codex-claude-loop

codex-claude-loop is a skill for Claude Code from ozzaii/codex-claude-loop. It costs 71 tokens per session (1,472 once invoked), scanned A, original, MIT.

A skill for running a controlled coding workflow between Claude and Codex, where Codex plans and implements changes and Claude approves the plan and reviews the resulting code.

In plain words
What is it for?
Use it for serious multi-file changes, repeated implementation follow-ups, and reviewing a code diff against an approved plan.
Why use it?
It keeps planning, implementation, and review connected in one ongoing Codex thread, with approval checkpoints that cannot be skipped.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code; reads ~/.codex paths; runs codex exec.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the codex-claude-loop plugin — 5 skills, 1 hook shipped together

Good fit Use it for serious multi-file changes, repeated implementation follow-ups, and reviewing a code diff against an approved plan.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ozzaii/codex-claude-loop
Claude Code
/plugin install codex-claude-loop

Made for: Claude Code.

Or install codex-claude-loop, the plugin that ships this one along with the rest of its 5 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-claude-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/ozzaii/codex-claude-loop/codex-claude-loop/github.svg)](https://agentmods.dev/skills/ozzaii/codex-claude-loop/codex-claude-loop)
Your own site
<a href="https://agentmods.dev/skills/ozzaii/codex-claude-loop/codex-claude-loop"><img src="https://agentmods.dev/badge/skills/ozzaii/codex-claude-loop/codex-claude-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codex-claude-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/ozzaii/codex-claude-loop/codex-claude-loop"><img src="https://agentmods.dev/badge/skills/ozzaii/codex-claude-loop/codex-claude-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.01472
Opus 5.5 $0.00028 $0.00589
Sonnet 5.5 $0.00014 $0.00294
Haiku 4.5 $0.00007 $0.00147

Measured 2mo ago against content hash fd72d27a6aab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-claude-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (lib/codex-claude-loop.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/codex-claude-loop/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-claude-loop — the gated Claude × Codex build loop

Claude is the principal orchestrator; it rarely types product code. Codex CLI does the hands-on implementation from persistent threads. The whole thing is bash around codex exec — no framework, no MCP, no daemon.

The cycle (one brief)

Claude writes a brief  →  Codex authors a plan (persistent thread)  →  back to Claude
   →  Claude APPROVES the plan (loop until tight)  →  Codex implements (same thread)
   →  Claude REVIEWS the diff against the plan (loop until clean)  →  cl_release

The persistent thread is the trick: the plan Codex authored carries into implementation, so it implements its own approved plan with full context. The approved plan text is also sent with the implementation instruction, so if a human edited and re-approved the plan file, the file wins over what the thread drafted.

How to run it

source ${CLAUDE_PLUGIN_ROOT}/skills/codex-claude-loop/lib/codex-claude-loop.sh then use the phase functions, or call bash lib/codex-claude-loop.sh <phase> … directly. Config via env (CL_REPO, CL_IMPL_MODEL, CL_PLAN_MODEL, CL_REVIEW_MODEL, CL_SANDBOX, CL_LOCK_TIMEOUT).

  1. First run: cl_doctor (codex/jq/git/sha256 present, the four codex capabilities the loop needs, repo + schema resolve).
  2. Codex plans: cl_plan <slug> <brief.md> → writes <slug>.plan.md, opens a persistent thread, stores its id.
  3. Claude approves the plan (judgment — YOU read it): read <slug>.plan.md. If tight, cl_record_verdict <slug> plan approve "why". If not, re-brief and re-plan. Loop until the plan holds. Prompt yourself to refute it, not rubber-stamp it.
  4. Codex implements: cl_impl <slug> → resumes the thread, writes code, runs tests, holds the writer lock, and records a success marker only if codex exited clean.
  5. Optional same-session follow-up: cl_prompt <slug> "<additional request>" queues behind the lane's writer lock, resumes the exact stored thread, and prints Codex's response. It requires a successful implementation and makes re-review mandatory.
  6. Claude reviews the diff: cl_review_human <slug> (rich review you read) — or inspect git diff <base> yourself. Judge it against the plan. Approve (cl_record_verdict <slug> review approve "why") or send the blocking items back into the same thread with cl_revise <slug> "…" and re-review. Loop until clean.
  7. Release: cl_release <slug> confirms both gates still hold for the tree as it is right now, and refuses otherwise. Then changelog, tag, merge, deploy (honor the project's own deploy gate).

Read the full file on GitHub · 98 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 98 lines · 71 tokens per session scan A fd72d27a6aab

Subscribe to this mod's changes

codex-claude-loop is a skill published in the GitHub repository ozzaii/codex-claude-loop (6 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,472 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

codex-claude-loop compared with skills from other repositories

codex-claude-loop next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
codex-claude-loopozzaii/codex-claude-loopSkill63mo agoMITA71Claude Code
craftkardebadas/claude-pluginSkill322d agoApache-2.0A83Claude Code
pipelinekardebadas/claude-pluginSkill322d agoApache-2.0A24Claude Code
pipeline-autokardebadas/claude-pluginSkill322d agoApache-2.0A93Claude Code
turbo-pipelinekardebadas/claude-pluginSkill322d agoApache-2.0A114Claude Code
bug-fixkardebadas/claude-pluginSkill322d agoApache-2.0A74Claude Code
fast-pipelinekardebadas/claude-pluginSkill322d agoApache-2.0A95Claude Code