What is codex-claude-loop?

A plugin for a two-agent coding workflow in which Codex plans and writes code while Claude approves the plan and reviews the changes.

Use it to delegate multi-file changes to Codex, continue work in one persistent thread, and process follow-up requests.

It adds checkpoints before implementation and before release, so coding work is not accepted without plan approval and a diff review.

codex-claude-loop — Plugin by ozzaii

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add ozzaii/codex-claude-loop

agentmods

npx agentmods add plugins/ozzaii/codex-claude-loop/plugin

Clone the repo

git clone --depth 1 https://github.com/ozzaii/codex-claude-loop

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

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 yesterday.

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/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "name": "codex-claude-loop",
  "version": "0.6.0",
  "description": "Gated Claude x Codex build loop: Codex plans, implements, and accepts queued follow-ups from one persistent thread; Claude approves the plan and reviews the diff.",
  "author": {
    "name": "Kaan Ozkan",
    "url": "https://github.com/ozzaii"
  },
  "homepage": "https://github.com/ozzaii/codex-claude-loop",
  "license": "MIT",
  "keywords": ["codex", "orchestration", "multi-agent", "code-review", "delegation"]
}

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.

yesterday First seen · 13 lines scan A 16a52ebf8e81

Subscribe to this mod's changes

codex-claude-loop is a plugin published in the GitHub repository ozzaii/codex-claude-loop (6 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Planning Productivity ai-agents claude-code claude-code-plugin claude-code-skills codex codex-cli

kardebadas-claude-plugin

Personal plugins for Codex and Claude Code.

kardebadas/claude-plugin · not measured

superb

Personal skill collection. Skills are invoked as superb: . craft turns a vague product idea into a decision-rich CRAFT.md brief — it questions, challenges and records, and deliberately stops short of planning. pipeline takes a settled idea to a finished branch, composing the superpowers skills with a zero-assumpt.

kardebadas/claude-plugin · not measured

codex-claude-loop

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

kardebadas-claude-plugin

superb

rails-consultant

rails-consultant

subtask

kortex