adr
01Command Claude Code
Draft an Architecture Decision Record for a load-bearing decision.
not rated 20 3d ago A 10 tokens
original MIT
20Stars on the repository
48Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
cost
02Command Claude Code
Re-plan the current task to minimize model cost without losing quality.
not rated 20 3d ago A 12 tokens
original MIT
onboard
03Command Claude Code
Onboard into the current repo — detect stack, install deps, get build+test green, write a grounded CLAUDE.md, and print a codebase map.
not rated 20 3d ago A 33 tokens
original MIT
pr-shepherd
04Command Claude Code
Take every open PR end-to-end — diagnose, fix mechanical failures, stop at the merge gate.
not rated 20 3d ago A 19 tokens
original MIT
pr
05Command Claude Code
Open a pull request with a description generated from the diff.
not rated 20 3d ago A 11 tokens
original MIT
review
06Command Claude Code
Review the current diff for correctness, security, and conventions.
not rated 20 3d ago A 11 tokens
original MIT
scaffold
07Command Claude Code
Scaffold a new module/service following this repo's existing conventions.
not rated 20 3d ago A 12 tokens
original MIT
sdlc
08Command Claude Code
Run the headless SDLC pipeline (plan→build→review→audit→security→QA→PR) on a task.
not rated 20 3d ago A 25 tokens
original MIT
ship
09Command Claude Code
Pre-ship pipeline — test, review, then prepare a clean commit.
not rated 20 3d ago A 14 tokens
original MIT
spec
10Command Claude Code
Draft a lightweight spec / intent doc for a feature — the ground truth the build and review verify AGAINST. Use before non-trivial work; skip for one-liners. Writes a short, committed spec to specs/.
not rated 20 3d ago A 44 tokens
original MIT
tdd
11Command Claude Code
Test-driven change — write the failing test first, then implement.
not rated 20 3d ago A 12 tokens
original MIT
team-review
12Command Claude Code
Review the current diff with a coordinated agent TEAM (parallel reviewers that talk to each other) instead of sequential subagents. Experimental — needs CLAUDECODEEXPERIMENTALAGENTTEAMS=1.
not rated 20 3d ago A 41 tokens
original MIT
triage
13Command Claude Code
Triage a failing test, panic, CI failure, or error log.
not rated 20 3d ago A 14 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: