parity-check
01Command Claude Code
Report safeword parity drift (pairs + contracts). Safeword-repo only.
not rated 11
+1 3d ago A 18 tokens
11Stars on the repository
88Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
audit
02Command Claude CodeCursor
Run comprehensive code audit for architecture, dead code, and test quality.
not rated 11
+1 3d ago A 13 tokens
bdd
03Command Claude CodeCursor
BDD orchestrator for feature-level work. Use when user says 'add', 'implement', 'build', 'feature', 'iteration', 'story', 'phase', 'resume', 'continue', or references a ticket/iteration/story. Also use when work touches 3+ files with new state/flows, or when user runs /bdd. Do NOT use for bug fixes, typos, config…
not rated 11
+1 3d ago A 90 tokens
Command Claude CodeCursor
Kill zombie dev servers and test processes for this project.
not rated 11
+1 3d ago A 10 tokens
closeout
05Command Claude CodeCursor
Close a completed local delivery safely after verification. Use when wrapping up a finished coding session: merging only when you've been explicitly told to merge, running the retro, and cleaning up the exact merged branch and worktree.
not rated 11
+1 3d ago A 0 tokens
debug
06Command Claude CodeCursor
Finds the real cause of a bug, in four steps, before you touch a fix. Use when encountering bugs, test failures, unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline ('debug this', 'fix this error', 'test is failing', 'not working').
not rated 11
+1 3d ago A 60 tokens
explain
07Command Claude CodeCursor
Plain-English view of any safeword block, verdict, ticket, or your current state (project).
not rated 11
+1 3d ago A 21 tokens
Command Claude CodeCursor
Internal fallback used only right after the shared review coordinator reports it's run out of reviewer routes. Not something a user invokes directly.
not rated 11
+1 3d ago A 25 tokens
lint
09Command Claude CodeCursor
Run bounded linters and formatters for changed files (project).
not rated 11
+1 3d ago A 13 tokens
Command Claude CodeCursor
Deep code review with web research. Use when the user says 'double check against latest', 'verify versions', or 'check security'. Adds live research on top of the automatic quality hook — confirms you're using current library versions and APIs, not stale ones.
not rated 11
+1 3d ago A 51 tokens
refactor
11Command Claude CodeCursor
Systematic refactoring with small-step discipline. Use when user says 'refactor', 'clean up', 'restructure', 'extract', 'rename', 'simplify', or mentions code smells. Enforces one change → test → commit when the commit can stay scoped. For structural improvements, NOT style/formatting (use /lint). NOT for adding…
not rated 11
+1 3d ago A 77 tokens
retro
12Command Claude CodeCursor
Run a safeword retrospective on the current session on demand — mine the transcript for friction (bugs / rough edges / gaps) and submit it through the outbound safety check before filing upstream. Use when the user says "run a retro", "/retro", or wants to capture friction before the session ends.
not rated 11
+1 3d ago A 61 tokens
review-spec
13Command Claude CodeCursor
Red-teams a ticket's test scenarios for gaps — cases that would pass even though the feature is broken (project).
not rated 11
+1 3d ago A 24 tokens
self-review
14Command Claude CodeCursor
Self-review the spec inline and earn its Tier 1 review stamp (project).
not rated 11
+1 3d ago A 16 tokens
spike
15Command Claude CodeCursor
Run a quick, throwaway experiment to answer one open technical question before committing to the real build. Only runs when you ask for it directly.
not rated 11
+1 3d ago A 29 tokens
testing
16Command Claude CodeCursor
How to write good tests — quality knowledge for any testing context.
not rated 11
+1 3d ago A 12 tokens
verify
17Command Claude CodeCursor
Verify ticket completion criteria — tests, build, lint, scenarios, dependency drift.
not rated 11
+1 3d ago A 15 tokens
Command Claude CodeCursor
Tests whether a proposed product bet has credible demand. Use when Why now depends on an unresolved, decision-critical demand claim or when the user explicitly asks for demand research. Do NOT use for child features, mandated work, parity work, or when a cheaper experiment can answer the question first.
not rated 11
+1 3d ago A 57 tokens
pr-readiness
19Command Claude CodeCursor
Prepare a pull request for human review and decide whether it may leave Draft. Use when creating or rewriting a PR description, marking a PR ready, responding to review, or checking mergeability.
not rated 11
+1 3d ago A 38 tokens
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: