diagnose
01Command Claude Code
Diagnose documentation issues and generate AI-ready fix prompts.
not rated 32
changed 6d ago A 10 tokens
original MIT
fix
02Command Claude Code
Fix documentation drift — mechanical (no AI) or AI-driven research, depending on the issue.
not rated 32
changed 6d ago A 18 tokens
original MIT
generate
03Command Claude Code
Reverse-engineer canonical documentation from existing codebase.
not rated 32
changed 6d ago A 9 tokens
original MIT
guard
04Command Claude Code
Run the full quality gate with severity triage and actionable remediation.
not rated 32
changed 6d ago A 12 tokens
original MIT
init
05Command Claude Code
Initialize Canonical-Driven Development in a project.
not rated 32
changed 6d ago A 9 tokens
original MIT
score
06Command Claude Code
Calculate CDD maturity score with multi-signal quality breakdown.
not rated 32
changed 6d ago A 11 tokens
original MIT
sync
07Command Claude Code
Refresh canonical code-truth sections and flag prose for review — refresh code-truth sections in place, preserve human prose.
not rated 32
changed 6d ago A 23 tokens
original MIT
trace
08Command Claude Code
Generate requirements traceability matrix.
not rated 32
changed 6d ago A 5 tokens
original MIT
docguard
09MCP server Claude CodeCodexCursor +2
Deterministic doc-drift detection: guard, score, explain, verify-claims and diagnose MCP tools. Runs locally from the docguard-cli npm package.
not rated 32 3d ago A
tokens not measured
original MIT
brief
10Command Claude Code
Load current spec intent and lifecycle before creating a new specification.
not rated 32
changed 6d ago A 11 tokens
original MIT
complete
11Command Claude Code
Review implementation evidence and plan the spec completion transaction.
not rated 32
changed 6d ago A 9 tokens
original MIT
preflight
12Command Claude Code
Gate a generated specification against registry integrity and prior intent.
not rated 32
changed 6d ago A 10 tokens
original MIT
review
13Command Claude Code
Review documentation against code without modifying the repository.
not rated 32
changed 6d ago A 8 tokens
original MIT
anchors
14Command Claude Code
List what each requirement tag anchors to (read-only).
not rated 32
changed 6d ago A 11 tokens
original MIT
Plugin Claude Code
Bundles 1 skill, 1 hook · 132 tokens together
Defensive, local-first security recon that briefs your AI coding agent on your OWN codebase. Read-only by default: facts + tailored probes + a calibrated findings ledger, code-in / artifacts-out, no LLM / no server / no running app. Live probes are opt-in against a TEST instance you own; production is out of scope.
not rated 2 yesterday A
tokens not measured
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: