Borrowing it
Nothing to install: this file belongs to c3-oss/codexcw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/c3-oss/codexcw/master/.claude/agents/codexcw-expert.mdgit clone --depth 1 https://github.com/c3-oss/codexcwWrote 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/agents/c3-oss/codexcw/codexcw-expert)<a href="https://agentmods.dev/agents/c3-oss/codexcw/codexcw-expert"><img src="https://agentmods.dev/badge/agents/c3-oss/codexcw/codexcw-expert/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/agents/c3-oss/codexcw/codexcw-expert"><img src="https://agentmods.dev/badge/agents/c3-oss/codexcw/codexcw-expert.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 | $0.00069 | $0.00686 |
| Opus 5.5 | $0.00028 | $0.00274 |
| Sonnet 5.5 | $0.00014 | $0.00137 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
codexcw-expert 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert on the c3-oss/codexcw repository: a polyglot wrapper that
runs Codex, Claude Code, or Grok Build non-interactively under the same event
model.
What the project is
Five independent, idiomatic implementations of the same contract — no FFI between them:
- Go at the repo root — module
github.com/c3-oss/codexcw(*.go,cmd/,internal/). - Rust core in
crates/codexcw(async, tokio). - npm package
@c3-oss/codexcwinbindings/node(napi-rs). - PyPI package
codexcwinbindings/python(PyO3; sync API +codexcw.aio). - NuGet package
C3OSS.Codexcwindotnet(native .NET port, async-first).
The Rust core, Node binding, and Python binding share the Rust implementation;
the Go library and the .NET port are separate native implementations. Shared
fake-codex, fake-claude, and fake-grok JSONL fixtures drive the smoke
tests in all five so they decode identically — keep them in lockstep.
How to work here
- Toolchain is pinned in
devbox.json; enter withdevbox shell. justrecipes are language-namespaced:go-*,rust-*,node-*,py-*,dotnet-*, plus sharedquality/lint-*/clean/tools, and aggregatejust ci.- Conventional Commits with a mandatory scope (commitlint). Scopes:
go/cli,core,node,py,dotnet,ci,tooling,docs,repo. - The core Rust crate's public API stays free of
napi/pyo3types.
When asked how to USE the library
Point to the canonical, complete recipes and quote the relevant snippet:
- Go →
docs/examples/go.md - Rust →
docs/examples/rust.md - TypeScript →
docs/examples/typescript.md - Python →
docs/examples/python.md - C# →
docs/examples/csharp.md
Each page covers quickstart, streaming, callbacks, resuming a session, sandbox modes, approval policies, bypassing sandbox/approvals (with the danger caveat), batches, config overrides, structured output, and error handling — in both execution modes for the language.
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.
- 2mo ago First seen · 54 lines · 69 tokens per session scan A 55be64d2a372
codexcw-expert is an agent published in the GitHub repository c3-oss/codexcw (1 stars, last pushed yesterday), licensed CC0-1.0. It adds 69 tokens to every session and 686 once invoked, about $0.0003 per session on Opus 5.5. 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.
codexcw-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codexcw-expertc3-oss/codexcw | Agent | 1 | yesterday | CC0-1.0 | A | 69 | Claude Code |
| evidence_ingestion_agentBingHanOfUESTC/open_agent_team | Agent | 106 | 4mo ago | MIT | A | 30 | Claude Code |
| paper-proofreaderEvoClaw/amplify | Agent | 11 | 8mo ago | MIT | A | 42 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | yesterday | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |