ClawRouter — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by BlockRunAI · Codex Skill · ★ 6.6k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ClawRouter safe to install? View the security audit →

About ClawRouter

The agent-native LLM router for OpenClaw Route every request to the right model at the right price. 15-dimension scoring, One wallet, 41+ models, zero API keys.         [](https://github.com/BlockRunAI/ClawRouter/ac

aiai-agentsanthropiccost-optimizationdeepseekgeminillmllm-routermicropaymentsopenai

Quick Facts

Stars6,611
Forks651
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score62.520580571032/100
Open Issues3
Last Updated2026-09-21
Created2026-02-03
Platformsgemini, node
Est. Tokens~17k

Compatible Skills

These tools work well together with ClawRouter for enhanced workflows:

  • pinion-os — semantic(0.41)+complementary+rare_topics+same_lang+shared_platform (58%)
  • aixyz — semantic(0.37)+complementary+rare_topics+same_lang+shared_platform (52%)
  • manifest — semantic(0.30)+rare_topics+same_lang+similar_pop+shared_platform (50%)
  • proxy — semantic(0.25)+complementary+rare_topics+same_lang+shared_platform (48%)

ClawRouter alternative? Top 6 similar tools

Looking for a ClawRouter alternative? If you're comparing ClawRouter with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • awesome-free-llm-apis by mnfst · ⭐ 6.9k

    List of Permanent Free LLM API (API Keys)

  • 9router by decolua · ⭐ 29.6k

    Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/G

  • repomix by yamadashy · ⭐ 28.4k

    📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w

  • bytebot by bytebot-ai · ⭐ 11.1k

    Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, ope

  • ai-guide by liyupi · ⭐ 19.8k

    程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享 OpenClaw 保姆级教程、大模型玩法(DeepSeek / GPT / Gemini / Claude / GLM)、最新 AI 资讯、Pr

  • unity-mcp by CoplayDev · ⭐ 14.4k

    Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets,

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is ClawRouter?

ClawRouter is The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.. It is categorized as a Codex Skill with 6.6k GitHub stars.

What programming language is ClawRouter written in?

ClawRouter is primarily written in TypeScript. It covers topics such as ai, ai-agents, anthropic.

How do I install or use ClawRouter?

You can find installation instructions and usage details in the ClawRouter GitHub repository at github.com/BlockRunAI/ClawRouter. The project has 6.6k stars and 651 forks, indicating an active community.

What license does ClawRouter use?

ClawRouter is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ClawRouter?

The top alternatives to ClawRouter on Agent Skills Hub include awesome-free-llm-apis, 9router, repomix. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools