This repository also configures its own agents. See what ai-conductor tells them →
Skill Claude CodeCodex
Use when buildreview fails or, at SHIP, when prd-audit, the as-built architecture review, or finish verification blocks. Emits a per-gap disposition and concrete tasks routed to the owning step, and HALTs only for gaps that need a human.
Skill Claude CodeCodex
Use only at an active pipeline batch boundary after code has changed. Reviews current-batch duplication, complexity, and over-engineering; do not invoke for ordinary refactors, code review, or requests that merely ask for simpler prose or code.
Skill Claude CodeCodex
Use only within active engineer/conduct DECIDE after architecture approval, when a committed .docs/stories acceptance artifact is required. Do not invoke for general user-story examples, requirements discussion, or direct implementation requests.
Skill Claude CodeCodex
Use when implementing any feature or bugfix. Five-step cycle: RED → DOMAIN → GREEN → DOMAIN → COMMIT. Enforces test-first development with domain integrity review at every phase boundary.
Skill Claude CodeCodex
Use only when an active workflow is about to rely on a nontrivial factual claim or assumption for a spec, plan, ADR, finding, or code decision. Do not invoke for casual questions, status reports, restatements, or trivially verifiable mechanics.
Skill Claude CodeCodex
Use BEFORE implementing any feature that has stories in .docs/stories/ — generates failing acceptance specs from acceptance criteria as the RED phase of TDD. Generates HTTP/request-level acceptance tests for headless/API projects, end-to-end UI tests for projects with a frontend, using the project's own test framework…
Skill Claude CodeCodex
Judge whether the cited Done when checks assert the supplied criterion.
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: