Codex loop
Skill oliver-kriska/claude-elixir-phoenix/plugins/elixir-phoenix/skills/codex-loop
Claude Code plugin for Elixir/Phoenix/LiveView — 20 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.
npx -y skills add oliver-kriska/claude-elixir-phoenix --skill codex-loopAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
SKILL.md
5.0 KB, as published. Nobody here has run it
Codex Loop (fix until clean)
Critic→Refiner loop with the Codex CLI as external critic: review → fix
approved findings → verify → re-review, until codex is clean or rounds run
out. Codex reviews; Claude fixes. Complements /phx:review (Claude panel)
— run either or both before a PR.
Usage
/phx:codex-loop # diff vs default branch, interactive
/phx:codex-loop --uncommitted # staged + unstaged + untracked
/phx:codex-loop --base develop # explicit base branch
/phx:codex-loop --auto # auto-approve P0/P1/P2, skip P3
/phx:codex-loop --max-rounds 2 # default 3
Iron Laws
- BOUNDED rounds — never exceed --max-rounds (default 3) — each round costs codex quota; report remaining findings instead of looping on
- Verify BEFORE re-review —
mix compile --warnings-as-errors+ tests must pass before burning a codex round on broken code - NEVER commit or push — leave git to the user
- Codex findings get Iron Law scrutiny — decline suggestions that violate an Iron Law, with explanation in the round report
- Skipped findings are reported, never dropped — every finding ends as fixed, declined (with reason), or deferred-by-user
- Missing CLI stops the skill with an install hint — suggest
/phx:reviewas the codex-free alternative; never crash
Workflow
Step 1: Preflight
Run command -v codex. If missing: STOP.
Show the install hint (brew install codex or npm i -g @openai/codex,
then codex login; codex doctor to diagnose) and suggest /phx:review.
Then two cheap checks that save review rounds:
- Dirty tree (
git status --short, only when using--base): codex inspects working-tree state too and WILL flag local dirt (stray edits, dirty submodules) as findings. Surface the dirt and ask: clean/stash first, or proceed knowing round 1 may spend findings on it. - Missing rubric: if
AGENTS.mdhas no## Review guidelinessection, note once that/phx:initinstalls the Elixir rubric that steers codex priorities — then proceed (it works without, on defaults).
Step 2: Detect Diff Mode
- Flag passed (
--base/--uncommitted) → use as given - Commits ahead of the default branch →
--base {default} - No commits yet →
--uncommitted
Step 3: Round Loop (max --max-rounds, default 3)
-
Review — ONE foreground Bash call, explicit
timeout: 600000(large diffs run 10+ min). On timeout with the process alive: ONEuntil [ -f {out} ]; do sleep 5; donewait — never poll-spam orpkilla running review (quota is spent either way). ALWAYS silence the streams — only the-ofile matters (10k+ lines otherwise):codex exec review --base {branch} --ephemeral \ -o /tmp/codex-round-{n}.md > /tmp/codex-round-{n}.log 2>&1NEVER pass custom instructions with a diff-mode flag — the CLI rejects the combination; the rubric comes from AGENTS.md
## Review guidelines(/phx:init). Parse the output file, NOT the exit code (0 even with findings). Recipes:${CLAUDE_SKILL_DIR}/references/codex-cli.md. -
Clean check — parse the output file; no
- [P{n}]bullets means CLEAN → go to Step 4. -
Triage — emit the findings table (
# | P | file:line | title | proposed action) as visible response text BEFORE anyAskUserQuestioncall — a table composed only in thinking never renders. Then ask approve-or-skip per finding (AskUserQuestion). With--auto: approve P0/P1/P2, skip P3 (list skipped in the round report). -
Fix — apply approved fixes with user-visible diffs. Check each against Iron Laws first (Law 4).
-
Verify — scoped, before the next round:
mix format {changed_files} && \ mix compile --warnings-as-errors && mix test {affected_tests}If verification fails 3 times, STOP with a BLOCKER report — do not burn another codex round on broken code.
-
Next round (n+1).
Step 4: Final Report
## Codex Loop Report — {CLEAN | MAX ROUNDS REACHED | BLOCKED}
Rounds: {n}/{max} | Fixed: {n} | Declined (Iron Law): {n} | Deferred: {n}
{per-round: findings → outcome}
{remaining findings if not CLEAN}
On CLEAN: suggest /phx:compound for non-obvious fixes, then commit/PR.
On MAX ROUNDS: list remaining findings; offer /phx:plan to convert them
into a follow-up plan.
Integration
implement → /phx:codex-loop (YOU ARE HERE) → clean → commit/PR → /phx:watch-pr --codex
↑ or arrive from /phx:review --codex verdict REQUIRES CHANGES
References
${CLAUDE_SKILL_DIR}/references/codex-cli.md— invocation recipes, parse patterns, verified gotchas (CLI 0.142.5)