv1.0.0 | 2026-06-18T14:08:47.212Z | auto\n\n- Initial release of the vow-enforcement skill, ported from claude-night-market/imbue.\n- Classifies constraints as soft vows, hard vows, or Nen Court (external validator) layers.\n- Documents protocol for choosing, monitoring, and upgrading enforcement mechanisms.\n- Provides example validator scripts for key constraints, with standardized JSON interface and exit codes.\n- Details integration guidance, graduation/demotion criteria, and user override flow for enforcement actions.\n\nArchive index:\n\nArchive v1.9.19: 3 files, 5619 bytes\n\nFiles: skill-card.md (1894b), SKILL.md (9481b), _meta.json (144b)\n\nFile v1.9.19:SKILL.md\n\n---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebase context.\n\n## Vow Classification Protocol\n\nWhen adding a new constraint, follow this sequence:\n\n### Step 1: Start as Soft Vow\n\nAdd the rule to the relevant skill or CLAUDE.md.\nThis is the cheapest path: zero cost, minutes to\ndeploy, ~80% compliance.\n\n### Step 2: Monitor Violation Rate\n\nTrack violations via execution logs, post-hoc audits\n(`imbue:justify` reports), user complaints, and Nen\nCourt findings from related audits.\n\n### Step 3: Graduate if Needed\n\nIf violation rate exceeds 20% over a 30-day window:\n\n- **Binary constraint?** Graduate to Hard Vow (hook).\n- **Judgment constraint?** Graduate to Nen Court.\n- **Ambiguous?** Try Hard Vow first. If false\n  positives exceed 10%, move to Nen Court.\n\n## Night Market Vow Inventory\n\nCurrent classification of existing constraints:\n\n| Constraint | Current Layer | Target Layer | Notes |\n|------------|--------------|--------------|-------|\n| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |\n| No `--no-verify` | Hard | Hard | Already hook-enforceable |\n| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |\n| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks `[Ex]` refs and status (#406) |\n| Bounded discovery reads | Hard | Hard | `vow_bounded_reads.py` with `fcntl.flock` for parallel safety (#418) |\n| No AI attribution in commits | Hard | Hard | Hook pattern-matches git commit command |\n| Markdown line wrapping at 80 chars | Nen Court | Nen Court | `validators/markdown_wrap.py` flags >80-char prose lines (#406) |\n| No emojis in commits | Hard | Hard | Hook pattern-matches git commit command |\n\n### Validator Invocation\n\nThe three Nen Court validators are standalone scripts under\n`plugins/imbue/validators/`.  Each reads JSON on stdin and writes a\nverdict JSON on stdout, using exit codes 0 (pass), 1 (violation), and\n2 (inconclusive).  Examples:\n\n```bash\n# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py\n```\n\nMission orchestrator integration: dispatch the appropriate validator\nat each phase boundary (see Nen Court Protocol below) and treat exit\ncode 1 as a blocking gate, exit code 2 as advisory.\n\n## Vow Graduation Criteria\n\nA vow graduates when any of these conditions hold:\n\n1. **Frequency**: 3+ violations detected in 30 days\n2. **Severity**: Single violation caused rollback,\n   data loss, or broken CI\n3. **User escalation**: User explicitly requests\n   enforcement (\"make it impossible to X\")\n\n### Graduation Process\n\n1. Document the violation pattern with evidence\n2. Design the hook or validator agent\n3. Test the enforcement mechanism in isolation\n4. Deploy alongside the soft vow (shadow mode)\n5. After 1 week with no false positives, retire the\n   soft vow\n\n### Demotion\n\nHard Vows can be demoted back to Soft if:\n\n- The hook produces > 10% false positive rate\n- The constraint was too aggressive (blocking\n  legitimate work)\n- The underlying concern no longer applies\n\n## Nen Court Protocol\n\nNen Court runs at phase boundaries in the mission\norchestrator lifecycle:\n\n- After `specify`: validate spec completeness\n- After `plan`: validate plan feasibility\n- After `execute`: validate Iron Law, additive bias,\n  proof-of-work\n- Before `pr-prep`: final compliance audit\n\n### Validator Agent Contract\n\n```yaml\nvalidator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]\n```\n\n### Verdicts\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| **pass** | Constraint satisfied | Phase advances |\n| **violation** | Constraint broken with evidence | Phase blocked until fixed or user overrides |\n| **inconclusive** | Cannot determine compliance | Flag for human review, do not block |\n\n### User Override\n\nThe user can override any Nen Court verdict:\n\n- \"Proceed anyway\" or \"override\" clears the block\n- The override is logged for future audit\n- Frequent overrides on the same constraint suggest\n  the constraint needs revision, not more enforcement\n\n## Integration Points\n\n- **`imbue:scope-guard`** -- Soft vow layer. Worthiness\n  scoring is a judgment call that belongs in skills.\n- **`imbue:proof-of-work`** -- Mixed enforcement.\n  Evidence rules are soft; evidence content can be\n  verified by a Nen Court validator.\n- **`imbue:justify`** -- Post-hoc Nen Court audit.\n  Already functions as a validator agent for additive\n  bias, Iron Law, and test mutations.\n- **Mission Orchestrator** -- Phase-routing with Nen\n  Court checkpoints between phases as gates:\n\n```\nspecify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep\n```\n\nPhase advances only when Nen Court returns `pass` or\nthe user provides an explicit override.\n\n## When to Use\n\n- Designing new constraints for the codebase\n- Auditing existing constraints for enforcement gaps\n- Deciding whether a rule needs a hook or a skill\n- Reviewing Nen Court findings at phase boundaries\n- Proposing constraint graduations after audits\n\n## When NOT to Use\n\n- One-off rules that apply to a single task\n- Constraints that are already hard-enforced and\n  working\n- Exploratory work where constraints would slow\n  learning\n\n## Related Skills\n\n- `imbue:karpathy-principles` - the discursive layer\n  this skill governs (vow-enforcement decides which\n  principles graduate from skills to hooks)\n- `imbue:scope-guard`, `imbue:proof-of-work`,\n  `leyline:additive-bias-defense` - example soft vows\n  that vow-enforcement classifies and may promote\n- See `docs/quality-gates.md#skill-level-quality-gate-composition`\n  for the federation this skill governs\n\nFile v1.9.19:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.9.19\",\n  \"publishedAt\": 1787750018587\n}\n\nFile v1.9.19:skill-card.md\n\n## Description:\n\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers.\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 agent operators use this skill to classify project constraints as soft guidance, hooks, or validator checks, and to decide when compliance rules should graduate into stronger enforcement.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Broad trigger terms may activate the skill during general compliance or governance conversations.\n\nMitigation: Review whether the activation behavior fits the workflow before deployment.\n\nRisk: Overly strict hook or validator choices can block legitimate work if a rule is misclassified.\n\nMitigation: Use shadow-mode testing and false-positive monitoring before making enforcement blocking.