{"id":"c5e14497-57eb-4399-bf25-c38fcdf252aa","entityType":"agent","slug":"clawhub-athola-nm-sanctum-session-management","name":"session-management","canonicalUrl":"https://www.xpersona.co/agent/clawhub-athola-nm-sanctum-session-management","canonicalPath":"/agent/clawhub-athola-nm-sanctum-session-management","generatedAt":"2026-10-10T10:50:35.669Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T05:52:13.419Z","emptyReason":null},"description":"Manages Claude Code sessions with naming, checkpointing, and resume strategies Skill: session-management Owner: athola Summary: Manages Claude Code sessions with naming, checkpointing, and resume strategies Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:20:44.574Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:40:46.964Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:57:40.018Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:05:30.158Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-sanctum-session-management","sourceUrl":"https://clawhub.ai/athola/nm-sanctum-session-management","homepage":"https://clawhub.ai/athola/skills/nm-sanctum-session-management","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/athola/nm-sanctum-session-management","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/athola/skills/nm-sanctum-session-management","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":64,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Manages Claude Code sessions with naming, checkpointing, and resume strategies Skill: session-management Owner: athola Summary: Manages Claude Code sessions wit"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:52:13.419Z","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":"2026-10-10T05:52:13.419Z","emptyReason":null},"stars":null,"forks":null,"downloads":1639,"packageName":null,"latestVersion":"1.9.19","tractionLabel":"1.6K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:52:13.418Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T05:52:13.419Z","lastCrawledAt":"2026-10-10T05:52:13.418Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T05:52:13.418Z","lastVerifiedAt":null,"highlights":[{"version":"1.9.19","createdAt":"2026-08-26T13:20:44.574Z","changelog":"Release v1.9.19","fileCount":3,"zipByteSize":4611},{"version":"1.9.17","createdAt":"2026-07-30T05:40:46.964Z","changelog":"Release v1.9.17","fileCount":3,"zipByteSize":4705},{"version":"1.9.16","createdAt":"2026-07-14T19:57:40.018Z","changelog":"Release v1.9.16","fileCount":3,"zipByteSize":4640},{"version":"1.9.14","createdAt":"2026-06-30T18:05:30.158Z","changelog":"Release v1.9.14","fileCount":3,"zipByteSize":4663},{"version":"1.9.13","createdAt":"2026-06-27T16:23:21.702Z","changelog":"Release v1.9.13","fileCount":3,"zipByteSize":4552},{"version":"1.9.12","createdAt":"2026-06-19T03:18:47.864Z","changelog":"Release v1.9.12","fileCount":3,"zipByteSize":4649},{"version":"1.0.3","createdAt":"2026-06-18T15:20:32.872Z","changelog":"Release v1.9.12","fileCount":3,"zipByteSize":4798},{"version":"1.0.2","createdAt":"2026-05-09T02:19:59.463Z","changelog":"Release v1.9.5","fileCount":3,"zipByteSize":4644}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-sanctum-session-management","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-sanctum-session-management/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T10:50:35.666Z"}},"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-sanctum-session-management/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-sanctum-session-management/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":"2026-10-10T05:52:13.419Z","emptyReason":null},"readme":"Skill: session-management\n\nOwner: athola\n\nSummary: Manages Claude Code sessions with naming, checkpointing, and resume strategies\n\nTags: latest:1.9.19\n\nVersion history:\n\nv1.9.19 | 2026-08-26T13:20:44.574Z | user\n\nRelease v1.9.19\n\nv1.9.17 | 2026-07-30T05:40:46.964Z | user\n\nRelease v1.9.17\n\nv1.9.16 | 2026-07-14T19:57:40.018Z | user\n\nRelease v1.9.16\n\nv1.9.14 | 2026-06-30T18:05:30.158Z | user\n\nRelease v1.9.14\n\nv1.9.13 | 2026-06-27T16:23:21.702Z | user\n\nRelease v1.9.13\n\nv1.9.12 | 2026-06-19T03:18:47.864Z | user\n\nRelease v1.9.12\n\nv1.0.3 | 2026-06-18T15:20:32.872Z | user\n\nRelease v1.9.12\n\nv1.0.2 | 2026-05-09T02:19:59.463Z | user\n\nRelease v1.9.5\n\nv1.0.1 | 2026-05-06T14:21:23.243Z | user\n\nRelease v1.9.4\n\nv1.0.0 | 2026-04-20T12:01:27.254Z | auto\n\nSession management skill for Claude Code, enabling named sessions, checkpointing, and seamless session resumption.\n\n- Provides commands for naming, checkpointing, and resuming sessions across workflows.\n- Supports advanced resume and debugging flows including PR-linked sessions, feature milestones, and investigations.\n- Improved resume experience: Grouped forks, keyboard shortcuts, session preview, and context enrichment.\n- Automatic memory (Claude Code 2.1.32+): Summaries and key results are recalled in future sessions.\n- macOS orphaned process issue resolved (Claude Code 2.1.46+).\n- Optimized performance and bug fixes for session resume, duplicate entries, and agent persistence on resume.\n\nArchive index:\n\nArchive v1.9.19: 3 files, 4611 bytes\n\nFiles: skill-card.md (1792b), SKILL.md (7579b), _meta.json (149b)\n\nFile v1.9.19:SKILL.md\n\n---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.9.19:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.9.19\",\n \"publishedAt\": 1787750444574\n}\n\nFile v1.9.19:skill-card.md\n\n## Description:\n\nManages Claude Code sessions with naming, checkpointing, and resume strategies.\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 engineers use this skill to organize long-running Claude Code work, name sessions, create checkpoints, and resume prior work with retained context.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Named sessions and automatic memory can retain and later recall project context.\n\nMitigation: Avoid using named sessions or automatic memory for secrets, credentials, or highly sensitive projects unless retained context is acceptable.\n\nRisk: Resuming old sessions can bring stale or incomplete context into current work.\n\nMitigation: Review the resumed session context and refresh repository state before relying on prior conclusions.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/athola/skills/nm-sanctum-session-management)\n- [OpenClaw Homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, markdown, shell commands]\n\n**Output Format:** [Markdown guidance with inline command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Documentation-only skill; no API keys, MCP tools, or credential environment variables were detected.]\n\n## Skill Version(s):\n\n1.9.19 (source: server release evidence)\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, 4705 bytes\n\nFiles: skill-card.md (2123b), SKILL.md (7579b), _meta.json (149b)\n\nFile v1.9.17:SKILL.md\n\n---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.9.17:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.9.17\",\n \"publishedAt\": 1785390046964\n}\n\nFile v1.9.17:skill-card.md\n\n## Description:
\nManages Claude Code sessions with naming, checkpointing, and resume strategies.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nClaude Code users and developers use this skill to name, checkpoint, resume, and troubleshoot long-running sessions across interruptions or multi-day work.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Named sessions and automatic memory can retain sensitive context across conversations.
\nMitigation: Avoid placing credentials, regulated data, or sensitive incident details in conversations unless that retained context is acceptable.
\nRisk: Generic triggers may surface the skill for broad session or debugging topics.
\nMitigation: Confirm that named-session or resume guidance is relevant before applying it.
\nRisk: Old named sessions may preserve stale or unnecessary work context.
\nMitigation: Periodically clean up named sessions that are no longer needed.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-sanctum-session-management)
\n- [ClawHub publisher profile](https://clawhub.ai/user/athola)
\n- [OpenClaw homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, markdown, shell commands]
\n**Output Format:** [Markdown guidance with inline shell commands]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [No generated files; provides session-management guidance and command examples.]
\n\n## Skill Version(s):
\n1.9.17 (source: server release evidence; artifact frontmatter lists 1.9.8)
\n\n## Ethical Considerations:
\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 v1.9.16: 3 files, 4640 bytes\n\nFiles: skill-card.md (1940b), SKILL.md (7579b), _meta.json (149b)\n\nFile v1.9.16:SKILL.md\n\n---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.9.16:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.9.16\",\n \"publishedAt\": 1784059060018\n}\n\nFile v1.9.16:skill-card.md\n\n## Description:
\nManages Claude Code sessions with naming, checkpointing, and resume strategies.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineers use this skill to organize long-running Claude Code work, name useful checkpoints, resume prior sessions, and troubleshoot session continuity.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Resumed or named sessions can carry forward sensitive context longer than intended.
\nMitigation: Avoid placing secrets or regulated data in sessions intended for resume, and use fresh-session controls when prior context should not carry forward.
\nRisk: Old named sessions can accumulate stale or unnecessary work context.
\nMitigation: Periodically clean up named sessions that are no longer needed.
\n\n\n## Reference(s):
\n- [Nm Sanctum Session Management on ClawHub](https://clawhub.ai/athola/skills/nm-sanctum-session-management)
\n- [Sanctum homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)
\n\n\n## Skill Output:
\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]
\n**Output Format:** [Markdown narrative with command examples and troubleshooting guidance]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Documentation-only guidance; no persistent output file is specified.]
\n\n## Skill Version(s):
\n1.9.16 (source: server release evidence; artifact frontmatter lists 1.9.8)
\n\n## Ethical Considerations:
\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 v1.9.14: 3 files, 4663 bytes\n\nFiles: skill-card.md (2019b), SKILL.md (7579b), _meta.json (149b)\n\nFile v1.9.14:SKILL.md\n\n---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.9.14:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.9.14\",\n \"publishedAt\": 1782842730158\n}\n\nFile v1.9.14:skill-card.md\n\n## Description:
\nManages Claude Code sessions with naming, checkpointing, and resume strategies.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineers use this skill to organize long-running Claude Code work, name sessions, create useful checkpoints, and resume prior context when work spans multiple sittings.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Named and resumed sessions can preserve work context longer than users expect.
\nMitigation: Use descriptive names only for work that should be preserved, periodically clean up old sessions, and review Claude Code or plugin settings when enabling the separate Sanctum plugin.
\nRisk: Resumed sessions may carry stale or incomplete context into later work.
\nMitigation: Refresh project state before relying on resumed context and use the documented troubleshooting commands when session state appears incomplete.
\n\n\n## Reference(s):
\n- [Sanctum plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)
\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-sanctum-session-management)
\n\n\n## Skill Output:
\n**Output Type(s):** [Text, Markdown, Shell commands]
\n**Output Format:** [Markdown with inline shell commands and command examples]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Documentation-only guidance; no tool calls, credentials, or MCP integrations were detected.]
\n\n## Skill Version(s):
\n1.9.14 (source: server release evidence)
\n\n## Ethical Considerations:
\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 v1.9.13: 3 files, 4552 bytes\n\nFiles: skill-card.md (1673b), SKILL.md (7579b), _meta.json (149b)\n\nFile v1.9.13:SKILL.md\n\n---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.9.13:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.9.13\",\n \"publishedAt\": 1782577401702\n}\n\nFile v1.9.13:skill-card.md\n\n## Description:
\nManages Claude Code sessions with naming, checkpointing, and resume strategies.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineers use this skill to organize long-running Claude Code work, name checkpoints, and resume prior sessions with relevant context.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Named sessions and automatic memory can preserve summaries, results, and work logs across resumed sessions.
\nMitigation: Avoid placing secrets, credentials, or sensitive client data into workflows that may be resumed or recalled later.
\n\n\n## Reference(s):
\n- [ClawHub Skill Page](https://clawhub.ai/athola/skills/nm-sanctum-session-management)
\n- [Clawdis Homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)
\n\n\n## Skill Output:
\n**Output Type(s):** [Guidance, Markdown, Shell commands]
\n**Output Format:** [Markdown with inline shell command examples]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Documentation-only guidance; no executable files are included in the artifact.]
\n\n## Skill Version(s):
\n1.9.13 (source: server release evidence)
\n\n## Ethical Considerations:
\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 v1.9.12: 3 files, 4649 bytes\n\nFiles: skill-card.md (1997b), SKILL.md (7579b), _meta.json (149b)\n\nFile v1.9.12:SKILL.md\n\n---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.9.12:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.9.12\",\n \"publishedAt\": 1781839127864\n}\n\nFile v1.9.12:skill-card.md\n\n## Description:
\nManages Claude Code sessions with naming, checkpointing, and resume strategies.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineers use this skill to organize complex Claude Code work with named sessions, checkpoints, and resume patterns. It is most useful for debugging, feature development, PR review, and investigations that span multiple sessions.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Session names and resumed context may expose project details or stale assumptions from prior work.
\nMitigation: Use descriptive but non-sensitive session names and review resumed context before acting on it.
\nRisk: The security evidence recommends limiting installation to ClawHub staff or development contexts.
\nMitigation: Install only in staff or development environments and keep admin credentials limited.
