agentforce314

Clawcodex — AI skill for Claude Code

AI community

Token efficient Claude Code full Python rebuild.

How to install Clawcodex

This entry records only its repository, not the path inside it, so there is no exact command to give. Open agentforce314/clawcodex and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Clawcodex does

Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python. Up to 200X Cost Saving!

Alternatives in AI

Codeburn — Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Code 9.7k ★
TokenTracker — Local-first AI token usage & cost tracker for 31 coding tools incl 1.4k ★
CoreCoder — Minimal AI coding agent (~1,400 LoC Python) inspired by Claude Code 616 ★

README

ClawCodex

**A production-oriented Python rebuild of Claude Code — real architecture, reliable CLI agent**

*Ported from the TypeScript reference implementation and extended with a Python-native runtime*

[![GitHub stars](https://img.shields.io/github/stars/agentforce314/clawcodex?style=for-the-badge&logo=github&color=yellow)](https://github.com/agentforce314/clawcodex/stargazers) [![GitHub forks](https://img.shields.io/github/forks/agentforce314/clawcodex?style=for-the-badge&logo=github&color=blue)](https://github.com/agentforce314/clawcodex/network/members) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=for-the-badge)](https://opensource.org/licenses/MIT) [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg?style=for-the-badge&logo=python&logoColor=white)](https://www.python.org/downloads/)

**🔥 Active Development • New Features Weekly 🔥**

![ClawCodex Screenshot](assets/clawcodex-screenshot-1.png)

🏆 Terminal-Bench 2.1

80.9% on Claude Opus 5 — a top-tier open-source result

72 of 89 tasks solved (pass@1) on the verified 89-task suite. On the [public leaderboard](https://www.tbench.ai/leaderboard/terminal-bench/2.1) that slots around 3rd — behind Claude Code / Fable 5 (83.8%) and Codex / GPT-5.5 (83.1%), ahead of Claude Code on Opus 4.8 (78.9%).

ClawCodex — the open-source Python rebuild of Claude Code — run headless on `claude-opus-5` at `effort=xhigh`. A single run (k=1) against the board's k=5 averages; benchmarked on `main` at #756. Fully reproducible from the open-source [Harbor adapter](eval/harbor/). **[Read the full breakdown ↓](#-news)**