Skip to main content
subagent CX Codex

perf-theory-gatherer — Claude Code subagent: what it does, install

perf-theory-gatherer analyzes git history and metrics to generate performance bottleneck hypotheses. Useful when investigating speed regressions across multiple runtimes.

MIT ★ 2,003 updated 2026-07-26

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add composio-community/awesome-claude-plugins
/plugin install perf@awesome-claude-plugins
Open on GitHub

What perf-theory-gatherer does

This subagent inspects git history alongside current metrics to detect performance bottlenecks. It runs on the opus model. Instead of inventing loose theories on its own, it collects repo boundaries and scenario details, then hands off the actual evaluation to the perf-theory-gatherer skill.

Tooling access includes file reading via Read and shell execution through Bash. The agent can invoke git, standard Node package managers, Go, Cargo, Python, pytest, Maven, and Gradle. That lets it inspect dependencies or run targeted profiling scripts directly.

Working with this agent requires a repository file at docs/perf-requirements.md. The subagent must read this file before producing output, and missing documentation blocks the run.

What it helps with

  • identify root causes of runtime regressions from commit history
  • generate performance bottleneck theories before running profiles
  • compare git revisions against requirements in docs/perf-requirements.md

Example prompts for the agent

  • Investigate recent commit history and list hypotheses for increased API latency.
  • Run perf-theory-gatherer to evaluate where throughput dropped in the last release.

How to install perf-theory-gatherer

1Plugin marketplace

/plugin marketplace add composio-community/awesome-claude-plugins
/plugin install perf@awesome-claude-plugins

2Manually: put the files in place

.claude/agents/perf-theory-gatherer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about perf-theory-gatherer

How to install perf-theory-gatherer in Claude Code?

Run /plugin marketplace add composio-community/awesome-claude-plugins, then execute /plugin install perf@awesome-claude-plugins. The agent definition sits at .claude/agents/perf-theory-gatherer.md.

What does perf-theory-gatherer do?

It inspects git logs and execution metrics to build testable theories about performance bottlenecks.

What files are required for perf-theory-gatherer to work?

The agent must inspect docs/perf-requirements.md before generating theories. Without this file, it refuses to produce output.

Source text

perf-theory-gatherer.md · MIT
---
name: perf-theory-gatherer
description: Generate top performance hypotheses after reviewing git history and current metrics.
tools: Read, Bash(git:*), Bash(node:*), Bash(npm:*), Bash(pnpm:*), Bash(yarn:*), Bash(cargo:*), Bash(go:*), Bash(pytest:*), Bash(python:*), Bash(mvn:*), Bash(gradle:*)
model: opus
---

# Perf Theory Gatherer

Generate hypotheses for performance bottlenecks and regressions. You MUST read `docs/perf-requirements.md` before outputting hypotheses.

You MUST execute the perf-theory-gatherer skill to produce hypotheses. Do not bypass the skill. This agent should only add agent-specific context (scenario, repo scope) and then run the skill.

© Community · MIT · composio-community/awesome-claude-plugins

Similar subagents

All subagents for Testing and QA →

From the same set68

The whole set →
perf-theory-gatherer perf-theory-gatherer — a skill that turns git history and code evidence into up to five hypotheses about a performance problem. CX Codex +1 2,300installs perf-benchmarker perf-benchmarker runs benchmarks sequentially under strict duration rules to catch performance regressions and set baseline metrics. CX Codex +1 2,300installs perf-analyzer perf-analyzer turns profiling and experiment results into evidence-backed performance recommendations. Use it when a decision needs a traceable basis. CX Codex +1 2,300installs bug-fix bug-fix takes a bug from a one-line description to a linked pull request: GitHub issue, branch, fix, commit, push, PR. CX Codex +1 ★ 2,003repo stars unpause-subs unpause-subs restores skill bus subscription handling after a pause. Use it when subscriptions were disabled for the project, globally, or at both levels. CX Codex +1 ★ 2,003repo stars unpause-subs unpause-subs restarts the skill bus after it has been paused and reactivates subscription handling. Use it to quickly return to normal operation after stopping the bus. CX Codex +1 ★ 2,003repo stars code-review code-review inspects recent repository changes using git context. It spots security flaws, performance bottlenecks, and test gaps before you push code. CX Codex +1 ★ 2,003repo stars list-subs list-subs inspects active skill-bus subscriptions across global and project settings. Use it to trace conditions and predict which skills would run. CX Codex +1 ★ 2,003repo stars

Project sponsors

Companies that keep this analytics open