# Model Selection Router

> - Route every AI job to the cheapest model that survives review, and stop defaulting to the frontier out of habit. Use whenever someone asks "which model should I use", "is the expensive model worth it", "should we switch models", "a new model came out — do we move?", "the benchmark says X is best", "we're overpaying for AI", "what should our default model be", or wants help with model routing, tiering, or per-task model assignment. Also fires on: choosing reasoning-effort settings, building a personal eval set, fighting a bad corporate default model with evidence, triaging an agent/tool launch, or spec'ing a whole job for an expensive frontier run. Covers three-tier routing (daily driver / cheap workhorse / frontier) plus specialists, the seven job-classification questions, benchmark-interpretation discipline, 30-minute and one-week eval protocols, and the five-question new-launch filter. If a model name appears before the work has been described, this skill applies.

## Facts
- Page: https://tashan.sh/capability/skill-cloud-byte-consulting-model-selection-router
- tashan id: skill:Cloud-Byte-Consulting/model-selection-router
- Source: https://github.com/Cloud-Byte-Consulting/plugins
- Type: skill
- Category: ai
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 95.0
- Freshness: 90.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: Apache-2.0
- Official: no

## Install

```sh
cp -r model-selection-router ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-22 by tashan (https://tashan.sh) from public evidence. Scorer s5.