AI slop audit. Finds dead code, orphan helpers, noop functions, tautological guards, redundant implementations, and over-engineered abstractions. Read-only static analysis. Uses a discovery-first protocol to build a per-project call-site manifest before scanning — prevents the false-positive wall that hits naive…
You are running the /r-audit full codebase audit. This command dispatches multiple reviewer and qa subagents in parallel to scan the entire codebase for latent issues, then synthesizes findings into a structured AUDIT.md.
Measure, score, and report on Claude Code context overhead for this workspace. Identifies bloat, tracks drift from baseline, and produces actionable optimization recommendations.
Governance initialization for any codebase. Scans the project, ingests existing convention files, detects languages and tooling, and generates supplementary governance under .rdf/governance/.
Take a spec (or equivalent input) and decompose it into an execution-grade implementation plan written to docs/plans/{YYYY-MM-DD}-{topic}-plan.md. You never write code. You produce plans.
You are running the /r-refresh governance refresh. This command re-scans the codebase and updates governance files to match current reality, preserving user modifications.
You are running the /r-ship release workflow. This is a composite workflow that verifies readiness, dispatches quality gates, prepares release artifacts, and publishes a PR.
Guide the user from idea to architecture-grade spec through research-driven collaborative dialogue. You never write code. You produce design documents.
Reload context and display project health. This is the recommended first command in any session. It gives the agent a warm handoff — enough context to continue where the last session left off.
You are running the /r-sync canonical source synchronization. This is an RDF-internal command that pulls emergency edits made directly to /.claude/ back into the rdf canonical source tree.
Deduplicate changelog entries for the current version. Scans CHANGELOG and CHANGELOG.RELEASE for duplicates, overlapping entries, tracking artifacts, fluff, and section proliferation. Report mode by default — only modify files when explicitly told to fix.
Analyze recent conversations to find improvements for CLAUDE.md files, and audit existing CLAUDE.md content for prose drift and memory-bound state contamination. Read-only report — no modifications.
Structural map of a source file — classes, functions, methods with line ranges. Reduces context cost when an agent needs one symbol from a large file by letting it read only the relevant line range.
Assess codebase modernization maturity and generate a phased remediation plan. This is a read-only assessment — it does NOT modify any project files.
★not rated 17
changed todayA0 tokens
GPL-2.0
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: