Command Claude Code
Judge code comments against the forbidden/false/stale/narration/noise/keep rubric and emit structured findings. Usage: /comment-judge.
not rated 171 yesterday A 0 tokens
original MIT
171Stars on the repository
197Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Command Claude Code
Spawn Haruspex Commentorum, fix accepted comment findings, and offer encodings for claimed constraints. Usage: /interfectio-commentarum [path|diff].
not rated 171 yesterday A 0 tokens
original MIT
show-me
51Command Claude Code
Explain a topic visually by producing a self-contained HTML artifact (diagram, infographic, or short slide deck) and opening it. Usage: /show-me.
not rated 171 yesterday A 0 tokens
original MIT
Command Claude Code
Keep a reviewable TSV decision trail for long-running or unattended work. Usage: /show-your-work [task-slug].
not rated 171 yesterday A 0 tokens
original MIT
blast-radius
53Command Claude Code
Find what a change could break beyond the diff before it ships, and prove the one fact it's safe because of by running real code instead of writing it up. Usage: /blast-radius.
not rated 171 yesterday A 0 tokens
original MIT
chimera
54Command Claude Code
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it, and verify the synthesized result. Usage: /chimera.
not rated 171 yesterday A 0 tokens
original MIT
fix-ci
55Command Claude Code
Find failing PR checks, inspect logs or check links, and apply focused fixes. Routing depends on failure type (build/test/security). Usage: /fix-ci [branch|PR].
not rated 171 yesterday A 0 tokens
original MIT
Command Claude Code
Resolve merge conflicts via rebase, validate build and tests, and finalize with a backup branch — linear history, never force-push without explicit consent. Usage: /fix-merge-conflicts.
not rated 171 yesterday A 0 tokens
original MIT
for-real
57Command Claude Code
Restate the last message in plain human language, with no jargon. Usage: /for-real.
not rated 171 yesterday A 0 tokens
original MIT
Command Claude Code
Fetch and summarize review comments from the active pull request, grouped by severity and actionability. Usage: /get-pr-comments [PR].
not rated 171 yesterday A 0 tokens
original MIT
loop-on-ci
59Command Claude Code
Monitor PR checks until green — watch required checks, fix failures via fix-ci, iterate until all pass. Capped at 5 iterations. Usage: /loop-on-ci [branch|PR].
not rated 171 yesterday A 0 tokens
original MIT
why
60Command Claude Code
Investigate why code is shaped the way it is — design rationale, regressions, postmortems, data-backed thresholds — by querying historical-evidence MCPs in parallel and returning a cited read on decisions and tradeoffs. Usage: /why.
not rated 171 yesterday A 0 tokens
original MIT
autonomous
61Command Claude Code
Turn autonomous mode on, off or status via the autonomous skill.
not rated 171 yesterday A 12 tokens
original MIT
ship
62Command Claude Code
Deliver one goal end to end (clarify, implement, PR, review, CI, merge) via the ship skill.
not rated 171 yesterday A 24 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: