perf-investigation-logger — Claude Code subagent
perf-investigation-logger — a subagent for structured documentation of performance investigations. Captures verbatim user statements, findings, and evidence in a single log.
MIT ★ 2,003 updated 2026-07-26
/plugin marketplace add composio-community/awesome-claude-plugins
/plugin install perf@awesome-claude-pluginsWhat perf-investigation-logger does
perf-investigation-logger automatically creates performance investigation records in a format aligned with your contract in docs/perf-requirements.md. The subagent collects exact user quotes, phase summaries, decisions with rationale, and pointers to evidence—files, commands, metrics.
Logs are written to {state-dir}/perf/investigations/<id>.md with phase, date, quote, evidence, and decision. It reads and writes directly, respecting the AI_STATE_DIR variable (defaults to .claude) and logging constraints.
Requires Claude Code with file read and write permissions.
What it helps with
- log performance investigations with user quotes verbatim
- connect decisions to evidence and code locations
- maintain a structured journal of analysis phases
- comply with
perf-requirements.mdwhen recording findings
Example prompts for the agent
- Investigate why rendering is slow in
src/render.jsand document the results - Create an investigation entry: user asked to check memory leak in
components/List - Record a profiling phase with the
node --prof app.jscommand and conclusions
How to install perf-investigation-logger
1Plugin marketplace
/plugin marketplace add composio-community/awesome-claude-plugins/plugin install perf@awesome-claude-plugins2Manually: put the files in place
.claude/agents/perf-investigation-logger.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/perf-investigation-logger.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/perf-investigation-logger.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about perf-investigation-logger
How do I install perf-investigation-logger in Claude Code?
Run these steps in order: /plugin marketplace add composio-community/awesome-claude-plugins, then /plugin install perf@awesome-claude-plugins, then open .claude/agents/perf-investigation-logger.md.
What does perf-investigation-logger do?
It writes structured investigation records with user quotes, phase summaries, decisions and file/command references to a log managed by AI_STATE_DIR.
Do I need to prepare perf-requirements.md first?
Yes. The subagent follows docs/perf-requirements.md as the canonical contract for log format and requirements.
Source text
perf-investigation-logger.md · MIT
---
name: perf-investigation-logger
description: Append structured investigation notes with exact user quotes and rationale.
tools: Read, Write
model: sonnet
---
# Perf Investigation Logger
You MUST follow `docs/perf-requirements.md` as the canonical contract.
Append structured investigation notes to `{state-dir}/perf/investigations/<id>.md`.
## Required Content
1. Exact user quotes (verbatim)
2. Phase summary
3. Decisions and rationale
4. Evidence pointers (files, metrics, commands)
## Output Format
```
## <Phase Name> - <YYYY-MM-DD>
**User Quote:** "<exact quote>"
**Summary**
- ...
**Evidence**
- Command: `...`
- File: `path:line`
**Decision**
- ...
```
## Constraints
- Use `AI_STATE_DIR` for state path (default `.claude`).
- Do not paraphrase user quotes.
You MUST execute the perf-investigation-logger skill to produce the log entry. Do not bypass the skill.
© Community · MIT · composio-community/awesome-claude-plugins