# Add to your Claude Code skills
git clone https://github.com/bravenewxyz/agent-cLast scanned: 5/20/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-20T07:43:45.572Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}agent-c is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by bravenewxyz. Ultra-lightweight AI Agent. It has 440 GitHub stars.
Yes. agent-c passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/bravenewxyz/agent-c" and add it to your Claude Code skills directory (see the Installation section above).
agent-c is primarily written in C. It is open-source under bravenewxyz on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agent-c against similar tools.
No comments yet. Be the first to share your thoughts!
An ultra-lightweight AI agent written in C that communicates with OpenRouter API and executes shell commands.

tools API for shell command executionagent.c), LZMA self-extracting archiveexport OR_KEY=your_openrouter_api_key
make
./agent-c
make # auto-detect platform
make macos # macOS with LZMA compression
make linux # Linux with UPX compression
make clean # remove build artifacts
The agent connects to OpenRouter, sends messages with a sh tool definition, and streams the response. When the model returns a tool_calls response, the agent executes the command, sends the result back, and gets a follow-up response. Up to 5 tool calls per turn.
See SPEC.md for full architecture and test cases.
CC0 — No Rights Reserved