A Claude Code plugin that coordinates several Codex workers, with separate Git worktrees and sessions that can resume later. Codex workers are AI agents that work on coding tasks.

Use it to split development work among agents, run parallel tasks, continue interrupted sessions, isolate changes in Git worktrees, and review pull requests.

It lets multiple agents work in parallel while keeping their code changes isolated, and supports reviewing a pull request with two models.

magic-codex — Plugin for Claude Code by wenqingyu

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.

Clone the repo

git clone --depth 1 https://github.com/wenqingyu/magic-cc-codex-worker

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/wenqingyu/magic-cc-codex-worker/plugin/github.svg)](https://agentmods.dev/plugins/wenqingyu/magic-cc-codex-worker/plugin)

Your own site

<a href="https://agentmods.dev/plugins/wenqingyu/magic-cc-codex-worker/plugin"><img src="https://agentmods.dev/badge/plugins/wenqingyu/magic-cc-codex-worker/plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/wenqingyu/magic-cc-codex-worker/plugin"><img src="https://agentmods.dev/badge/plugins/wenqingyu/magic-cc-codex-worker/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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

When invoked not measured The manifest loads nothing itself; its 9 commands, 3 agents, 2 MCP servers cost 356 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

magic-codex 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.

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

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Contents

What it installs

The manifest is a name and a version. 9 commands, 3 agents, 2 MCP servers travel with it, and installing the plugin installs all of them — 356 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

2mo ago First seen · 13 lines scan A 3ada769a60e1

Subscribe to this mod's changes

magic-codex is a plugin published in the GitHub repository wenqingyu/magic-cc-codex-worker (5 stars, last pushed 6mo ago), with no licence file. 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.

Building agents Claude Code Git and workflow agent-workers ai-agents anthropic claude claude-code-plugin

hermitd-dev

Git safeguards, debugging, and merge-conflict resolution for your Hermit.

gtapps/hermitd · not measured

dark-factory

Curie's default dark factory agent: one labelled GitHub issue in, one reviewed pull request or one stated reason out. One agent reads the issue through the platform's getissue tool, pins acceptance criteria, plans, gets the plan reviewed by an Opus plan-reviewer subagent, writes a failing test where feasible, implemen.

curie-eng/curie · not measured

github-activity

Read-only GitHub activity reporter for program managers. One hosted connector reads merged pull requests, opened and closed issues, and milestone movement across several repositories since a point in time. It holds no write tool, the tool policy allows only the read tool so anything else fails closed, and the…

curie-eng/curie · not measured

privacy-guard

Keeps private infrastructure details out of public repositories. Ships the privacy-guard skill: session rules for what must never cross the public boundary, plus a per-repo pre-commit gate built on a gitignored local denylist and gitleaks. The denylist is never committed, so the hook is a no-op for external…

fvadicamo/dev-agent-skills · not measured

github-workflow

Git commit, PR creation, review, and merge skills following Conventional Commits.