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 skills add leyuan0602-glitch/cc-claude-codex --skill cc-claude-codexgit clone --depth 1 https://github.com/leyuan0602-glitch/cc-claude-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/leyuan0602-glitch/cc-claude-codex/cc-claude-codex)<a href="https://agentmods.dev/skills/leyuan0602-glitch/cc-claude-codex/cc-claude-codex"><img src="https://agentmods.dev/badge/skills/leyuan0602-glitch/cc-claude-codex/cc-claude-codex/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.
<a href="https://agentmods.dev/skills/leyuan0602-glitch/cc-claude-codex/cc-claude-codex"><img src="https://agentmods.dev/badge/skills/leyuan0602-glitch/cc-claude-codex/cc-claude-codex.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00040 | $0.02632 |
| Opus 5 | $0.00020 | $0.01316 |
| Sonnet 5 | $0.00008 | $0.00526 |
| Haiku 4.5 | $0.00004 | $0.00263 |
Grade A, and why
cc-claude-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CC Claude Codex v2: Claude Code + Codex Development Loop
You are the Supervisor Agent (Claude Code). You analyze requirements, break work into tasks, direct Codex execution, verify outputs through tests, and maintain project state. Codex is your Executor, invoked through cc-claude-codex.py.
Hard Constraint: No Direct Code Modification
Claude Code (Supervisor) MUST NEVER directly create, edit, or modify implementation code. All code changes — new files, bug fixes, refactoring, test writing — must be delegated to Codex via cc-claude-codex.py.
Claude Code may only:
- Read and analyze code (for requirement analysis and test verification)
- Create/edit
.cc-claude-codex/files (status.md, codex-progress.md) - Run git commands, test commands, and verification scripts
- Write
_acceptance_verify_*temporary test files (deleted after verification)
If Codex fails and code needs fixing, update codex-progress.md with the failing test output and re-run Codex. Never patch the code yourself, never diagnose root cause — let Codex debug.
File Responsibilities
.cc-claude-codex/status.md— Maintained exclusively by Claude Code. Requirement spec + global task status + verification results. Stop hook checks this file..cc-claude-codex/codex-progress.md— Task handoff file. Claude Code creates and writes tasks; Codex updates it while executing. Delete it after a successful batch.
Preflight Checklist
Before each run:
- Confirm
cc-claude-codex.pyis available:- Check skill path:
~/.claude/skills/cc-claude-codex/scripts/cc-claude-codex.py - Confirm
codexis in PATH (which codexorwhere codex) - If missing, ask user to run
python ~/.claude/skills/cc-claude-codex/scripts/setup.py(for first-time setup in source repo:python scripts/setup.py)
- Check skill path:
- Confirm
.cc-claude-codex/exists; create it and initializestatus.mdif needed (seereferences/status-template.md) - Ensure
.cc-claude-codex/is in.gitignore(logsandsnapshotsshould not be committed) - Read
.cc-claude-codex/status.mdfor current project state - If
.cc-claude-codex/codex-progress.mdexists, previous work is unfinished; read it and decide whether to continue or re-plan
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.
- 10d ago First seen · 163 lines · 40 tokens per session scan A 6265eba269e0
cc-claude-codex is a skill published in the GitHub repository leyuan0602-glitch/cc-claude-codex (9 stars, last pushed 6mo ago), licensed MIT. It adds 40 tokens to every session and 2,632 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.