Perf Theory Gatherer — Development agent for Claude Code
Generate top performance hypotheses after reviewing git history and current metrics.
How to install Perf Theory Gatherer
Installs to ~/.claude/agents/agent-sh-perf-perf-theory-gatherer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/agent-sh/perf/HEAD/agents/perf-theory-gatherer.md -o ~/.claude/agents/agent-sh-perf-perf-theory-gatherer.md Restart Claude Code, or start a new session, for it to be picked up.
What Perf Theory Gatherer does
name: perf-theory-gatherer description: Generate top performance hypotheses after reviewing git history and current metrics. tools:
- Skill
- 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 o
Alternatives in Development
- Startup Metrics Framework — Comprehensive guide to tracking, calculating, and optimizing key performance metrics for different s... - wsho 31.9k ★
- Civitai Perf Review — Reviews a feature segment in the main Civitai Next.js app (src/) for production performance — N+1 queries, uni 7.2k ★
- Brag Spotter — Proactively scans for achievements and wins that aren't in the brag doc yet 4.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Perf Engineer
Performance diagnosis specialist for the Hydraia pipeline. Measurement-first — establishes a baseline, profile
Perf Reviewer
Performance review specialist that analyzes code for performance anti-patterns and suggests optimizations. Use
Loop Perf Prep
Prepare lightweight performance checks (RPS/latency budget assertions) for the current loop iteration. Use pro
Perf Adversary
Red-team performance reviewer for in-flight code diffs. Reads a git diff and produces a ranked critique focuse
Perf Optimizer
Optimizes ported code for 68k hardware performance. Knows instruction timing, CHIP/FAST RAM characteristics, c
Frontend Perf Reviewer
Use AFTER frontend code is written to review for Core Web Vitals / runtime-performance regressions. Reports se
Related Skills
Autonomous Debugger
Evidence-driven debugging skill for Claude Code and AI coding agents. Investigates codebases, reproduces failu
Perf Audit
Baseline measurements + Top 5 bottlenecks per PERF.md (measurement-only, no edits)
Ab Test
Design A/B tests with clear hypotheses, success metrics, sample size requirements, and duration estimates.