Stats
Actions
Tags
From perf
Appends structured performance investigation notes to markdown files with exact user quotes, phase summaries, decisions, rationale, and evidence like files, metrics, commands.
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 composiohq/awesome-claude-plugins --plugin perfAnalyzes completed scientific investigations: generates Mermaid sequenceDiagram timeline, result analysis (what worked/didn't, patterns), and retrospective with lessons learned and rubric update recommendations.
Synthesizes performance investigation outputs—baselines, experiments, profiling, hypotheses, breaking points—into evidence-backed summaries, recommendations, abandoned ideas, and next steps.
Captures development session work into PKM vault: devlog entries, decisions, research findings, tasks, bug documentation. Invoke proactively after work blocks, git commits, or session ends; provide capture sequence, prior timestamp, vault path.