\n\n\n## Reference(s):
\n- [ClawHub Skill Page](https://clawhub.ai/athola/nm-sanctum-session-management)
\n- [Sanctum Plugin Homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)
\n\n\n## Skill Output:
\n**Output Type(s):** [Guidance, Markdown, Shell commands]
\n**Output Format:** [Markdown with inline command examples]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Provides workflow patterns, naming conventions, troubleshooting guidance, and command examples for Claude Code session management.]
\n\n## Skill Version(s):
\n1.9.12 (source: server release evidence)
\n\n## Ethical Considerations:
\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 v1.0.3: 3 files, 4798 bytes\n\nFiles: skill-card.md (2343b), SKILL.md (7579b), _meta.json (148b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.0.3:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.0.3\",\n \"publishedAt\": 1781796032872\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:
\nManages Claude Code sessions with naming, checkpointing, and resume strategies.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineers use this skill to organize long-running Claude Code work, name sessions, resume prior work, and apply checkpointing patterns during debugging, feature work, PR review, and investigations.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill includes shell commands and session-resume commands that may act on local processes or workspace state.
\nMitigation: Review commands before execution and run them only in the intended local environment.
\nRisk: Named sessions and automatic memory can preserve project context longer than expected.
\nMitigation: Use non-sensitive session names, periodically clean up old sessions, and review retained context before resuming sensitive work.
\nRisk: Scanner telemetry is clean, but the security evidence advises reviewing skill files before granting file, command, network, or credential access.
\nMitigation: Install only the recognized publisher and version, then review the skill contents before enabling elevated agent access.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/athola/nm-sanctum-session-management)
\n- [Sanctum plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, markdown, shell commands]
\n**Output Format:** [Markdown guidance with inline Claude Code slash commands and shell commands]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Includes session naming patterns, resume workflows, checkpoint practices, and troubleshooting steps.]
\n\n## Skill Version(s):
\n1.0.3 (source: ClawHub release metadata; artifact frontmatter declares 1.9.8)
\n\n## Ethical Considerations:
\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 v1.0.2: 3 files, 4644 bytes\n\nFiles: skill-card.md (1988b), SKILL.md (7517b), _meta.json (148b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: session-management\ndescription: Manage Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.5\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.0.2:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1778293199463\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:
\nManage Claude Code sessions with naming, checkpointing, and resume strategies.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineers use this skill to organize long-running Claude Code work, name sessions, create practical checkpoints, and resume investigations, feature work, or PR reviews across sittings.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Named or resumed sessions can preserve sensitive context longer than intended.
\nMitigation: Avoid naming or resuming sessions that contain secrets you no longer need, and periodically clean up old named sessions.
\nRisk: The separate Sanctum Claude Code plugin may add behavior that was not reviewed in this artifact.
\nMitigation: Review the plugin separately before installing it; this card covers only the documentation-only skill artifact.
\n\n\n## Reference(s):
\n- [ClawHub release page](https://clawhub.ai/athola/nm-sanctum-session-management)
\n- [Sanctum homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, markdown, shell commands]
\n**Output Format:** [Markdown with inline Claude Code and shell command examples]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Documentation-only guidance; no executable code is included in the reviewed artifact.]
\n\n## Skill Version(s):
\n1.0.2 (source: server release metadata; artifact frontmatter states 1.9.5)
\n\n## Ethical Considerations:
\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 v1.0.1: 2 files, 3548 bytes\n\nFiles: SKILL.md (7517b), _meta.json (148b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: session-management\ndescription: Manage Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.4\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.0.1:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1778077283243\n}\n\nArchive v1.0.0: 2 files, 3548 bytes\n\nFiles: SKILL.md (7517b), _meta.json (148b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: session-management\ndescription: Manage Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.8.2\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions**: Sorted by last activity\n\n### 6. Resume Hint on Exit (Claude Code 2.1.31+)\n\nClaude Code now shows a resume hint when you exit, displaying the command to continue your conversation. This makes session resumption more discoverable — users no longer need to know about `--resume` beforehand.\n\n## Best Practices\n\n### Naming Conventions\n\nUse descriptive, hyphenated names:\n\n| Pattern | Example | Use Case |\n|---------|---------|----------|\n| `debugging-` | `debugging-auth-401` | Bug investigation |\n| `feature--` | `feature-search-v2` | Feature development |\n| `pr-review-` | `pr-review-156` | PR reviews |\n| `investigate-` | `investigate-perf` | Research |\n| `refactor-` | `refactor-api-layer` | Refactoring work |\n\n### When to Name Sessions\n\nName sessions when:\n- Work will span multiple days\n- You might need to pause unexpectedly\n- The session contains valuable context\n- You want to reference it later\n\n### Session Cleanup\n\nUnnamed sessions are eventually garbage collected. Named sessions persist longer. Periodically clean up old named sessions you no longer need.\n\n## Integration with Sanctum\n\nCombine session management with other Sanctum skills:\n\n1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context\n2. **Name the session**: `/rename `\n3. **Work**: Use appropriate skills for the task\n4. **Resume if needed**: `claude --resume `\n\n## Troubleshooting\n\n### Session Not Found\n\nIf a named session isn't appearing in `/resume`:\n- Check for typos in the name\n- Sessions may expire after extended inactivity\n- Use `/resume` screen to browse available sessions\n\n### Duplicate Sessions in VS Code\n\nIf you see duplicate session entries when resuming in VS Code:\n- **Claude Code 2.1.38+**: Fixed — resume now correctly reuses the existing session without creating duplicates\n- **Older versions**: Ignore the duplicate entries; they point to the same underlying session\n\n### Lost Context After Resume\n\nIf context seems incomplete or resume is slow:\n- **Claude Code 2.1.30+**: 68% memory reduction for `--resume` via stat-based session loading with progressive enrichment — especially impactful for users with many sessions. Also fixes hangs when resuming sessions with corrupted transcript files (parentUuid cycles).\n- **Claude Code 2.1.29+**: Fixed slow startup when resuming sessions with many `once: true` hooks — `saved_hook_context` loading is now optimized\n- **Claude Code 2.1.21+**: Fixed API errors when resuming sessions interrupted during tool execution — previously these sessions could fail to resume entirely\n- **Claude Code 2.1.20+**: Session compaction/resume is now fixed — resume correctly loads the compact summary instead of full history\n- Use `/catchup` to refresh git state\n- Use `/debug` (Claude Code 2.1.30+) for session troubleshooting diagnostics\n- Re-run `Skill(sanctum:git-workspace-review)` if needed\n- If on older versions: resumed sessions may reload uncompacted history, increasing context usage unexpectedly\n\n### macOS Orphaned Processes (Claude Code 2.1.46+)\n\nPreviously, disconnecting from a terminal on macOS could leave orphaned Claude Code processes running. This is now fixed in 2.1.46+. If you encounter stale CC processes on older versions, manually check and kill them:\n\n```bash\n# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep\n```\n\n### 7. Automatic Memory (Claude Code 2.1.32+)\n\nClaude now automatically records and recalls memories as it works. Session summaries, key results, and work logs are captured implicitly and recalled in future sessions. This provides passive cross-session continuity without manual checkpoint management.\n\n- **No action required**: Memory recording is automatic on first-party Anthropic API\n- **Complements named sessions**: Automatic memory handles implicit continuity; named sessions provide explicit organization\n- **Token overhead**: Recalled memories add to baseline context — factor this into MECW budgets\n\n### 8. Agent Persistence on Resume (Claude Code 2.1.32+)\n\n`--resume` now re-uses the `--agent` value from the previous conversation by default. Agent-specific workflows that are resumed will continue with the same agent configuration without needing to re-specify it.\n\n```\n# Start with a specific agent\nclaude --agent my-agent\n\n# Resume later — my-agent is automatically used\nclaude --resume\n```\n\n## See Also\n\n- `/catchup` - Refresh context from git changes\n- `/clear` - Start fresh session\n- `Skill(sanctum:git-workspace-review)` - Capture repo context\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1776686487254\n}","readmeExcerpt":"Skill: session-management Owner: athola Summary: Manages Claude Code sessions with naming, checkpointing, and resume strategies Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:20:44.574Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:40:46.964Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:57:40.018Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:05:30.158Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue"},{"language":"text","snippet":"# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed"},{"language":"text","snippet":"# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123"},{"language":"text","snippet":"# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156"},{"language":"text","snippet":"# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak"},{"language":"bash","snippet":"# Find orphaned claude processes\nps aux | grep -i claude | grep -v grep"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: session-management\ndescription: Manages Claude Code sessions with naming, checkpointing, and resume strategies\nversion: 1.9.8\ntriggers:\n - session\n - resume\n - checkpoint\n - debugging\n - organizing long-running work or resuming across sessions\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/sanctum\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: sanctum\n---\n\n> **Night Market Skill** — ported from [claude-night-market/sanctum](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n# Session Management\n\n\n## When To Use\n\n- Managing session checkpoints and state preservation\n- Resuming work across Claude Code sessions\n\n## When NOT To Use\n\n- Short sessions that do not need checkpoints\n- Fresh starts where no prior session context exists\n\n## Overview\n\nClaude Code supports named sessions for better workflow organization. Use this skill to manage complex, long-running work across multiple sessions.\n\n## Available Commands\n\n| Command | Description |\n|---------|-------------|\n| `/rename` | Name the current session (auto-generates name if no argument given, 2.1.41+) |\n| `/resume` | Resume a previous session (REPL) |\n| `claude --resume ` | Resume from terminal |\n\n## Workflow Patterns\n\n### 1. Debugging Sessions\n\nName debug sessions for easy resumption:\n\n```\n# Start debugging\n/rename debugging-auth-issue\n\n# ... work on the issue ...\n\n# If you need to pause, session is auto-saved\n# Resume later:\nclaude --resume debugging-auth-issue\n```\n\n### 2. Feature Development Checkpoints\n\nCreate checkpoints during long feature work:\n\n```\n# After completing milestone 1\n/rename feature-x-milestone-1\n\n# Continue in new session\n# Reference old session if needed\n```\n\n### 3. PR Review Sessions\n\nFor complex PR reviews that span multiple sittings:\n\n```\n# Start review\n/rename pr-review-123\n\n# Take breaks without losing context\n# Resume:\nclaude --resume pr-review-123\n```\n\n### 4. PR-Linked Sessions (Claude Code 2.1.27+)\n\nSessions are automatically linked to PRs when created via `gh pr create`. Resume PR-specific sessions later:\n\n```\n# Resume session for a specific PR\nclaude --from-pr 156\nclaude --from-pr https://github.com/org/repo/pull/156\n\n# Workflow: review → pause → resume with full context\n/rename pr-review-156\n# ... review work ...\n# Later:\nclaude --from-pr 156\n```\n\n### 5. Investigation Sessions\n\nWhen investigating issues that may require research:\n\n```\n# Start investigation\n/rename investigate-memory-leak\n\n# Pause to gather more info externally\n# Resume with full context:\nclaude --resume investigate-memory-leak\n```\n\n## Resume Screen Features\n\nThe `/resume` screen provides:\n\n- **Grouped forked sessions**: See related sessions together\n- **Keyboard shortcuts** (defaults, customizable via `/keybindings`):\n - Preview session content\n - Rename a session\n- **Recent sessions*"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-sanctum-session-management\",\n \"version\": \"1.9.19\",\n \"publishedAt\": 1787750444574\n}"},{"path":"skill-card.md","content":"## Description:\n\nManages Claude Code sessions with naming, checkpointing, and resume strategies.\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 engineers use this skill to organize long-running Claude Code work, name sessions, create checkpoints, and resume prior work with retained context.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Named sessions and automatic memory can retain and later recall project context.\n\nMitigation: Avoid using named sessions or automatic memory for secrets, credentials, or highly sensitive projects unless retained context is acceptable.\n\nRisk: Resuming old sessions can bring stale or incomplete context into current work.\n\nMitigation: Review the resumed session context and refresh repository state before relying on prior conclusions.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/athola/skills/nm-sanctum-session-management)\n- [OpenClaw Homepage](https://github.com/athola/claude-night-market/tree/master/plugins/sanctum)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, markdown, shell commands]\n\n**Output Format:** [Markdown guidance with inline command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Documentation-only skill; no API keys, MCP tools, or credential environment variables were detected.]\n\n## Skill Version(s):\n\n1.9.19 (source: server release evidence)\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":"Manages Claude Code sessions with naming, checkpointing, and resume strategies Skill: session-management Owner: athola Summary: Manages Claude Code sessions with naming, checkpointing, and resume strategies Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:20:44.574Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:40:46.964Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:57:40.018Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:05:30.158Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":894,"uniquenessScore":56,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T05:52:13.419Z","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":"2026-10-10T05:52:13.419Z","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":"2026-10-10T10:50:35.669Z","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"}]}}}