rand

Bench — Development skill for Claude Code

Development community

Run performance benchmarks for RLM-Claude-Code.

How to install Bench

Installs to ~/.claude/commands/rand-rlm-claude-code-bench.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/rand/rlm-claude-code/HEAD/.claude/commands/bench.md -o ~/.claude/commands/rand-rlm-claude-code-bench.md

Restart Claude Code, or start a new session, for it to be picked up.

What Bench does

Run performance benchmarks for RLM-Claude-Code.

Commands

# All benchmarks
uv run pytest tests/benchmarks/ --benchmark-only

# With comparison to baseline
uv run pytest tests/benchmarks/ --benchmark-only --benchmark-compare

# Save results
uv run pytest tests/benchmarks/ --benchmark-only --benchmark-json=results.json

# Specific benchmark
uv run pytest tests/benchmarks/test_performance.py::test_complexity_classifier_latency --benchmark-only

Performance Targets

| Component |

Alternatives in Development

Skill Creator — Create new skills, modify existing skills, and measure skill performance 94.1k ★
Performance Reviewer 24.1k ★
KPI — PUA KPI 报告卡 — 生成段位和绩效报告 19.5k ★