Initialize Compound V in this project — detect backends and capabilities (Codex, Context7, required skills/agents), walk through any missing installs one at a time, pick a routing stance, and save project + user config.
Refresh the Compound V tier→model map — discover the concrete models each backend (claude, codex, antigravity, cursor, devin, opencode) currently offers, show them, let you assign deep/standard/light, and write the result into .claude/compound-v.json so intent-based routing survives model churn without touching any…
Aktualisiert das legal-audit-de Plugin selbst (neue Plugin-Version vom Marketplace ziehen) UND refreshed die KB gegen Primärquellen. All-in-One-Update.
Live-Rechts-Check einer oeffentlichen Website via chrome-devtools-mcp — testet Cookie-Banner-Blocking, Drittanbieter-Leaks VOR Consent, Google-Fonts-Leak, Embed-Verhalten, tatsaechlich gesetzte Cookies. Ergaenzt /legal-audit um die Verhaltens-Dimension.
Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a probe id substring to filter.
Author a new skill from scratch with paired trigger fixtures and full validation. Use when adding a skill that has no upstream skills.sh source (discipline, meta, or internal-pattern skills).
Save current session work to project memory. Updates MEMORY.md with completed tasks, decisions, and discoveries from this session.
30 2mo agoA23 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: