perf-benchmarker

Original：🇺🇸 English

Translated

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.

3installs

Sourcecomposio-community/awesome-claude-plugins

Added on2026-08-11

NPX Install

npx skill4agent add composio-community/awesome-claude-plugins perf-benchmarker

SKILL.md Content

View Translation Comparison →

perf-benchmarker

Run sequential benchmarks with strict duration rules.

docs/perf-requirements.md

as the canonical contract.

Required Rules

Benchmarks MUST run sequentially (never parallel).
Minimum duration: 60s per run (30s only for binary search).
Warmup: 10s minimum before measurement.
Re-run anomalies.

Output Format

command: <benchmark command>
duration: <seconds>
warmup: <seconds>
results: <metrics summary>
notes: <anomalies or reruns>

Output Contract

Benchmarks MUST emit a JSON metrics block between markers:

PERF_METRICS_START
{"scenarios":{"low":{"latency_ms":120},"high":{"latency_ms":450}}}
PERF_METRICS_END

Constraints

No short runs unless binary-search phase.
Do not change code while benchmarking.

perf-benchmarker

NPX Install

Tags

SKILL.md Content

perf-benchmarker

Required Rules

Output Format

Output Contract

Constraints