← ClaudeAtlas

codex-implementlisted

Delegate a well-scoped implementation to OpenAI Codex through its Claude Code companion plugin in an isolated git worktree, then independently verify it with tests and adversarial review before a user-approved merge. Use when the user wants Codex to implement a bounded change, wants a second model's implementation attempt, or wants a safe Codex implementation-and-review workflow.
aarontzeng/dev-lead · ★ 1 · AI & Automation · score 67
Install: claude install-skill aarontzeng/dev-lead
# Delegate implementation to Codex, then verify Use the Codex companion's `task --write` runtime. It gives the implementation session `workspace-write`; it is not a permission to modify the main checkout. Create the worktree yourself, keep the task inside it, and retain merge authority. The review gate for work implemented here is a **non-GPT reviewer, at every risk level** — the cross-family rule ([`docs/methodology.md`](../../docs/methodology.md) §1) has no LOW-risk exemption. A `codex-adversarial-review` pass over Codex's own work is a fresh context, **not** model diversity: legitimate as an *additional* supplement, never as the gate. HIGH-risk work takes two reviewers from two non-GPT families. ## Before the first run of a session Read **[`../codex-adversarial-review/references/codex-runtime.md`](../codex-adversarial-review/references/codex-runtime.md)**. It holds the family-level mechanics shared by both codex roles — companion resolution, the `--background` launcher-output trap, `status` lying about liveness, report recovery from session rollouts, what the sandboxes can and cannot do, and the model/effort plumbing. This file assumes them and covers only what makes a run an *implementation*. ## Preconditions Use this only for a bounded change with acceptance criteria. Do not delegate a vague investigation, a destructive migration, production operations, or a task whose premise has not been checked against the current code. Before creating a worktree: ```bash git