The agent harness that makes small local models finish hard tasks — and prove it. Done is enforced by the engine, not the prompt: gates, rewinds, a judge, and a replayable Proof-of-Done receipt on every finished run. Any model in the socket. Local, sovereign, air-gapped-capable. macOS · Linux · Windows.
Skill Claude CodeCodex
Load BEFORE creating a git commit or a GitHub pull request. Step-by-step protocol for drafting commit messages, staging safely, amend rules, and gh pr create choreography.
Skill Claude CodeCodex
Use when you want to evolve your own capabilities — create new tools to avoid repeating patterns, add hooks to improve your own behavior, build skills to accumulate domain knowledge, or override built-in tools to adapt to project needs. This is your self-iteration interface.
Skill Claude CodeCodex
Use whenever you need a decision, clarification, or approval from the user — covers how to ask with the question tool, and how to resolve the decision yourself when no user is available (question tool absent, or a [Never-Ask] response).
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Skill Claude CodeCodex
Use when you have a written implementation plan to execute in a separate session with review checkpoints.
Skill Claude CodeCodex
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
Skill Claude CodeCodex
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
Skill Claude CodeCodex
Use when creating new skills or editing existing skills for the project or personal skill library.
Skill Claude CodeCodex
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
Skill Claude CodeCodex
Use when you have a spec or requirements for a multi-step task, before touching code.
Skill Claude CodeCodex needs its repo
Use after implementation is verified and before merge — consolidates multiple spec iterations into a single final-state report, marks related specs, and records key lessons.
Skill Claude CodeCodex
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code.
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
Skill Claude CodeCodex
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
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: