Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.
Skill Claude CodeCodex
Audit, explain, or compare existing Tenuo warrants and delegation chains. Use for review-only requests about effective authority, blast radius, chain validity, or authorization risk. Do not use to implement enforcement in an application or tool boundary (use tenuo-agent-authorization).
Skill Claude CodeCodex needs its repo
Create or delegate Tenuo warrants from natural-language authority requirements. Use when designing capabilities and constraints, minting a warrant, or narrowing authority for a child agent. Do not use for integrating enforcement into an application or tool boundary (use tenuo-agent-authorization), or for a review-only…
Skill Claude CodeCodex
Add or retrofit Tenuo authorization for AI-agent tools and effects. Use when implementing Tenuo, protecting an MCP or framework tool, choosing a gateway, sidecar, or embedded enforcement boundary, or testing that an agent cannot exceed delegated authority. Do not use for a review-only audit of an existing warrant.
Skill Claude CodeCodex
Diagnose a denied Tenuo call and make the legitimate call work with the smallest change to authority. Use when a call, test, or agent step fails with a Tenuo denial, monotonicity, proof-of-possession, chain, expiry, approval, or unknown-argument error. Do not use to design new authority from scratch (use…
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: