benchmark
01Command Claude Code
Benchmark aicrew skill quality, trigger accuracy, token efficiency, and pipeline timing.
not rated 3 3mo ago A 16 tokens
original MIT
3Stars on the repository
35Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
brainstorm
02Command Claude Code
Generate 3 materially different implementation options with trade-offs before coding.
not rated 3 3mo ago A 12 tokens
original MIT
conclude
03Command Claude Code
Use at session end to save project learnings and produce a commit message.
not rated 3 3mo ago A 14 tokens
original MIT
dev
04Command Claude Code
Use when starting any development task — bug fix, feature, or refactor.
not rated 3 3mo ago A 15 tokens
original MIT
fix
05Command Claude Code
Use for a fast bug fix with minimal ceremony (3 questions, TDD, done).
not rated 3 3mo ago A 18 tokens
original MIT
handoff
06Command Claude Code
Generate a compact cross-tool handoff block from current session state.
not rated 3 3mo ago A 12 tokens
original MIT
Command Claude Code
Use when auditing the Claude Code / AI harness setup for reliability, cost, and completeness.
not rated 3 3mo ago A 17 tokens
original MIT
lean
08Command Claude Code
Boost or disable lean mode: terse output plus context-economy reads (default is already lean).
not rated 3 3mo ago A 20 tokens
original MIT
normal
09Command Claude Code
Alias for /lean off — restore verbose output.
not rated 3 3mo ago A 9 tokens
original MIT
quick
10Command Claude Code
Scout → Act flow with graph-first discovery, speculative context, and Karpathy guardrails (no full /dev pipeline).
not rated 3 3mo ago A 24 tokens
original MIT
session
11Command Claude Code
Set session label for state checkpoints (multi-tool safe).
not rated 3 3mo ago A 11 tokens
original MIT
terse
12Command Claude Code
Reinforce default terse output (already on by default).
not rated 3 3mo ago A 12 tokens
original MIT
Command Claude Code needs its repo
Use when maintaining, improving, or adding to the /Agents/ skills system.
not rated 3 3mo ago A 15 tokens
original MIT
audit
14Command Claude Code
Run this checklist against all changed files before declaring work done.
not rated 3 3mo ago A 16 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: