mcpField
P
perf-benchmarker

perf-benchmarker

github.com/agent-shTesting & quality1.0k88 installsUpdated today
Repository

About perf-benchmarker

perf-benchmarker is a benchmarking skill for running sequential performance tests under explicit timing and output rules. It is intended for users who need repeatable runs and structured metrics.

Key features

  1. 01Sequential benchmark runs
  2. 02Minimum run and warmup durations
  3. 03Anomaly reruns
  4. 04JSON metrics block output

Use cases

  1. 01Comparing performance across scenarios
  2. 02Running controlled benchmark measurements

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agent-sh/agentsys --skill perf-benchmarker

After installing, type/perf-benchmarkerin Claude Code to confirm it loaded.

Details

From the project README

perf-benchmarker

Run sequential benchmarks with strict duration rules.

Follow docs/perf-requirements.md as the canonical contract.

Parse Arguments

const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const command = args.find(a => !a.match(/^\d+$/)) || '';
const duration = parseInt(args.find(a => a.match(/^\d+$/)) || '60', 10);

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.

Comments

Markdown supported