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 nidhi-singh02 · Codex Skill · ★ 52
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-router safe to install? View the security audit →
Agent Router Local-first, quota-aware routing for AI coding agents in Herdr. is a command-line tool that picks an AI coding agent, model, and reasoning effort for a task, then starts that agent for you in a Herdr pane. It filters your subscriptions with fixed rules (enabled models, quota, the 40% reserve on shared accounts), asks TypeSafe to rank what is left and choose an effort, starts the chosen agent (Cursor, Claude Code, Codex, or OpenCode), and hands it the task. Pre-release: the project is under active development. Review the security and privacy notes below before using real credentials or shared accounts. Demo Why Agent Router? Quota-aware: routes around depleted or reserved subscription capacity. Policy-first: deterministic eligibility rules run before semantic ranking. Local-first: configuration, usage snapshots, decisions, and session history stay on your machine unless an explicitly configured integration needs them. Agent-agnostic: supports Cursor, Claude Code, Codex, and OpenCode through one command. Prerequisites Node.js 20 or newer ( reads ). A TypeSafe API key. Routing always calls TypeSafe; there is no fallback. Each run sends the task text to
| Stars | 52 |
| Forks | 3 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 72.4778198118978/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-19 |
| Created | 2026-09-17 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~18k |
These tools work well together with agent-router for enhanced workflows:
Looking for a agent-router alternative? If you're comparing agent-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.
A curated set of modern CLI/TUI tools and AI coding assistants in a container. Batteries included.
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Credential-scoped AI quota, context, and cache in Herdr for Claude, Codex, Grok, Agy, OpenCode, Pi, omp, Devin
Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context.
Advanced Claude Code CLI toolkit - agents, hooks, skills, MCP servers, phased development, site intelligence d
Explore other popular codex skill tools:
agent-router is CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr. It is categorized as a Codex Skill with 52 GitHub stars.
agent-router is primarily written in TypeScript. It covers topics such as agents, ai, claude-code.
You can find installation instructions and usage details in the agent-router GitHub repository at github.com/nidhi-singh02/agent-router. The project has 52 stars and 3 forks, indicating an active community.
agent-router is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agent-router on Agent Skills Hub include squarebox, jev-review, claude-code-open. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: