Maintainer of this skill?
Automated security scan — not a certification.
by kandada
A python-based light but strong lobster. A lightweight but powerful AI Agent framework in Python, with multi-channel support, tool calling, cron scheduling and streaming output
# Add to your Claude Code skills
git clone https://github.com/kandada/fastclawLast scanned: 10/20/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-10-20T09:10:07.087Z",
"npmAuditRan": true,
"pipAuditRan": false,
"promptInjectionRan": true
}See how fastclaw compares with popular alternatives.
fastclaw is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by kandada. A python-based light but strong lobster. A lightweight but powerful AI Agent framework in Python, with multi-channel support, tool calling, cron scheduling and streaming output. It has 169 GitHub stars.
Yes. fastclaw 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/kandada/fastclaw" and add it to your Claude Code skills directory (see the Installation section above).
fastclaw is primarily written in Python. It is open-source under kandada 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 fastclaw against similar tools.
No comments yet. Be the first to share your thoughts!
30 days in the Featured rail · terms & refunds
⚠️ 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.
Automated security scan — not a certification.
A lightweight but powerful AI Agent framework in Python.
# Install
pip install fastclaw-ai
# Run
fastclaw start
# Persistent running (recommended for server)
nohup fastclaw start > /tmp/fastclaw.log 2>&1 &
After starting, visit http://localhost:8765 , click Settings in the top right corner to configure main_agent, recommended: deepseek-chat.
Or edit the config file:
vim ~/.fastclaw/workspace/data/agents/main_agent/metadata.json
# Interactive chat
fastclaw chat
# New session
fastclaw chat --new
# Check status
fastclaw status
git clone https://github.com/kandada/fastclaw.git
cd fastclaw
pip install -r requirements.txt
# Run
python main.py start
# Persistent running
nohup python main.py start > fastclaw.log 2>&1 &
After starting, visit http://localhost:8765 , click Settings in the top right corner to configure main_agent, recommended: deepseek-chat.
Or edit the config file:
vim workspace/data/agents/main_agent/metadata.json
# Interactive chat
python main.py chat
# New session
python main.py chat --new
# Check status
python main.py status
FastClaw is built on the core concept of event-driven agent orchestration. Key design principles:
fastbrowser skill — real-browser automation (JS/SPA rendering, screenshots, downloads) and OS accessibility (read/act on web pages and native desktop apps) via the fastbrowser CLI driven with run_shellreasoning_content / thinking field / <think>...</think> tags (MiniMax-M3, Qwen3, etc.)skill_creator bundled meta-skill — guides the agent to create, update and optimize skills via chat/api/skills/user) — create, read, update, delete user skills_template excluded from skill listspython-socks[asyncio] dependency to fix Lark (Feishu) connection failure when using a SOCKS proxySyntaxError on Python 3.10/3.11 caused by backslash (\) inside f-string {} expressions (a Python 3.12+ syntax)UnicodeDecodeError on Windows Chinese systems by adding encoding="utf-8" to all read_text() / write_text() calls, fixing the crash on second startup</div> tags from WebUI HTML that could cause DOM parsing issueshttp://localhost:{port} alongside http://0.0.0.0:{port} for easier access on Windowsexcept blocks in router.py for easier debuggingripgrep an optional dependency to avoid compilation issues on Windows without MSVCGPL-3.0
Copyright (c) 2024-2026 xiefujin. All rights reserved.
https://www.fastclaw.world/ | https://fastclaw-ai.com/
FastClaw is part of the FastMind ecosystem. Other projects built on FastMind:
Inspired by OpenClaw. Special thanks to the open source community.
FastClaw is powerful, but its use depends entirely on the user - all responsibility lies with the user yourself.
Author：xiefujin email: 490021684@qq.com，welcome to contact me.