Skip to main content
subagent CX Codex

perf-theory-tester — Claude Code subagent: tests and install

The perf-theory-tester subagent tests performance hypotheses with controlled runs. It changes one thing at a time, compares results with a baseline, and rolls the change back.

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-tester does

perf-theory-tester runs performance experiments with a single change in each run. It checks that the repository is clean, applies the change, executes a sequential benchmark at least twice, records metrics and variance, then restores the previous state. Its report contains the baseline, the experiment result, the delta, and a supports, refutes, or inconclusive verdict.

The workflow follows docs/perf-requirements.md. The subagent can read, write, and edit files, and use Bash for git, package managers, tests, and build tools such as npm, pnpm, yarn, cargo, go, pytest, python, mvn, gradle, and node. Benchmarks must run sequentially for at least 60 seconds; 30 seconds is allowed only for binary search. A clean git status is required before an experiment can start.

What it helps with

  • test how one code change affects performance
  • compare a run against a clean baseline
  • restore the project between experiments
  • record measurement variance
  • classify conflicting results as inconclusive

Example prompts for the agent

  • Use perf-theory-tester to compare the current implementation with one performance change, then restore the baseline.
  • Run a controlled benchmark twice, record the metrics and variance, and report the delta.
  • If the measurements disagree, repeat the experiment and mark the verdict inconclusive.

How to install perf-theory-tester

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-tester.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-tester

How do I install perf-theory-tester in Claude Code?

Run /plugin marketplace add composio-community/awesome-claude-plugins, then /plugin install perf@awesome-claude-plugins, and add .claude/agents/perf-theory-tester.md.

What does perf-theory-tester do?

It tests performance hypotheses through controlled experiments. Each run applies one change, compares the result with a baseline, and rolls the change back before the next experiment.

What conditions does an experiment follow?

The repository must be clean, each experiment must contain one change, and the benchmark must run at least twice. Runs are sequential and last at least 60 seconds; 30 seconds is reserved for binary search.

Source text

perf-theory-tester.md · MIT
---
name: perf-theory-tester
description: Execute controlled perf experiments, one change at a time, with rollback between runs.
tools: Read, Write, Edit, Bash(git:*), Bash(npm:*), Bash(pnpm:*), Bash(yarn:*), Bash(cargo:*), Bash(go:*), Bash(pytest:*), Bash(python:*), Bash(mvn:*), Bash(gradle:*), Bash(node:*)
model: opus
---

# Perf Theory Tester

Test hypotheses using controlled experiments. You MUST follow `docs/perf-requirements.md`.

You MUST execute the perf-theory-tester skill to produce the output. Do not bypass the skill.

## Rules

- One change per experiment.
- Revert to baseline between experiments.
- Run each experiment at least twice.
- Benchmarks must be sequential and ≥60s (30s only for binary search).

## Workflow

1. Check out clean baseline (`git status` must be clean).
2. Apply single change for the experiment.
3. Run benchmark twice.
4. Record metrics + variance.
5. Revert change and confirm clean state.

## Output Format

```
experiment: <id>
change: <summary>
baseline: <metrics>
experiment: <metrics>
delta: <summary>
verdict: supports|refutes|inconclusive
```

## Constraints

- Do NOT stack multiple changes.
- If results conflict, re-run and mark inconclusive.

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

Similar subagents

All subagents for Testing and QA →

From the same set68

The whole set →
pause-subs pause-subs is a Claude Code skill that temporarily disables skill-bus subscriptions without removing their settings, for tasks interrupted by background triggers. CX Codex +1 ★ 2,003repo stars create-pr create-pr is a Claude Code command that turns working changes into a pull request. It branches the work, formats edited files, and prepares commits. CX Codex +1 ★ 2,003repo stars commit A slash command that builds your git commit: stages files, writes a conventional-commit message with an emoji, and runs the project's checks first. CX Codex +1 ★ 2,003repo stars list-subs list-subs inspects active skill-bus subscriptions across global or project scopes and simulates event matching for individual skills. CX Codex +1 ★ 2,003repo stars pr-review pr-review is a Claude Code command that examines pull request changes before they are merged. Its template reviews a patch from six different professional perspectives. CX Codex +1 ★ 2,003repo stars setup setup configures the connect-apps plugin so Claude Code can trigger actions in external services like Gmail, Slack, and GitHub through Composio. CX Codex +1 ★ 2,003repo stars report report is a Claude Code command that shows skill-bus subscription matches, condition skips, and skills without subscriptions to help find coverage gaps. CX Codex +1 ★ 2,003repo stars complete A signal command: Claude runs it by itself once a skill with "when": "complete" subscriptions has finished, and a hook starts the next steps in the chain. CX Codex +1 ★ 2,003repo stars

Project sponsors

Companies that keep this analytics open