\n\n## Reference(s):\n\n- [Vow Enforcement on ClawHub](https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement)\n- [Configured homepage for the imbue plugin](https://github.com/athola/claude-night-market/tree/master/plugins/imbue)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Analysis, Configuration instructions, Shell commands]\n\n**Output Format:** [Markdown guidance with tables and inline shell and YAML examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [No direct execution; the skill provides guidance for classifying and auditing enforcement choices.]\n\n## Skill Version(s):\n\n1.9.19 (source: ClawHub release metadata; artifact frontmatter says 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, 5709 bytes\n\nFiles: skill-card.md (2146b), SKILL.md (9481b), _meta.json (144b)\n\nFile v1.9.17:SKILL.md\n\n---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebase context.\n\n## Vow Classification Protocol\n\nWhen adding a new constraint, follow this sequence:\n\n### Step 1: Start as Soft Vow\n\nAdd the rule to the relevant skill or CLAUDE.md.\nThis is the cheapest path: zero cost, minutes to\ndeploy, ~80% compliance.\n\n### Step 2: Monitor Violation Rate\n\nTrack violations via execution logs, post-hoc audits\n(`imbue:justify` reports), user complaints, and Nen\nCourt findings from related audits.\n\n### Step 3: Graduate if Needed\n\nIf violation rate exceeds 20% over a 30-day window:\n\n- **Binary constraint?** Graduate to Hard Vow (hook).\n- **Judgment constraint?** Graduate to Nen Court.\n- **Ambiguous?** Try Hard Vow first. If false\n  positives exceed 10%, move to Nen Court.\n\n## Night Market Vow Inventory\n\nCurrent classification of existing constraints:\n\n| Constraint | Current Layer | Target Layer | Notes |\n|------------|--------------|--------------|-------|\n| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |\n| No `--no-verify` | Hard | Hard | Already hook-enforceable |\n| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |\n| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks `[Ex]` refs and status (#406) |\n| Bounded discovery reads | Hard | Hard | `vow_bounded_reads.py` with `fcntl.flock` for parallel safety (#418) |\n| No AI attribution in commits | Hard | Hard | Hook pattern-matches git commit command |\n| Markdown line wrapping at 80 chars | Nen Court | Nen Court | `validators/markdown_wrap.py` flags >80-char prose lines (#406) |\n| No emojis in commits | Hard | Hard | Hook pattern-matches git commit command |\n\n### Validator Invocation\n\nThe three Nen Court validators are standalone scripts under\n`plugins/imbue/validators/`.  Each reads JSON on stdin and writes a\nverdict JSON on stdout, using exit codes 0 (pass), 1 (violation), and\n2 (inconclusive).  Examples:\n\n```bash\n# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py\n```\n\nMission orchestrator integration: dispatch the appropriate validator\nat each phase boundary (see Nen Court Protocol below) and treat exit\ncode 1 as a blocking gate, exit code 2 as advisory.\n\n## Vow Graduation Criteria\n\nA vow graduates when any of these conditions hold:\n\n1. **Frequency**: 3+ violations detected in 30 days\n2. **Severity**: Single violation caused rollback,\n   data loss, or broken CI\n3. **User escalation**: User explicitly requests\n   enforcement (\"make it impossible to X\")\n\n### Graduation Process\n\n1. Document the violation pattern with evidence\n2. Design the hook or validator agent\n3. Test the enforcement mechanism in isolation\n4. Deploy alongside the soft vow (shadow mode)\n5. After 1 week with no false positives, retire the\n   soft vow\n\n### Demotion\n\nHard Vows can be demoted back to Soft if:\n\n- The hook produces > 10% false positive rate\n- The constraint was too aggressive (blocking\n  legitimate work)\n- The underlying concern no longer applies\n\n## Nen Court Protocol\n\nNen Court runs at phase boundaries in the mission\norchestrator lifecycle:\n\n- After `specify`: validate spec completeness\n- After `plan`: validate plan feasibility\n- After `execute`: validate Iron Law, additive bias,\n  proof-of-work\n- Before `pr-prep`: final compliance audit\n\n### Validator Agent Contract\n\n```yaml\nvalidator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]\n```\n\n### Verdicts\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| **pass** | Constraint satisfied | Phase advances |\n| **violation** | Constraint broken with evidence | Phase blocked until fixed or user overrides |\n| **inconclusive** | Cannot determine compliance | Flag for human review, do not block |\n\n### User Override\n\nThe user can override any Nen Court verdict:\n\n- \"Proceed anyway\" or \"override\" clears the block\n- The override is logged for future audit\n- Frequent overrides on the same constraint suggest\n  the constraint needs revision, not more enforcement\n\n## Integration Points\n\n- **`imbue:scope-guard`** -- Soft vow layer. Worthiness\n  scoring is a judgment call that belongs in skills.\n- **`imbue:proof-of-work`** -- Mixed enforcement.\n  Evidence rules are soft; evidence content can be\n  verified by a Nen Court validator.\n- **`imbue:justify`** -- Post-hoc Nen Court audit.\n  Already functions as a validator agent for additive\n  bias, Iron Law, and test mutations.\n- **Mission Orchestrator** -- Phase-routing with Nen\n  Court checkpoints between phases as gates:\n\n```\nspecify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep\n```\n\nPhase advances only when Nen Court returns `pass` or\nthe user provides an explicit override.\n\n## When to Use\n\n- Designing new constraints for the codebase\n- Auditing existing constraints for enforcement gaps\n- Deciding whether a rule needs a hook or a skill\n- Reviewing Nen Court findings at phase boundaries\n- Proposing constraint graduations after audits\n\n## When NOT to Use\n\n- One-off rules that apply to a single task\n- Constraints that are already hard-enforced and\n  working\n- Exploratory work where constraints would slow\n  learning\n\n## Related Skills\n\n- `imbue:karpathy-principles` - the discursive layer\n  this skill governs (vow-enforcement decides which\n  principles graduate from skills to hooks)\n- `imbue:scope-guard`, `imbue:proof-of-work`,\n  `leyline:additive-bias-defense` - example soft vows\n  that vow-enforcement classifies and may promote\n- See `docs/quality-gates.md#skill-level-quality-gate-composition`\n  for the federation this skill governs\n\nFile v1.9.17:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.9.17\",\n  \"publishedAt\": 1785389698005\n}\n\nFile v1.9.17:skill-card.md\n\n## Description: <br>\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers. <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 to classify project rules by enforcement strength, decide when to promote guidance into hooks or validator gates, and audit enforcement gaps. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may be invoked during broad compliance, governance, hooks, or constraints discussions where strict enforcement design is not intended. <br>\nMitigation: Use the skill deliberately for projects where enforcement classification is in scope, and confirm that blocking behavior or audit logging is wanted before adopting its recommendations. <br>\nRisk: Hard vows and validator gates can block legitimate work if a rule is too broad or produces false positives. <br>\nMitigation: Test enforcement mechanisms in isolation or shadow mode, review false-positive rates, and preserve explicit human override paths for inconclusive or disputed findings. