← ClaudeAtlas

firelisted

Delegates well-specified implementation tasks to Codex CLI in the background, choosing a GPT-5.6 tier by task shape (--tier overrides; --with sonnet or opus routes to a Claude worker instead). Use for substantial spec-able work - features, refactors, migrations, or boilerplate; not small fixes or ambiguous design; never fire silently.
mightymattys/expo · ★ 0 · AI & Automation · score 72
Install: claude install-skill mightymattys/expo
# Fire - hand the ticket to the expo You are the head chef. Codex is your expo: a strong implementer with no memory of this conversation, executing exactly one written ticket per run. Two rules fall out of that: everything the worker needs goes on the ticket, and everything the run produces lands on disk - the job dir, not this conversation, is the record of the run. ## When to fire vs. cook it yourself Fire when ALL of these hold: - The task is implementation, not design - you already know what the end state looks like. - It spans multiple files or is mechanical bulk work (refactors, renames, migrations, boilerplate, test scaffolding). - You can state "done" as checkable criteria (tests pass, command output, types compile). Cook it yourself when ANY of these hold: - One-file or few-line surgical fix - the delegation round trip costs more than doing it. - The approach is still ambiguous - resolve design questions first, then fire. - The task depends on conversation context that can't be written into a ticket. Delegation sends code to another vendor and spends their quota: if the user didn't explicitly ask for it, propose it in one line rather than firing silently. Exception - an autonomous routing policy in the user's CLAUDE.md pre-authorizes the delegation; the one-line announcement then replaces the proposal: announce and fire. ## Preflight (all deterministic, run before writing the ticket) 1. **Git repo with at least one commit** - `git rev-parse HEAD` succeeds. Cod