ca

Ask a fresh Codex session to review local changes together with the branch diff from the default branch. Use when the user asks for a Codex review, another model's perspective, or an independent review after ordinary implementation. Works without a plan, PR, previous conversation, or ca implementation loop.

Reclaim worktrees after features land — remove every merged worktree in the repo (ca/sa/ha and any other, regardless of location) and delete their merged branches. Use once a ca PR is merged. Safe by default — never removes a worktree with uncommitted changes, never deletes an unmerged branch, and never touches the main checkout (it removes the current worktree too, but only if its branch is merged). Invoke explicitly with /ca:clean-worktrees.

Standards for writing and reviewing code — quality, test rigor, security, and codebase consistency. Use whenever implementing, changing, or reviewing code, or when checking a PR or diff for bugs, missing test coverage, vulnerabilities, missed propagation, or style drift.

Review a pull request in ca. Runs the dual-model review — a blind Claude review and an offline Codex second opinion in parallel, then a Claude synthesis pass that adjudicates them into one ca_claude_review.v1 verdict. This is the entry point for reviewing any PR by hand, inside or outside the implement loop. Use when the user says review this PR, dual review this PR, review with both Claude and Codex, re-review after the ca loop, or invokes /ca:dual-review. Pass --claude-only for a single-model review.

Kick off the ca implement loop for a saved plan — create an isolated git worktree for it and print the exact Codex command to run there. Use when the user has a saved plan and wants to build it with the ca loop, or says things like "implement this plan with ca", "start building this plan", "kick off implementation of", "set up the worktree for", or invokes /ca:implement. Hands off to a Codex session; it does not implement the plan itself.

Merge a ca PR after confirming it is genuinely ready — open, not draft (in ca a draft means the Codex-Claude review loop has not approved it), green CI, mergeable, no unresolved blocking feedback. Use once the ca loop marked the PR ready and you want it merged from the CLI. Refuses to merge drafts, red checks, or conflicts. Invoke explicitly with /ca:merge-pr.

Draft an implementation plan for an epic or feature, then spar with Codex to harden it before saving. Use when the user wants to plan a sizable change and have a second model stress-test the plan, or says things like "plan this feature", "draft a plan and spar with Codex", "write an implementation plan for", or invokes /ca:plan-loop. Produces a saved task-by-task plan ready for the ca implement loop.

Resolve merge conflicts between a ca feature branch and its base branch, in an isolated worktree, preserving the intent of both sides. Use when a ca PR or feature branch is behind or conflicting with the base branch and you want the conflicts resolved, verified, and pushed. Invoke explicitly with /ca:resolve-conflicts.

Internal blind-review leg of the ca loop. Emits one structured ca_claude_review.v1 JSON verdict (approve / request_changes / blocked) for a pull request judged against the plan it was built from, in final or checkpoint mode. The ca implement loop and /ca:dual-review invoke it through claude -p; it is not the entry point for reviewing a PR by hand — use /ca:dual-review for that. Reviews the PR diff; does not edit code.

Synthesize a blind Claude review and an advisory Codex second-opinion review into the single ca_claude_review.v1 verdict for a ca final review round. Use when the ca loop invokes /ca:synthesize-review with blind, second_opinion, plan, pr, round, and out paths. Does not edit code.