smart-model-routing

Solid

Dynamic model selection based on task complexity scoring. Replaces static model mappings with a weighted signal system that picks Opus, Sonnet, or Haiku-class speed per task. Works with agent-assignment-matrix.md.

AI & Automation 496 stars 41 forks Updated 1 months ago MIT

Install

View on GitHub

Quality Score: 86/100

Stars 20%
90
Recency 20%
75
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Smart Model Routing Dynamic model selection based on task complexity. Never use a sledgehammer where a scalpel will do — and never use a scalpel where you need a sledgehammer. ## Core Philosophy Static model assignments ("always use Sonnet for code") waste money on trivial tasks and produce poor results on complex ones. This skill scores every task across three signal categories and routes it to the appropriate model tier automatically. **Default rule: inherit parent model.** Only override when the score clearly warrants a different tier. Never specify a model without a scoring reason. --- ## Signal Categories Three weighted categories are evaluated. Their scores combine into a single complexity score (0-20 typical range, can exceed). ### Category 1: Lexical Signals (weight: 0.3) Analyze the raw text of the request. #### Architecture Keywords (+3 each) Trigger words that indicate high-stakes design work: - "redesign", "overhaul", "new system", "migrate", "refactor entire", "rewrite" - "architecture", "from scratch", "greenfield", "new service", "platform" Example: "Redesign the authentication system" → +3 #### Risk Keywords (+2 each) Domains where mistakes are expensive or irreversible: - "production", "security", "auth", "authentication", "authorization" - "payment", "billing", "database migration", "data loss", "rollback" - "GDPR", "compliance", "PII", "encryption", "secrets", "credentials" Example: "Update the payment processing logic" → +2 #### Simple Keyw...

Details

Author
vibeeval
Repository
vibeeval/vibecosystem
Created
2 months ago
Last Updated
1 months ago
Language
C#
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

model-routing

Vendor-neutral routing guide for choosing the right model tier by task type. Mechanical work uses a smaller/faster model; implementation uses a standard model; architecture, security, and release audit use the most capable model.

7 Updated 2 days ago
yeaight7
AI & Automation Listed

model

Model selection strategy and routing. Use when choosing between models for different task types, subagent configurations, or optimizing token cost vs quality tradeoffs.

42 Updated 1 months ago
xiaobei930
AI & Automation Solid

smart-routing

Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

1,160 Updated today
a5c-ai
AI & Automation Listed

cost-routing

Top-level dispatcher that classifies every incoming request into scout / coder / architect tiers BEFORE any tool call. Routes Read, Grep, Glob, file-search, symbol-lookup, "where is X", and "list files matching Y" to haiku-scout. Routes known-location Edit, Write, multi-file refactor, test authoring, and bounded code changes to sonnet-coder. Reserves the main opus context for ambiguous design questions, ADRs, and tradeoff analysis. Use whenever a request lands in the main context and might involve file IO, code search, code edits, or design reasoning — which is almost every turn.

1 Updated 2 days ago
The-Artificer-of-Ciphers-LLC
AI & Automation Listed

cost-aware-pipeline

Cost-aware LLM pipeline patterns for optimal model routing, narrow retry strategies, and prompt caching. Reduces API costs 40-70% through intelligent model selection, targeted retries, and cache-friendly prompt structures. Use when: (1) Building multi-model pipelines, (2) Optimizing API costs, (3) Designing retry strategies for LLM calls, (4) Implementing prompt caching, (5) Choosing between haiku/sonnet/opus for sub-tasks.

11 Updated today
stevengonsalvez