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement) <br>\n- [Clawdis Homepage](https://github.com/athola/claude-night-market/tree/master/plugins/imbue) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Analysis, Markdown, Shell commands, Configuration] <br>\n**Output Format:** [Markdown guidance with tables, protocols, and example shell commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [No executable skill code is included in this release.] <br>\n\n## Skill Version(s): <br>\n1.9.17 (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 v1.9.16: 3 files, 5721 bytes\n\nFiles: skill-card.md (2222b), SKILL.md (9481b), _meta.json (144b)\n\nFile v1.9.16:SKILL.md\n\n---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebase context.\n\n## Vow Classification Protocol\n\nWhen adding a new constraint, follow this sequence:\n\n### Step 1: Start as Soft Vow\n\nAdd the rule to the relevant skill or CLAUDE.md.\nThis is the cheapest path: zero cost, minutes to\ndeploy, ~80% compliance.\n\n### Step 2: Monitor Violation Rate\n\nTrack violations via execution logs, post-hoc audits\n(`imbue:justify` reports), user complaints, and Nen\nCourt findings from related audits.\n\n### Step 3: Graduate if Needed\n\nIf violation rate exceeds 20% over a 30-day window:\n\n- **Binary constraint?** Graduate to Hard Vow (hook).\n- **Judgment constraint?** Graduate to Nen Court.\n- **Ambiguous?** Try Hard Vow first. If false\n  positives exceed 10%, move to Nen Court.\n\n## Night Market Vow Inventory\n\nCurrent classification of existing constraints:\n\n| Constraint | Current Layer | Target Layer | Notes |\n|------------|--------------|--------------|-------|\n| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |\n| No `--no-verify` | Hard | Hard | Already hook-enforceable |\n| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |\n| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks `[Ex]` refs and status (#406) |\n| Bounded discovery reads | Hard | Hard | `vow_bounded_reads.py` with `fcntl.flock` for parallel safety (#418) |\n| No AI attribution in commits | Hard | Hard | Hook pattern-matches git commit command |\n| Markdown line wrapping at 80 chars | Nen Court | Nen Court | `validators/markdown_wrap.py` flags >80-char prose lines (#406) |\n| No emojis in commits | Hard | Hard | Hook pattern-matches git commit command |\n\n### Validator Invocation\n\nThe three Nen Court validators are standalone scripts under\n`plugins/imbue/validators/`.  Each reads JSON on stdin and writes a\nverdict JSON on stdout, using exit codes 0 (pass), 1 (violation), and\n2 (inconclusive).  Examples:\n\n```bash\n# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py\n```\n\nMission orchestrator integration: dispatch the appropriate validator\nat each phase boundary (see Nen Court Protocol below) and treat exit\ncode 1 as a blocking gate, exit code 2 as advisory.\n\n## Vow Graduation Criteria\n\nA vow graduates when any of these conditions hold:\n\n1. **Frequency**: 3+ violations detected in 30 days\n2. **Severity**: Single violation caused rollback,\n   data loss, or broken CI\n3. **User escalation**: User explicitly requests\n   enforcement (\"make it impossible to X\")\n\n### Graduation Process\n\n1. Document the violation pattern with evidence\n2. Design the hook or validator agent\n3. Test the enforcement mechanism in isolation\n4. Deploy alongside the soft vow (shadow mode)\n5. After 1 week with no false positives, retire the\n   soft vow\n\n### Demotion\n\nHard Vows can be demoted back to Soft if:\n\n- The hook produces > 10% false positive rate\n- The constraint was too aggressive (blocking\n  legitimate work)\n- The underlying concern no longer applies\n\n## Nen Court Protocol\n\nNen Court runs at phase boundaries in the mission\norchestrator lifecycle:\n\n- After `specify`: validate spec completeness\n- After `plan`: validate plan feasibility\n- After `execute`: validate Iron Law, additive bias,\n  proof-of-work\n- Before `pr-prep`: final compliance audit\n\n### Validator Agent Contract\n\n```yaml\nvalidator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]\n```\n\n### Verdicts\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| **pass** | Constraint satisfied | Phase advances |\n| **violation** | Constraint broken with evidence | Phase blocked until fixed or user overrides |\n| **inconclusive** | Cannot determine compliance | Flag for human review, do not block |\n\n### User Override\n\nThe user can override any Nen Court verdict:\n\n- \"Proceed anyway\" or \"override\" clears the block\n- The override is logged for future audit\n- Frequent overrides on the same constraint suggest\n  the constraint needs revision, not more enforcement\n\n## Integration Points\n\n- **`imbue:scope-guard`** -- Soft vow layer. Worthiness\n  scoring is a judgment call that belongs in skills.\n- **`imbue:proof-of-work`** -- Mixed enforcement.\n  Evidence rules are soft; evidence content can be\n  verified by a Nen Court validator.\n- **`imbue:justify`** -- Post-hoc Nen Court audit.\n  Already functions as a validator agent for additive\n  bias, Iron Law, and test mutations.\n- **Mission Orchestrator** -- Phase-routing with Nen\n  Court checkpoints between phases as gates:\n\n```\nspecify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep\n```\n\nPhase advances only when Nen Court returns `pass` or\nthe user provides an explicit override.\n\n## When to Use\n\n- Designing new constraints for the codebase\n- Auditing existing constraints for enforcement gaps\n- Deciding whether a rule needs a hook or a skill\n- Reviewing Nen Court findings at phase boundaries\n- Proposing constraint graduations after audits\n\n## When NOT to Use\n\n- One-off rules that apply to a single task\n- Constraints that are already hard-enforced and\n  working\n- Exploratory work where constraints would slow\n  learning\n\n## Related Skills\n\n- `imbue:karpathy-principles` - the discursive layer\n  this skill governs (vow-enforcement decides which\n  principles graduate from skills to hooks)\n- `imbue:scope-guard`, `imbue:proof-of-work`,\n  `leyline:additive-bias-defense` - example soft vows\n  that vow-enforcement classifies and may promote\n- See `docs/quality-gates.md#skill-level-quality-gate-composition`\n  for the federation this skill governs\n\nFile v1.9.16:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.9.16\",\n  \"publishedAt\": 1784058701555\n}\n\nFile v1.9.16:skill-card.md\n\n## Description: <br>\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers. <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 to classify project rules, audit enforcement gaps, and decide whether constraints belong in skill guidance, hooks, or external validation gates. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Broad trigger words may make the skill appear in more governance or compliance conversations than intended. <br>\nMitigation: Treat its recommendations as advisory unless the user intentionally implements separate hooks or validators. <br>\nRisk: Guidance about enforcement layers could be mistaken for active enforcement. <br>\nMitigation: Confirm that any required hooks, permissions, or validator agents are implemented and tested outside this documentation-only skill. <br>\nRisk: Soft rules can fail when model goals conflict with project constraints. <br>\nMitigation: Promote high-risk binary constraints to hard hooks and route judgment-heavy checks through external validation gates. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement) <br>\n- [Metadata homepage](https://github.com/athola/claude-night-market/tree/master/plugins/imbue) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, shell commands, configuration] <br>\n**Output Format:** [Markdown guidance with tables, examples, and command snippets] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Documentation-only release artifact with no executable code included.] <br>\n\n## Skill Version(s): <br>\n1.9.16 (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 v1.9.14: 3 files, 5599 bytes\n\nFiles: skill-card.md (1957b), SKILL.md (9481b), _meta.json (144b)\n\nFile v1.9.14:SKILL.md\n\n---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebase context.\n\n## Vow Classification Protocol\n\nWhen adding a new constraint, follow this sequence:\n\n### Step 1: Start as Soft Vow\n\nAdd the rule to the relevant skill or CLAUDE.md.\nThis is the cheapest path: zero cost, minutes to\ndeploy, ~80% compliance.\n\n### Step 2: Monitor Violation Rate\n\nTrack violations via execution logs, post-hoc audits\n(`imbue:justify` reports), user complaints, and Nen\nCourt findings from related audits.\n\n### Step 3: Graduate if Needed\n\nIf violation rate exceeds 20% over a 30-day window:\n\n- **Binary constraint?** Graduate to Hard Vow (hook).\n- **Judgment constraint?** Graduate to Nen Court.\n- **Ambiguous?** Try Hard Vow first. If false\n  positives exceed 10%, move to Nen Court.\n\n## Night Market Vow Inventory\n\nCurrent classification of existing constraints:\n\n| Constraint | Current Layer | Target Layer | Notes |\n|------------|--------------|--------------|-------|\n| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |\n| No `--no-verify` | Hard | Hard | Already hook-enforceable |\n| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |\n| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks `[Ex]` refs and status (#406) |\n| Bounded discovery reads | Hard | Hard | `vow_bounded_reads.py` with `fcntl.flock` for parallel safety (#418) |\n| No AI attribution in commits | Hard | Hard | Hook pattern-matches git commit command |\n| Markdown line wrapping at 80 chars | Nen Court | Nen Court | `validators/markdown_wrap.py` flags >80-char prose lines (#406) |\n| No emojis in commits | Hard | Hard | Hook pattern-matches git commit command |\n\n### Validator Invocation\n\nThe three Nen Court validators are standalone scripts under\n`plugins/imbue/validators/`.  Each reads JSON on stdin and writes a\nverdict JSON on stdout, using exit codes 0 (pass), 1 (violation), and\n2 (inconclusive).  Examples:\n\n```bash\n# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py\n```\n\nMission orchestrator integration: dispatch the appropriate validator\nat each phase boundary (see Nen Court Protocol below) and treat exit\ncode 1 as a blocking gate, exit code 2 as advisory.\n\n## Vow Graduation Criteria\n\nA vow graduates when any of these conditions hold:\n\n1. **Frequency**: 3+ violations detected in 30 days\n2. **Severity**: Single violation caused rollback,\n   data loss, or broken CI\n3. **User escalation**: User explicitly requests\n   enforcement (\"make it impossible to X\")\n\n### Graduation Process\n\n1. Document the violation pattern with evidence\n2. Design the hook or validator agent\n3. Test the enforcement mechanism in isolation\n4. Deploy alongside the soft vow (shadow mode)\n5. After 1 week with no false positives, retire the\n   soft vow\n\n### Demotion\n\nHard Vows can be demoted back to Soft if:\n\n- The hook produces > 10% false positive rate\n- The constraint was too aggressive (blocking\n  legitimate work)\n- The underlying concern no longer applies\n\n## Nen Court Protocol\n\nNen Court runs at phase boundaries in the mission\norchestrator lifecycle:\n\n- After `specify`: validate spec completeness\n- After `plan`: validate plan feasibility\n- After `execute`: validate Iron Law, additive bias,\n  proof-of-work\n- Before `pr-prep`: final compliance audit\n\n### Validator Agent Contract\n\n```yaml\nvalidator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]\n```\n\n### Verdicts\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| **pass** | Constraint satisfied | Phase advances |\n| **violation** | Constraint broken with evidence | Phase blocked until fixed or user overrides |\n| **inconclusive** | Cannot determine compliance | Flag for human review, do not block |\n\n### User Override\n\nThe user can override any Nen Court verdict:\n\n- \"Proceed anyway\" or \"override\" clears the block\n- The override is logged for future audit\n- Frequent overrides on the same constraint suggest\n  the constraint needs revision, not more enforcement\n\n## Integration Points\n\n- **`imbue:scope-guard`** -- Soft vow layer. Worthiness\n  scoring is a judgment call that belongs in skills.\n- **`imbue:proof-of-work`** -- Mixed enforcement.\n  Evidence rules are soft; evidence content can be\n  verified by a Nen Court validator.\n- **`imbue:justify`** -- Post-hoc Nen Court audit.\n  Already functions as a validator agent for additive\n  bias, Iron Law, and test mutations.\n- **Mission Orchestrator** -- Phase-routing with Nen\n  Court checkpoints between phases as gates:\n\n```\nspecify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep\n```\n\nPhase advances only when Nen Court returns `pass` or\nthe user provides an explicit override.\n\n## When to Use\n\n- Designing new constraints for the codebase\n- Auditing existing constraints for enforcement gaps\n- Deciding whether a rule needs a hook or a skill\n- Reviewing Nen Court findings at phase boundaries\n- Proposing constraint graduations after audits\n\n## When NOT to Use\n\n- One-off rules that apply to a single task\n- Constraints that are already hard-enforced and\n  working\n- Exploratory work where constraints would slow\n  learning\n\n## Related Skills\n\n- `imbue:karpathy-principles` - the discursive layer\n  this skill governs (vow-enforcement decides which\n  principles graduate from skills to hooks)\n- `imbue:scope-guard`, `imbue:proof-of-work`,\n  `leyline:additive-bias-defense` - example soft vows\n  that vow-enforcement classifies and may promote\n- See `docs/quality-gates.md#skill-level-quality-gate-composition`\n  for the federation this skill governs\n\nFile v1.9.14:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.9.14\",\n  \"publishedAt\": 1782842438244\n}\n\nFile v1.9.14:skill-card.md\n\n## Description: <br>\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers. <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-governance reviewers use this skill to classify project constraints, decide whether rules belong in soft instructions, hooks, or validator checks, and plan enforcement changes. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may influence governance or enforcement design in ways that block legitimate work if applied too broadly. <br>\nMitigation: Review proposed hooks, validators, and blocking gates before enabling them. <br>\nRisk: Documentation-only guidance can be mistaken for an installed enforcement package. <br>\nMitigation: Confirm any required companion configuration or tools are installed before relying on the guidance for enforcement. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement) <br>\n- [Clawdis homepage](https://github.com/athola/claude-night-market/tree/master/plugins/imbue) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Markdown, Code, Shell commands, Configuration] <br>\n**Output Format:** [Markdown with tables, shell examples, and configuration examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Documentation-only guidance; no bundled executable code.] <br>\n\n## Skill Version(s): <br>\n1.9.14 (source: server release; artifact frontmatter says 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, 5539 bytes\n\nFiles: skill-card.md (1786b), SKILL.md (9481b), _meta.json (144b)\n\nFile v1.9.13:SKILL.md\n\n---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebase context.\n\n## Vow Classification Protocol\n\nWhen adding a new constraint, follow this sequence:\n\n### Step 1: Start as Soft Vow\n\nAdd the rule to the relevant skill or CLAUDE.md.\nThis is the cheapest path: zero cost, minutes to\ndeploy, ~80% compliance.\n\n### Step 2: Monitor Violation Rate\n\nTrack violations via execution logs, post-hoc audits\n(`imbue:justify` reports), user complaints, and Nen\nCourt findings from related audits.\n\n### Step 3: Graduate if Needed\n\nIf violation rate exceeds 20% over a 30-day window:\n\n- **Binary constraint?** Graduate to Hard Vow (hook).\n- **Judgment constraint?** Graduate to Nen Court.\n- **Ambiguous?** Try Hard Vow first. If false\n  positives exceed 10%, move to Nen Court.\n\n## Night Market Vow Inventory\n\nCurrent classification of existing constraints:\n\n| Constraint | Current Layer | Target Layer | Notes |\n|------------|--------------|--------------|-------|\n| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |\n| No `--no-verify` | Hard | Hard | Already hook-enforceable |\n| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |\n| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks `[Ex]` refs and status (#406) |\n| Bounded discovery reads | Hard | Hard | `vow_bounded_reads.py` with `fcntl.flock` for parallel safety (#418) |\n| No AI attribution in commits | Hard | Hard | Hook pattern-matches git commit command |\n| Markdown line wrapping at 80 chars | Nen Court | Nen Court | `validators/markdown_wrap.py` flags >80-char prose lines (#406) |\n| No emojis in commits | Hard | Hard | Hook pattern-matches git commit command |\n\n### Validator Invocation\n\nThe three Nen Court validators are standalone scripts under\n`plugins/imbue/validators/`.  Each reads JSON on stdin and writes a\nverdict JSON on stdout, using exit codes 0 (pass), 1 (violation), and\n2 (inconclusive).  Examples:\n\n```bash\n# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py\n```\n\nMission orchestrator integration: dispatch the appropriate validator\nat each phase boundary (see Nen Court Protocol below) and treat exit\ncode 1 as a blocking gate, exit code 2 as advisory.\n\n## Vow Graduation Criteria\n\nA vow graduates when any of these conditions hold:\n\n1. **Frequency**: 3+ violations detected in 30 days\n2. **Severity**: Single violation caused rollback,\n   data loss, or broken CI\n3. **User escalation**: User explicitly requests\n   enforcement (\"make it impossible to X\")\n\n### Graduation Process\n\n1. Document the violation pattern with evidence\n2. Design the hook or validator agent\n3. Test the enforcement mechanism in isolation\n4. Deploy alongside the soft vow (shadow mode)\n5. After 1 week with no false positives, retire the\n   soft vow\n\n### Demotion\n\nHard Vows can be demoted back to Soft if:\n\n- The hook produces > 10% false positive rate\n- The constraint was too aggressive (blocking\n  legitimate work)\n- The underlying concern no longer applies\n\n## Nen Court Protocol\n\nNen Court runs at phase boundaries in the mission\norchestrator lifecycle:\n\n- After `specify`: validate spec completeness\n- After `plan`: validate plan feasibility\n- After `execute`: validate Iron Law, additive bias,\n  proof-of-work\n- Before `pr-prep`: final compliance audit\n\n### Validator Agent Contract\n\n```yaml\nvalidator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]\n```\n\n### Verdicts\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| **pass** | Constraint satisfied | Phase advances |\n| **violation** | Constraint broken with evidence | Phase blocked until fixed or user overrides |\n| **inconclusive** | Cannot determine compliance | Flag for human review, do not block |\n\n### User Override\n\nThe user can override any Nen Court verdict:\n\n- \"Proceed anyway\" or \"override\" clears the block\n- The override is logged for future audit\n- Frequent overrides on the same constraint suggest\n  the constraint needs revision, not more enforcement\n\n## Integration Points\n\n- **`imbue:scope-guard`** -- Soft vow layer. Worthiness\n  scoring is a judgment call that belongs in skills.\n- **`imbue:proof-of-work`** -- Mixed enforcement.\n  Evidence rules are soft; evidence content can be\n  verified by a Nen Court validator.\n- **`imbue:justify`** -- Post-hoc Nen Court audit.\n  Already functions as a validator agent for additive\n  bias, Iron Law, and test mutations.\n- **Mission Orchestrator** -- Phase-routing with Nen\n  Court checkpoints between phases as gates:\n\n```\nspecify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep\n```\n\nPhase advances only when Nen Court returns `pass` or\nthe user provides an explicit override.\n\n## When to Use\n\n- Designing new constraints for the codebase\n- Auditing existing constraints for enforcement gaps\n- Deciding whether a rule needs a hook or a skill\n- Reviewing Nen Court findings at phase boundaries\n- Proposing constraint graduations after audits\n\n## When NOT to Use\n\n- One-off rules that apply to a single task\n- Constraints that are already hard-enforced and\n  working\n- Exploratory work where constraints would slow\n  learning\n\n## Related Skills\n\n- `imbue:karpathy-principles` - the discursive layer\n  this skill governs (vow-enforcement decides which\n  principles graduate from skills to hooks)\n- `imbue:scope-guard`, `imbue:proof-of-work`,\n  `leyline:additive-bias-defense` - example soft vows\n  that vow-enforcement classifies and may promote\n- See `docs/quality-gates.md#skill-level-quality-gate-composition`\n  for the federation this skill governs\n\nFile v1.9.13:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.9.13\",\n  \"publishedAt\": 1782577157077\n}\n\nFile v1.9.13:skill-card.md\n\n## Description: <br>\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers. <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 to classify project rules by enforcement strength, decide when to promote soft guidance into hooks or validator gates, and audit enforcement gaps. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Broad enforcement guidance could lead teams to add hooks or validator gates that block legitimate work. <br>\nMitigation: Scope, test, and review enforcement mechanisms before deployment, and preserve explicit override or revision paths. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement) <br>\n- [Imbue plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/imbue) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Markdown, Configuration, Shell commands] <br>\n**Output Format:** [Markdown guidance with tables and command examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Documentation-style guidance; no executable payload is included in the released artifact.] <br>\n\n## Skill Version(s): <br>\n1.9.13 (source: server release evidence; 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 v1.9.12: 3 files, 5644 bytes\n\nFiles: skill-card.md (2056b), SKILL.md (9481b), _meta.json (144b)\n\nFile v1.9.12:SKILL.md\n\n---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebase context.\n\n## Vow Classification Protocol\n\nWhen adding a new constraint, follow this sequence:\n\n### Step 1: Start as Soft Vow\n\nAdd the rule to the relevant skill or CLAUDE.md.\nThis is the cheapest path: zero cost, minutes to\ndeploy, ~80% compliance.\n\n### Step 2: Monitor Violation Rate\n\nTrack violations via execution logs, post-hoc audits\n(`imbue:justify` reports), user complaints, and Nen\nCourt findings from related audits.\n\n### Step 3: Graduate if Needed\n\nIf violation rate exceeds 20% over a 30-day window:\n\n- **Binary constraint?** Graduate to Hard Vow (hook).\n- **Judgment constraint?** Graduate to Nen Court.\n- **Ambiguous?** Try Hard Vow first. If false\n  positives exceed 10%, move to Nen Court.\n\n## Night Market Vow Inventory\n\nCurrent classification of existing constraints:\n\n| Constraint | Current Layer | Target Layer | Notes |\n|------------|--------------|--------------|-------|\n| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |\n| No `--no-verify` | Hard | Hard | Already hook-enforceable |\n| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |\n| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks `[Ex]` refs and status (#406) |\n| Bounded discovery reads | Hard | Hard | `vow_bounded_reads.py` with `fcntl.flock` for parallel safety (#418) |\n| No AI attribution in commits | Hard | Hard | Hook pattern-matches git commit command |\n| Markdown line wrapping at 80 chars | Nen Court | Nen Court | `validators/markdown_wrap.py` flags >80-char prose lines (#406) |\n| No emojis in commits | Hard | Hard | Hook pattern-matches git commit command |\n\n### Validator Invocation\n\nThe three Nen Court validators are standalone scripts under\n`plugins/imbue/validators/`.  Each reads JSON on stdin and writes a\nverdict JSON on stdout, using exit codes 0 (pass), 1 (violation), and\n2 (inconclusive).  Examples:\n\n```bash\n# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py\n```\n\nMission orchestrator integration: dispatch the appropriate validator\nat each phase boundary (see Nen Court Protocol below) and treat exit\ncode 1 as a blocking gate, exit code 2 as advisory.\n\n## Vow Graduation Criteria\n\nA vow graduates when any of these conditions hold:\n\n1. **Frequency**: 3+ violations detected in 30 days\n2. **Severity**: Single violation caused rollback,\n   data loss, or broken CI\n3. **User escalation**: User explicitly requests\n   enforcement (\"make it impossible to X\")\n\n### Graduation Process\n\n1. Document the violation pattern with evidence\n2. Design the hook or validator agent\n3. Test the enforcement mechanism in isolation\n4. Deploy alongside the soft vow (shadow mode)\n5. After 1 week with no false positives, retire the\n   soft vow\n\n### Demotion\n\nHard Vows can be demoted back to Soft if:\n\n- The hook produces > 10% false positive rate\n- The constraint was too aggressive (blocking\n  legitimate work)\n- The underlying concern no longer applies\n\n## Nen Court Protocol\n\nNen Court runs at phase boundaries in the mission\norchestrator lifecycle:\n\n- After `specify`: validate spec completeness\n- After `plan`: validate plan feasibility\n- After `execute`: validate Iron Law, additive bias,\n  proof-of-work\n- Before `pr-prep`: final compliance audit\n\n### Validator Agent Contract\n\n```yaml\nvalidator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]\n```\n\n### Verdicts\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| **pass** | Constraint satisfied | Phase advances |\n| **violation** | Constraint broken with evidence | Phase blocked until fixed or user overrides |\n| **inconclusive** | Cannot determine compliance | Flag for human review, do not block |\n\n### User Override\n\nThe user can override any Nen Court verdict:\n\n- \"Proceed anyway\" or \"override\" clears the block\n- The override is logged for future audit\n- Frequent overrides on the same constraint suggest\n  the constraint needs revision, not more enforcement\n\n## Integration Points\n\n- **`imbue:scope-guard`** -- Soft vow layer. Worthiness\n  scoring is a judgment call that belongs in skills.\n- **`imbue:proof-of-work`** -- Mixed enforcement.\n  Evidence rules are soft; evidence content can be\n  verified by a Nen Court validator.\n- **`imbue:justify`** -- Post-hoc Nen Court audit.\n  Already functions as a validator agent for additive\n  bias, Iron Law, and test mutations.\n- **Mission Orchestrator** -- Phase-routing with Nen\n  Court checkpoints between phases as gates:\n\n```\nspecify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep\n```\n\nPhase advances only when Nen Court returns `pass` or\nthe user provides an explicit override.\n\n## When to Use\n\n- Designing new constraints for the codebase\n- Auditing existing constraints for enforcement gaps\n- Deciding whether a rule needs a hook or a skill\n- Reviewing Nen Court findings at phase boundaries\n- Proposing constraint graduations after audits\n\n## When NOT to Use\n\n- One-off rules that apply to a single task\n- Constraints that are already hard-enforced and\n  working\n- Exploratory work where constraints would slow\n  learning\n\n## Related Skills\n\n- `imbue:karpathy-principles` - the discursive layer\n  this skill governs (vow-enforcement decides which\n  principles graduate from skills to hooks)\n- `imbue:scope-guard`, `imbue:proof-of-work`,\n  `leyline:additive-bias-defense` - example soft vows\n  that vow-enforcement classifies and may promote\n- See `docs/quality-gates.md#skill-level-quality-gate-composition`\n  for the federation this skill governs\n\nFile v1.9.12:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.9.12\",\n  \"publishedAt\": 1781838812500\n}\n\nFile v1.9.12:skill-card.md\n\n## Description: <br>\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers. <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 engineers use this skill to classify project rules into soft vows, hard vows, or validator checkpoints and to audit when governance controls should be promoted, demoted, or overridden. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Broad activation terms such as hooks, compliance, or governance may trigger the skill for tasks where enforcement design is not actually needed. <br>\nMitigation: Review the response for task fit before adopting any proposed blocking controls. <br>\nRisk: Governance recommendations may add unnecessary or overly strict phase gates, hooks, or validators. <br>\nMitigation: Test proposed controls in shadow mode, monitor false positives, and keep an explicit human override path. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/nm-imbue-vow-enforcement) <br>\n- [Clawdis homepage](https://github.com/athola/claude-night-market/tree/master/plugins/imbue) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, shell commands, configuration] <br>\n**Output Format:** [Markdown guidance with tables, validator contracts, and shell command examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May recommend hooks, settings changes, validators, or phase gates for human review before adoption.] <br>\n\n## Skill Version(s): <br>\n1.9.12 (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 v1.0.0: 3 files, 5669 bytes\n\nFiles: skill-card.md (2037b), SKILL.md (9481b), _meta.json (143b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebase context.