benchmark-runner

SkillDev tools

Run performance benchmarks with criterion. Compare against baselines and profile hotspots.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the benchmark-runner skill

What this skill tells your AI

The instructions your AI receives, as published by nwiizo/ccswarm in .agents/skills/benchmark-runner/SKILL.md and read by ahel’s review.

Run performance benchmarks on ccswarm.

Run Benchmarks

cargo build --release --workspace

# All benchmarks
cargo bench --workspace

# Specific benchmark
cargo bench -- "$ARGUMENTS"

# Save baseline for comparison
cargo bench -- --save-baseline before
# ... make changes ...
cargo bench -- --baseline before

Profile

cargo flamegraph --bench ${1:-orchestrator_bench}

Key Metrics

AreaTarget
Task delegation< 1ms
Full workflow< 100ms
Memory per agent< 10MB
Variance< 20%

Results in target/criterion/report/index.html.

Signals

GitHub stars
151
Forks
15
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
benchmark-runner
Source
github.com/nwiizo/ccswarm