agent-c

Name: agent-c
Author: bravenewxyz

Verified

Ultra-lightweight AI Agent

444stars

29forks

Added 12/27/2025

Installation

# Add to your Claude Code skills
git clone https://github.com/bravenewxyz/agent-c

Getting Started

Guides for using ai agents skills like agent-c.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 5/20/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-05-20T07:43:45.572Z",
  "semgrepRan": false,
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is agent-c?

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 444 GitHub stars.

Is agent-c safe to use?

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.

How do I install agent-c?

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).

What programming language is agent-c written in?

agent-c is primarily written in C. It is open-source under bravenewxyz on GitHub, so you can review or fork the full source.

Are there alternatives to agent-c?

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.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,960

obsidian-claude-sidebar awesome-claude-code-skills

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.

Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.

Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Read the Terms of Service

Agent-C

An ultra-lightweight AI agent written in C that communicates with OpenRouter API and executes shell commands.

Agent-C Preview

Features

Zero Dependencies: No curl, no libssl — native TLS via macOS SecureTransport
Tool Calling: OpenAI-compatible tools API for shell command execution
Streaming: Tokens print as they arrive via SSE
~4KB binary: Single file (agent.c), LZMA self-extracting archive
Conversation Memory: Sliding window of 20 messages with tool call history
Cross-Platform: macOS and Linux

Quick Start

export OR_KEY=your_openrouter_api_key
make
./agent-c

Build

make          # auto-detect platform
make macos    # macOS with LZMA compression
make linux    # Linux with UPX compression
make clean    # remove build artifacts

How It Works

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.