claude-code-plugin-ref…
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
Summarizes recent git changes for context recovery after session breaks. Use when resuming work after a gap or handing off to another session.
$ npx -y skills add athola/claude-night-market --skill catchup --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/catchupContext preview
The summary Claude sees to decide when to auto-load this skill.
Summarizes recent git changes for context recovery after session breaks. Use when resuming work after a gap or handing off to another session.
name: catchup description: Summarizes recent git changes for context recovery after session breaks. Use when resuming work after a gap or handing off to another session. alwaysApply: false category: analysis-methods tags: - summarization - context-acquisition - insights - follow-ups dependencies: - imbue:proof-of-work tools: [] usage_patterns: - context-catchup - handoff-preparation - progress-review complexity: intermediate model_hint: fast estimated_tokens: 700 progressive_loading: true module_strategy: context-based role: entrypoint
Structured method for quickly understanding recent changes in git repositories, meeting notes, sprint progress, document revisions, or system logs. Answers "what changed and what matters?" efficiently.
diff analysis - use diff-analysis instead
**Keywords**: catchup, summary, status, progress, context, handoff **Cues**: "get me up to speed", "current status", "summarize progress"
Load modules based on context:
**Git**: Load `modules/git-catchup-patterns.md` for git commands. Consider `sanctum:git-workspace-review` for initial data gathering.
**Documents/Notes**: Load `modules/document-analysis-patterns.md` for meeting notes, sprint tracking, document revisions.
**Logs/Events**: Load `modules/log-analysis-patterns.md` for time-series and metric analysis.
**Always Available**: `imbue:proof-of-work`, TodoWrite workflow, structured output.
1. `catchup:context-confirmed` - Boundaries established 2. `catchup:delta-captured` - Changes enumerated 3. `catchup:insights-extracted` - Themes identified 4. `catchup:followups-recorded` - Actions captured
Define scope (git branch, sprint, meetings), baseline (last state), and current target. See modules for commands.
Enumerate changed items with metrics. Prioritize source/config/docs over generated artifacts. See modules for strategies.
Per item: **What** (change), **Why** (motivation), **Implications** (tests/risks/deps). Rollup into themes.
Capture: Tests, Documentation, Reviews, Blockers, Questions. If none, state explicitly.
## Summary [2-3 sentence theme + risk overview] ## Key Changes - [Item]: [what/why/implication] ## Follow-ups - [ ] [Action with owner] ## Blockers/Questions - [Item requiring resolution]
**Verification:** Run the command with `--help` flag to verify availability.
Use `imbue:diff-analysis` for risk assessment, `imbue:proof-of-work` for reproducibility, `sanctum:git-workspace-review` for git data. Feed to `brainstorming` or `writing-plans` as needed.
Reference paths and lines (don't reproduce). Summarize outputs. Defer deep analysis. Use progressive loading.
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
States load-bearing decisions, invariants, and weak points. Use when judging a design change. Do not use for gating; use night-market-change-control.
Rebuild the dev environment: uv, Python tiers, pins, traps. Use when onboarding or toolchain breaks. Do not use for daily commands; use night-market-operations.
Classify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage; use night-market-debugging-playbook.
Search and record project memory (Discussions, journal, ADRs). Use before re-investigating anything. Do not use for settled battles; see failure-archaeology.
Bind loop 'done' to unfakeable gates. Use to harden egregore/herald loops or promote completion_integrity. Not for QA gates; use night-market-validation-and-qa.