router — security grade SAFE, quality 54/100

Security audit verdict: SAFE · quality 54/100

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 workweave · Codex Skill · ★ 3.8k

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

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

About router

<path d="M643 364C687.22 364 731.44 364 777 364C777 388.21 777 388.21 776.188 395.906C776.098 396.82 776.009 397.735 775.917 398.677C775.625 401.619 775.314 404.56 775 407.5C774.893 408.53 774.786 409.559 774.675 410.62C772.868 427.87 770.568 445.036 768 462.188C767.758 463.821 767.758 463.821 767.512 465.487C765.566 478.525 763.183 491.358 760.118 504.181C759.029 508.762 758.146 513.366 757.312 518C752.878 541.244 746.262 564.49 739 587C738.601 588.248 738.202 589.496 737.792 590.782C721.256 642.383 700.303 692.675 672 739C671.478 739.857 670.956 740.713 670.418 741.596C663.399 753.057 655.906 764.133 648 775C647.242 776.044 646.484 777.088 645.703 778.164C636.891 790.096 627.532 801.572 617.406 812.41C615.421 814.547 613.511 816.714 611.625 818.938C604.113 827.59 595.76 835.627 587 843C586.083 843.806 585.167 844.611 584.223 845.441C567.404 860.14 549.49 871.892 528.375 879.375C5

agentic-codingai-gatewayanthropicclaude-codecodexmodel-routeropenai-compatible

Quick Facts

Stars3,772
Forks103
LanguageGo
CategoryCodex Skill
Quality Score53.8165494307233/100
Open Issues106
Last Updated2026-09-04
Created2026-04-27
Platformsclaude-code, codex, go
Est. Tokens~21k

Compatible Skills

These tools work well together with router for enhanced workflows:

  • bifrost — semantic(0.29)+complementary+rare_topics+same_lang+shared_platform (59%)
  • skillboss-skills — semantic(0.31)+complementary+rare_topics+similar_pop+shared_platform (55%)

router alternative? Top 6 similar tools

Looking for a router alternative? If you're comparing router 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.

  • octopus by bestruirui · ⭐ 2.6k

    One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关

  • awesome-claude-skills by travisvn · ⭐ 15.1k

    A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particular

  • claude-code-ultimate-guide by FlorianBruniaux · ⭐ 6.0k

    The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and producti

  • Claude-Code-Everything-You-Need-to-Know by wesammustafa · ⭐ 2.6k

    A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl

  • pilot-shell by maxritter · ⭐ 2.1k

    Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software

  • llmgateway by theopenco · ⭐ 1.6k

    Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Go Agent Tools

Frequently Asked Questions

What is router?

router is Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.. It is categorized as a Codex Skill with 3.8k GitHub stars.

What programming language is router written in?

router is primarily written in Go. It covers topics such as agentic-coding, ai-gateway, anthropic.

How do I install or use router?

You can find installation instructions and usage details in the router GitHub repository at github.com/workweave/router. The project has 3.8k stars and 103 forks, indicating an active community.

What are the best alternatives to router?

The top alternatives to router on Agent Skills Hub include octopus, awesome-claude-skills, claude-code-ultimate-guide. 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