\n\n## Vow Classification Protocol\n\nWhen adding a new constraint, follow this sequence:\n\n### Step 1: Start as Soft Vow\n\nAdd the rule to the relevant skill or CLAUDE.md.\nThis is the cheapest path: zero cost, minutes to\ndeploy, ~80% compliance.\n\n### Step 2: Monitor Violation Rate\n\nTrack violations via execution logs, post-hoc audits\n(`imbue:justify` reports), user complaints, and Nen\nCourt findings from related audits.\n\n### Step 3: Graduate if Needed\n\nIf violation rate exceeds 20% over a 30-day window:\n\n- **Binary constraint?** Graduate to Hard Vow (hook).\n- **Judgment constraint?** Graduate to Nen Court.\n- **Ambiguous?** Try Hard Vow first. If false\n  positives exceed 10%, move to Nen Court.\n\n## Night Market Vow Inventory\n\nCurrent classification of existing constraints:\n\n| Constraint | Current Layer | Target Layer | Notes |\n|------------|--------------|--------------|-------|\n| Iron Law (no impl without failing test) | Nen Court | Nen Court | `validators/iron_law.py` audits commit order (#406) |\n| No `--no-verify` | Hard | Hard | Already hook-enforceable |\n| Scope-guard worthiness scoring | Soft | Soft | Requires judgment, not binary |\n| Proof-of-work evidence | Nen Court | Nen Court | `validators/proof_of_work.py` checks `[Ex]` refs and status (#406) |\n| Bounded discovery reads | Hard | Hard | `vow_bounded_reads.py` with `fcntl.flock` for parallel safety (#418) |\n| No AI attribution in commits | Hard | Hard | Hook pattern-matches git commit command |\n| Markdown line wrapping at 80 chars | Nen Court | Nen Court | `validators/markdown_wrap.py` flags >80-char prose lines (#406) |\n| No emojis in commits | Hard | Hard | Hook pattern-matches git commit command |\n\n### Validator Invocation\n\nThe three Nen Court validators are standalone scripts under\n`plugins/imbue/validators/`.  Each reads JSON on stdin and writes a\nverdict JSON on stdout, using exit codes 0 (pass), 1 (violation), and\n2 (inconclusive).  Examples:\n\n```bash\n# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py\n```\n\nMission orchestrator integration: dispatch the appropriate validator\nat each phase boundary (see Nen Court Protocol below) and treat exit\ncode 1 as a blocking gate, exit code 2 as advisory.\n\n## Vow Graduation Criteria\n\nA vow graduates when any of these conditions hold:\n\n1. **Frequency**: 3+ violations detected in 30 days\n2. **Severity**: Single violation caused rollback,\n   data loss, or broken CI\n3. **User escalation**: User explicitly requests\n   enforcement (\"make it impossible to X\")\n\n### Graduation Process\n\n1. Document the violation pattern with evidence\n2. Design the hook or validator agent\n3. Test the enforcement mechanism in isolation\n4. Deploy alongside the soft vow (shadow mode)\n5. After 1 week with no false positives, retire the\n   soft vow\n\n### Demotion\n\nHard Vows can be demoted back to Soft if:\n\n- The hook produces > 10% false positive rate\n- The constraint was too aggressive (blocking\n  legitimate work)\n- The underlying concern no longer applies\n\n## Nen Court Protocol\n\nNen Court runs at phase boundaries in the mission\norchestrator lifecycle:\n\n- After `specify`: validate spec completeness\n- After `plan`: validate plan feasibility\n- After `execute`: validate Iron Law, additive bias,\n  proof-of-work\n- Before `pr-prep`: final compliance audit\n\n### Validator Agent Contract\n\n```yaml\nvalidator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]\n```\n\n### Verdicts\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| **pass** | Constraint satisfied | Phase advances |\n| **violation** | Constraint broken with evidence | Phase blocked until fixed or user overrides |\n| **inconclusive** | Cannot determine compliance | Flag for human review, do not block |\n\n### User Override\n\nThe user can override any Nen Court verdict:\n\n- \"Proceed anyway\" or \"override\" clears the block\n- The override is logged for future audit\n- Frequent overrides on the same constraint suggest\n  the constraint needs revision, not more enforcement\n\n## Integration Points\n\n- **`imbue:scope-guard`** -- Soft vow layer. Worthiness\n  scoring is a judgment call that belongs in skills.\n- **`imbue:proof-of-work`** -- Mixed enforcement.\n  Evidence rules are soft; evidence content can be\n  verified by a Nen Court validator.\n- **`imbue:justify`** -- Post-hoc Nen Court audit.\n  Already functions as a validator agent for additive\n  bias, Iron Law, and test mutations.\n- **Mission Orchestrator** -- Phase-routing with Nen\n  Court checkpoints between phases as gates:\n\n```\nspecify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep\n```\n\nPhase advances only when Nen Court returns `pass` or\nthe user provides an explicit override.\n\n## When to Use\n\n- Designing new constraints for the codebase\n- Auditing existing constraints for enforcement gaps\n- Deciding whether a rule needs a hook or a skill\n- Reviewing Nen Court findings at phase boundaries\n- Proposing constraint graduations after audits\n\n## When NOT to Use\n\n- One-off rules that apply to a single task\n- Constraints that are already hard-enforced and\n  working\n- Exploratory work where constraints would slow\n  learning\n\n## Related Skills\n\n- `imbue:karpathy-principles` - the discursive layer\n  this skill governs (vow-enforcement decides which\n  principles graduate from skills to hooks)\n- `imbue:scope-guard`, `imbue:proof-of-work`,\n  `leyline:additive-bias-defense` - example soft vows\n  that vow-enforcement classifies and may promote\n- See `docs/quality-gates.md#skill-level-quality-gate-composition`\n  for the federation this skill governs\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1781791727212\n}\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers. <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 to design, audit, and graduate project constraints across skill instructions, hooks, and external validator gates. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Generic trigger words may activate the skill during unrelated compliance, governance, or hook discussions. <br>\nMitigation: Invoke it with clear scope, and disable or ignore it when the task is not about this enforcement architecture. <br>\nRisk: Strict hooks or validator gates can block legitimate work when a constraint is too broad or produces false positives. <br>\nMitigation: Test enforcement in isolation, use shadow mode before blocking, keep human review for inconclusive results, and allow explicit user overrides. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/nm-imbue-vow-enforcement) <br>\n- [Project homepage](https://github.com/athola/claude-night-market/tree/master/plugins/imbue) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Markdown, Shell commands, Configuration] <br>\n**Output Format:** [Markdown guidance with tables, YAML examples, and bash command examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires the related Night Market imbue configuration for the full workflow.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: ClawHub release evidence; 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>","readmeExcerpt":"Skill: vow-enforcement Owner: athola Summary: Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:13:38.587Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:34:58.005Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:51:41.555Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:00:38.244Z | user Release v1.9.14 v1.9.13 | 2026-06-27T1","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py"},{"language":"yaml","snippet":"validator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]"},{"language":"text","snippet":"specify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep"},{"language":"bash","snippet":"# Markdown wrap audit on a list of files\necho '{\"files\": [\"README.md\", \"docs/guide.md\"]}' \\\n  | python plugins/imbue/validators/markdown_wrap.py\n\n# Iron Law audit on an explicit commit log\necho '{\"commits\": [\n  {\"sha\": \"abc\", \"ts\": 100, \"files\": [\"tests/test_x.py\"]},\n  {\"sha\": \"def\", \"ts\": 200, \"files\": [\"src/x.py\"]}\n]}' | python plugins/imbue/validators/iron_law.py\n\n# Proof-of-work audit on agent output\necho '{\"text\": \"Tested foo [E1] [E2] [E3]. Status: PASS.\", \"min_evidence\": 3}' \\\n  | python plugins/imbue/validators/proof_of_work.py"},{"language":"yaml","snippet":"validator:\n  name: iron-law-court\n  constraint: \"Tests must drive implementation\"\n  inputs:\n    - git log with timestamps\n    - diff of test files vs implementation files\n  checks:\n    - test file modified before implementation file\n    - no test assertions changed to match output\n    - coverage did not decrease\n  output:\n    verdict: pass | violation | inconclusive\n    evidence: [list of specific findings]\n    recommendation: [action if violation]"},{"language":"text","snippet":"specify -> [Nen Court: spec review] -> plan\nplan    -> [Nen Court: plan review] -> execute\nexecute -> [Nen Court: justify]     -> pr-prep"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: vow-enforcement\ndescription: |\n  Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers\nversion: 1.9.8\ntriggers:\n  - enforcement\n  - constraints\n  - hooks\n  - compliance\n  - governance\n  - designing or auditing enforcement mechanisms for project rules\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/imbue\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.imbue:proof-of-work\", \"night-market.imbue:scope-guard\", \"night-market.imbue:justify\"]}}}\nsource: claude-night-market\nsource_plugin: imbue\n---\n\n> **Night Market Skill** — ported from [claude-night-market/imbue](https://github.com/athola/claude-night-market/tree/master/plugins/imbue). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> Rules that depend on willpower fail under pressure.\n> Enforcement earns trust by making the right path the\n> only path.\n\n# Vow Enforcement\n\n## Table of Contents\n\n- [The Problem](#the-problem)\n- [Three Enforcement Layers](#three-enforcement-layers)\n- [Vow Classification Protocol](#vow-classification-protocol)\n- [Night Market Vow Inventory](#night-market-vow-inventory)\n- [Vow Graduation Criteria](#vow-graduation-criteria)\n- [Nen Court Protocol](#nen-court-protocol)\n- [Integration Points](#integration-points)\n- [When to Use](#when-to-use)\n- [When NOT to Use](#when-not-to-use)\n\n## The Problem\n\nODCV-Bench found that agents break self-imposed\nconstraints 30-50% of the time when goals conflict.\nPractitioner consensus confirms: past 150 soft rules,\ncompliance drops for ALL rules, not just the new ones.\n\nThe core insight: \"settings.json is a firewall;\nCLAUDE.md is an employee handbook.\" Handbooks work for\nguidance. Firewalls work for enforcement. Mixing them\nup creates a false sense of security.\n\n## Three Enforcement Layers\n\n| Layer | Mechanism | Compliance | Examples |\n|-------|-----------|------------|---------|\n| **Soft Vow** | Skill instructions, CLAUDE.md rules | ~80% | \"Write tests first\", \"Keep commits small\" |\n| **Hard Vow** | Hooks (PreToolUse/PostToolUse), settings.json permissions | ~100% | Block `--no-verify`, enforce file size limits |\n| **Nen Court** | External validator agents checking output | Deterministic | Lint checks, test runs, constraint audits |\n\n**Soft Vows** rely on model compliance. Cheap to add\nand easy to iterate, but unreliable under goal\nconflict. Use when the constraint requires judgment,\nviolation is annoying but not dangerous, or you are\nstill learning what the right rule is.\n\n**Hard Vows** block forbidden actions before they\nexecute via hooks and settings.json permissions. Use\nwhen the constraint is binary, violation causes real\ndamage, or the soft vow version was violated\nrepeatedly.\n\n**Nen Court** spawns external validator agents that\naudit output after a phase completes. Use when the\nconstraint requires analysis (not pattern matching),\na hook cannot express the rule, or the check needs\ncodebas"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-imbue-vow-enforcement\",\n  \"version\": \"1.9.19\",\n  \"publishedAt\": 1787750018587\n}"},{"path":"skill-card.md","content":"## Description:\n\nClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers.\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 agent operators use this skill to classify project constraints as soft guidance, hooks, or validator checks, and to decide when compliance rules should graduate into stronger enforcement.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Broad trigger terms may activate the skill during general compliance or governance conversations.\n\nMitigation: Review whether the activation behavior fits the workflow before deployment.\n\nRisk: Overly strict hook or validator choices can block legitimate work if a rule is misclassified.\n\nMitigation: Use shadow-mode testing and false-positive monitoring before making enforcement blocking.\n\n## Reference(s):\n\n- [Vow Enforcement on ClawHub](https://clawhub.ai/athola/skills/nm-imbue-vow-enforcement)\n- [Configured homepage for the imbue plugin](https://github.com/athola/claude-night-market/tree/master/plugins/imbue)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Analysis, Configuration instructions, Shell commands]\n\n**Output Format:** [Markdown guidance with tables and inline shell and YAML examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [No direct execution; the skill provides guidance for classifying and auditing enforcement choices.]\n\n## Skill Version(s):\n\n1.9.19 (source: ClawHub release metadata; artifact frontmatter says 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":"Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers Skill: vow-enforcement Owner: athola Summary: Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:13:38.587Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:34:58.005Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:51:41.555Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:00:38.244Z | user Release v1.9.14 v1.9.13 | 2026-06-27T1","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1086,"uniquenessScore":55,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T19:48:25.049Z","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":"2026-10-11T19:48:25.049Z","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":"2026-10-11T23:19:19.379Z","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"}]}}}