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/circlemouth/codex-wrapper/agents-mdgit clone --depth 1 https://github.com/circlemouth/Codex-WrapperWhat 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 | $0.00672 | $0.00672 |
| Opus 5 | $0.00336 | $0.00336 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade B, and why
Codex-Wrapper AGENTS.md scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- When extending Codex CLI integration, verify `~/.codex/config.toml` compatibility and add migration notes if defaults shift. How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Language
- 以降、このリポジトリでのアシスタントからの返答は日本語で行うこと。
Project Structure & Module Organization
app/holds the FastAPI service:main.pyexposes/v1/chat/completionsand/v1/responses,codex.pyshells out to the Codex CLI, and sibling modules handle config, schemas, and security gates.docs/contains bilingual product docs plus English-only references such asENV.mdand API plans; keep translations in sync perCONTRIBUTING.md.submodules/codextracks the upstream Codex CLI; rungit submodule update --init --recursiveafter cloning.workspace/is a scratch area for manual experiments (e.g.,test_filter.py); treat anything promoted from here as real tests before merging.
Build, Test, and Development Commands
python3 -m venv .venv && source .venv/bin/activateensures isolation for Python deps.pip install -r requirements.txtinstalls FastAPI, uvicorn, and supporting libraries.uvicorn app.main:app --host 0.0.0.0 --port 8000 --reloadruns the wrapper locally with auto-reload.pytestexecutes unit tests; add targeted suites undertests/(preferred) or migrate scripts fromworkspace/.
Coding Style & Naming Conventions
- Follow PEP 8 with 4-space indentation and snake_case for functions, PascalCase for Pydantic models.
- Keep async boundaries explicit—prefer async FastAPI endpoints delegating to helpers in
app.codex. - Add type hints and short docstrings where behavior is security-sensitive (e.g., sandbox enforcement).
- Use
blackor an equivalent formatter before committing; avoid mixing style-only changes with feature work.
Testing Guidelines
- Write pytest cases that cover both streaming and non-streaming flows in
app.main; mock Codex CLI responses to avoid external calls. - Name tests
test_<feature>.pyand fixtures<scope>_<name>for clarity. - Include regression tests when altering request parsing, prompt assembly, or sandbox validation—these areas gate user safety.
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.
- 2d ago First seen · 38 lines · 672 tokens per session scan B 594911acc92a
Codex-Wrapper AGENTS.md is an instructions file published in the GitHub repository circlemouth/Codex-Wrapper (22 stars, last pushed 8mo ago), licensed MIT. It adds 672 tokens to every session, about $0.0034 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.