luna-maxinglisted
Install: claude install-skill asiridalugoda/autonomous-loop
# Luna-maxing
## Overview
Tandem build: **Claude orchestrates, Codex builds and reviews.** Every line of product code, every fix and every review verdict comes from a Codex seat (`codex exec -m gpt-5.6-luna`, effort `max`). The Claude session plans, rules on ambiguities, dispatches, runs the local gates itself, and owns git and draft PRs. Nothing is pushed until the controller's own gates are green on that exact head AND the Codex review is clean.
**REQUIRED SUB-SKILL:** superpowers:subagent-driven-development (ledger, briefs, review packages, fix-loop discipline). This skill replaces its subagents with Codex seats.
## Roles
| Seat | Who | Session |
|---|---|---|
| Orchestrator: plan, rulings, dispatch, gates, git, rebases without conflicts, draft PRs, ledger | Claude | this session |
| Implementer, fixer, conflict-resolving rebase job | Codex Luna max | implementer thread, resumed for fixes |
| Reviewer, scoped re-reviewer | Codex Luna max | fresh session every time |
The controller never edits product code. A controller "quick fix" skips review.
## Quick reference
| Step | Tool |
|---|---|
| Dispatch a seat (background) | `LUNA_WS=<ws> scripts/dispatch.sh NAME WORKTREE PROMPT` (`--resume THREAD` for fixes) |
| Wait out a usage limit | `scripts/wait-codex-reset.sh "<RESET_AT>"` (background) |
| Local green | `LUNA_WS=<ws> LUNA_GATES_PROFILE=profiles/<project>.sh scripts/gates.sh NAME WORKTREE BASE [args]` |
| Prompt bodies | `templates/implementer.md`, `reviewer.md`,