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.
npx agentmods add skills/lzhgus/cc-plugin-codex/claude-code-companionnpx skills add lzhgus/cc-plugin-codex --skill claude-code-companiongit clone --depth 1 https://github.com/lzhgus/cc-plugin-codexWrote 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.
[](https://agentmods.dev/skills/lzhgus/cc-plugin-codex/claude-code-companion)<a href="https://agentmods.dev/skills/lzhgus/cc-plugin-codex/claude-code-companion"><img src="https://agentmods.dev/badge/skills/lzhgus/cc-plugin-codex/claude-code-companion.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00050 | $0.01106 |
| Opus 5 | $0.00025 | $0.00553 |
| Sonnet 5 | $0.00010 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade C, and why
claude-code-companion scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Run `cc_setup` once before any other tool. If it reports `claude installed: no` or `authenticated: no`, stop and tell the user how to fix it (`!curl -fsSL https://claude.ai/install.sh | bash` on macOS/Linux/WSL, `!irm Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Run `cc_setup` once before any other tool. If it reports `claude installed: no` or `authenticated: no`, stop and tell the user how to fix it (`!curl -fsSL https://claude.ai/install.sh | bash` on macOS/Linux/WSL, `!irm How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code companion
Overview
This plugin wraps the locally installed claude CLI (headless mode) and exposes it to Codex as MCP tools under the claude-code server. Use these tools when the user wants Claude Code to review code, take on a task, or continue work started in Codex.
The plugin uses the same claude install, login, and config the user already has. It does not bundle Claude Code.
Prerequisites
claudeis on PATH and logged in (OAuth orANTHROPIC_API_KEY).- Run
cc_setuponce before any other tool. If it reportsclaude installed: noorauthenticated: no, stop and tell the user how to fix it (!curl -fsSL https://claude.ai/install.sh | bashon macOS/Linux/WSL,!irm https://claude.ai/install.ps1 | iexon Windows PowerShell, and/or!claude login). - For tools that operate on a repository, pass
repo_pathwith the absolute path to the current Codex project/repository. Plugin MCP servers run from the plugin cache, not from the user's repository, soprocess.cwd()is not enough.
Tools
| Tool | Use when |
|---|---|
cc_setup |
Readiness check. Always first. |
cc_review |
Read-only review of current uncommitted changes or a branch vs --base. Pass repo_path. |
cc_adversarial_review |
Read-only steerable review that challenges the design; accepts focus. Pass repo_path. |
cc_rescue |
Delegate a task (bug, fix, investigation, follow-up) to Claude Code. Can mutate files. Pass repo_path. |
cc_transfer |
Hand the current Codex session transcript to Claude Code; get a claude --resume <id> command. Pass repo_path. |
cc_status |
List running/recent background jobs for this repo. Pass repo_path. |
cc_result |
Read the stored output of a finished job + its Claude session id. Pass repo_path. |
cc_cancel |
Kill a running background job. Pass repo_path. |
When to use which
- Review the diff →
cc_review. For a branch review, passbase: "main"(or another ref). - Challenge the approach →
cc_adversarial_reviewwithfocusdescribing the concern (auth, data loss, race conditions, rollback, etc.). - Hand off a task →
cc_rescue. Pass the task astask. Preferbackground: truefor anything non-trivial, then surface progress viacc_status/cc_result. - Continue a prior run →
cc_rescuewithresume: "<session-id>"(get the id fromcc_status/cc_result). Usefresh: trueto force a new session. - Move the conversation to Claude Code →
cc_transfer.
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.
- 5d ago First seen · 70 lines · 50 tokens per session scan C 154a2bc7d414
claude-code-companion is a skill published in the GitHub repository lzhgus/cc-plugin-codex (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,106 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…