lucassantana-dev/forgekit/adt-smart-model-route
Claude Code and agent skill by lucassantana-dev/forgekit
- community
Checking that the SKILL.md file is still in the repository.
Auto-classify prompt complexity via Haiku (with heuristic fallback) and inject model routing hints for Agent tool calls. Wired as a UserPromptSubmit hook — fires on every prompt, routes low tasks to Haiku, standard to Sonnet, complex to Sonnet with thorough reasoning, and critical (security/arch/migrations) to Opus. Handles model selection, for example choose model by task complexity.
Install
npx vskill@latest install lucassantana-dev/forgekit/adt-smart-model-routeSKILL.md
The same SKILL.md was published earlier as lucassantana-dev/forgekit/adt-smart-model-route.
Smart Model Route
Classifies each incoming prompt and injects a systemMessage telling the AI which model to pass to Agent tool calls and what reasoning depth to use. Uses Haiku for classification when ANTHROPIC_API_KEY is available; otherwise falls back to keyword heuristics.
How It Works
UserPromptSubmithook fires on every prompt- Sends prompt to
claude-haiku-4-5with a classification system prompt - Returns
low | medium | high | critical - Injects a
[AUTO:haiku]or[AUTO:heuristic]system message for non-medium tasks - Claude uses this to calibrate reasoning depth and
model:parameter on Agent calls
Classification Rules
| Level | Signals | Agent model | |
|---|---|---|---|
| low | Search, grep, read, git status, quick questions, <20 words | claude-haiku-4-5 | |
| medium | Standard coding, bug fixes, typical tasks (default) | claude-haiku-4-5 (env) | |
| high | Implement, refactor, debug, optimize, PR review, >15 words | claude-sonnet-4-6 | |
| critical | Security, OAuth, CVE, arch decisions, prod deploys, migrations | claude-opus-4-7 |
Installation
- Copy
complexity-classifier.shto~/.claude/hooks/ - Make it executable:
chmod +x ~/.claude/hooks/complexity-classifier.sh - Add to
settings.json:
- To enable Haiku-based classification (vs heuristic fallback):
Or to route through a local LiteLLM / Ollama proxy (set these to your own host + key):
Using in Agent Calls
Once the hook is active, Claude reads the injected hint and applies it:
Session Model Override
For architecture or security sessions, switch the main model:
Switch back when done:
Dependencies
anthropicPython SDK (for Haiku classification):pip install anthropic- Heuristic fallback requires no dependencies
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/catalog/catalog/skills/adt-smart-model-route/SKILL.md
Popularity
- Repository stars
- 1
- Repository forks
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/lucassantana-dev/forgekit/adt-smart-model-route)