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 instructions/dwgx/claude-codex-subagent/claude-mdgit clone --depth 1 https://github.com/dwgx/claude-codex-subagentWrote 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/instructions/dwgx/claude-codex-subagent/claude-md)<a href="https://agentmods.dev/instructions/dwgx/claude-codex-subagent/claude-md"><img src="https://agentmods.dev/badge/instructions/dwgx/claude-codex-subagent/claude-md.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 | $0.00702 | $0.00702 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
claude-codex-subagent CLAUDE.md 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 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.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Maintainer Guide
Default answer language for this maintainer is Chinese unless the user asks for English. Keep responses direct and evidence-backed.
What This Repo Teaches
This repo teaches Claude Code to use local Codex as a worker subagent. Claude keeps orchestration, judgment, and user conversation state. Codex handles context-heavy or tool-heavy work: current web facts, large reads, bulk repo analysis, long file writes, audits, test runs, and fresh-context debugging.
Dispatch Defaults
For Codex CLI 0.141.0+:
codex exec --skip-git-repo-check --sandbox workspace-write -C <repo> -
Use stdin for generated or multiline prompts. Do not teach new examples with
--full-auto; it is deprecated. If a persona still says sandbox: full-auto,
the wrapper treats it as a legacy alias for --sandbox workspace-write.
Escalate deliberately:
--sandbox workspace-write: normal local repo reads, edits, tests, lint, build.--search: helper-script shorthand for current public web facts. Directcodex execuses--config web_search="live"; top-level interactivecodexsupports--search.--dangerously-bypass-approvals-and-sandbox: shell network, cross-workspace access, global installs, or Windows sandbox ACL fallback after reporting the exact error.--ephemeral: throwaway checks that should not persist a session.--json,-o,--output-schema: automation and machine-readable outputs.
How To Prompt Codex
Every dispatch prompt should include:
- goal and done condition,
- scope and working directory,
- what not to touch,
- exact return format,
- verification expectations,
- whether file edits are allowed.
Prefer short final returns. The point of this skill is to avoid reinflating the main Claude context with Codex's full internal work.
Use Personas
reviewer: severity-ranked code review.debugger: fresh root-cause analysis.auditor: security audit.researcher: current web/docs research.refactorer: cleanup/dead-code/stale TODO survey.
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 · 83 lines · 702 tokens per session scan A f9002c84adf8
claude-codex-subagent CLAUDE.md is an instructions file published in the GitHub repository dwgx/claude-codex-subagent (3 stars, last pushed 2mo ago), licensed MIT. It adds 702 tokens to every session, about $0.0035 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 instructions, from other repositories
clawhub AGENTS.md
AGENTS.md instructions for openclaw/clawhub, covering repository guidelines, project structure & module organization, durable intent & specs, build, test, and development commands and coding style & naming conventions.
avoid-ai-writing CLAUDE.md
Claude Code instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
rolecraft AGENTS.md
AGENTS.md instructions for rolecraft-sh/rolecraft, covering rolecraft — development guidelines, ⚠️ startup checklist (read before every task), workflow, interaction rules and code style.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
pencil-skill AGENTS.md
Instructions for Nisus74/pencil-skill, covering pencil-dev-skill: project context, project purpose, naming conventions, repository structure and project context files.