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 tzachbon · Claude Skill · ★ 76
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-model-router-hook safe to install? View the security audit →
Claude Model Router Hook Automatic model switching for Claude Code. No API calls, no config. A Claude Code hook system that classifies every prompt by task complexity and switches your active model automatically. Sub-agent model rules are injected into every session so spawned agents also use the right tier. Features Classifies prompts by complexity using keyword and pattern matching (zero API calls) Warns on tier mismatch by default; optionally auto-switches () Injects sub-agent model-selection rules into every session via Prefix any prompt with to bypass classification and keep the current model Logs every classification and switch to How It Works Two hook scripts run inside Claude Code: () injects a into every session that enforces these sub-agent rules: Architecture, deep multi-file analys
| Stars | 76 |
| Forks | 7 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 71.0759802685104/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-29 |
| Created | 2026-03-07 |
| Platforms | claude-code, python |
| Est. Tokens | ~17k |
Looking for a claude-model-router-hook alternative? If you're comparing claude-model-router-hook with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
📜 An MCP server for conversation history search and retrieval in Claude Code
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more.
Automated loop driver, slash commands, council automation, MCP browser bridge, and portfolio governance for Cl
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Explore other popular claude skill tools:
claude-model-router-hook is Claude Code hooks that auto-switch model tier based on task complexity. It is categorized as a Claude Skill with 76 GitHub stars.
claude-model-router-hook is primarily written in Python. It covers topics such as ai-tools, anthropic, automation.
You can find installation instructions and usage details in the claude-model-router-hook GitHub repository at github.com/tzachbon/claude-model-router-hook. The project has 76 stars and 7 forks, indicating an active community.
claude-model-router-hook is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claude-model-router-hook on Agent Skills Hub include claude-emporium, claudepro-directory, claude-historian-mcp. 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: