Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From perf
Append structured investigation notes for performance debugging, preserving exact user quotes, decisions, rationale, and evidence pointers.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
perf:agents/perf-investigation-loggersonnetThe summary Claude sees when deciding whether to delegate to this agent
You MUST follow `docs/perf-requirements.md` as the canonical contract. Append structured investigation notes to `{state-dir}/perf/investigations/<id>.md`. 1. Exact user quotes (verbatim) 2. Phase summary 3. Decisions and rationale 4. Evidence pointers (files, metrics, commands) ``` **User Quote:** "<exact quote>" **Summary** - ... **Evidence** - Command: `...` - File: `path:line` **Decision** -...You MUST follow docs/perf-requirements.md as the canonical contract.
Append structured investigation notes to {state-dir}/perf/investigations/<id>.md.
## <Phase Name> - <YYYY-MM-DD>
**User Quote:** "<exact quote>"
**Summary**
- ...
**Evidence**
- Command: `...`
- File: `path:line`
**Decision**
- ...
AI_STATE_DIR for state path (default .claude).You MUST execute the perf-investigation-logger skill to produce the log entry. Do not bypass the skill.
npx claudepluginhub composio-community/awesome-claude-plugins --plugin perf3plugins reuse this agent
First indexed Feb 9, 2026
Logs learnings, errors, and corrections to .learnings/ files. Spawnable by other agents or at session end for quality/security findings, user corrections, command failures, or knowledge gaps. Deduplicates entries and flags promotion candidates.
Documents development incidents — test failures, production bugs, failed refactors, performance issues, security vulnerabilities, and problematic architectural decisions. Captures what went wrong, what was tried, and what was learned. Use after Phase 6 (Reflect) or during escalation.
Analyzes completed investigations to produce structured process-quality artefacts: timeline (mermaid diagram), result analysis, and retrospective with lessons learned. Invoke after investigation reaches resolved-verified status.