What is codexcw AGENTS.md?

Repository instructions for humans and coding agents working on c3-oss/codexcw. The project is a monorepo, meaning one repository contains several related implementations, including Go, Rust, Node.js, Python, and .NET versions.

It helps agents and developers decide where to make changes, run the correct language-specific checks, use shared test fixtures, and prepare compliant commits or pull requests.

It gives contributors one place to find the project structure, development commands, coding rules, testing guidance, and commit requirements.

codexcw AGENTS.md — Instructions file by c3-oss

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.

agentmods

npx agentmods add instructions/c3-oss/codexcw/agents-md

Clone the repo

git clone --depth 1 https://github.com/c3-oss/codexcw

Made for: Codex, OpenCode.

Per session 1,621 This file is loaded in full into every session.

When invoked 1,621 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01621	$0.01621
Opus 5	$0.00811	$0.00811
Sonnet 5	$0.00324	$0.00324
Haiku 4.5	$0.00162	$0.00162

Measured 2d ago against content hash ee66e10befb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexcw AGENTS.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 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.

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.

AGENTS.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Canonical guide for humans and AI coding agents working in this repository. Read this end-to-end before proposing substantial changes.

Project shape

A polyglot monorepo: five independent, idiomatic implementations of the same agent CLI wrapper — codex exec --json by default, with selectable claude and grok agents that normalize their streaming JSON into the shared event model. There is no FFI between the Go and .NET ports and the Rust side — each implementation is native to its ecosystem; they share a repo so the spec and test fixtures stay a single source of truth.

Go (root) — the public Go library github.com/c3-oss/codexcw. Go module at the repo root (go.mod), CGO-free. Root *.go, cmd/codexcw/ (example CLI), internal/, scripts/.
crates/codexcw/ — the Rust core (codexcw on crates.io), async (tokio), FFI-free.
bindings/node/ — napi-rs binding + npm package @c3-oss/codexcw (a hand-written index.js wraps the generated native loader).
bindings/python/ — PyO3 binding (_codexcw) + PyPI package codexcw (sync API in codexcw/__init__.py, asyncio facade in codexcw/aio.py).
dotnet/ — the native .NET port + NuGet package C3OSS.Codexcw (dotnet/Codexcw library, dotnet/Codexcw.Tests xUnit suite), FFI-free like the Go port.
Generated outputs (gitignored): bin/, target/, dist/, node_modules/, *.node, *.so, .venv/, dotnet/**/bin/, dotnet/**/obj/, *.nupkg.

Complete usage recipes per language (quickstart, streaming, resume, sandbox / approval, bypass, batches, structured output, errors — in both sync and async forms) live in docs/examples/{go,rust,typescript,python,csharp}.md. The Codex skill (.codex/skills/codexcw/) and the codexcw-expert Claude subagent point there.

Build, test, develop

Toolchain is pinned in devbox.json (Go + golangci-lint + goreleaser; Rust via rustup + rust-toolchain.toml; Node + pnpm; Python + uv + maturin; .NET SDK; plus the quality tools). Enter with devbox shell and run via just. Recipes are language-namespaced:

Read the full file on GitHub · 115 lines

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.

2d ago First seen · 115 lines · 1,621 tokens per session scan A ee66e10befb9

Subscribe to this mod's changes

codexcw AGENTS.md is an instructions file published in the GitHub repository c3-oss/codexcw (1 stars, last pushed 2d ago), licensed CC0-1.0. It adds 1,621 tokens to every session, about $0.0081 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.

agent automation codex codex-cli go monorepo

codexcw AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS

Project shape

Build, test, develop

What this file has done since we first saw it

Other instructions, from other repositories

MobileVC CLAUDE.md

wanwu-workflow CLAUDE.md

acodex AGENTS.md

AgentHub AGENTS.md

arcvellum AGENTS.md

lightcode copilot-instructions.md