# Agent Model Assignment

> Use when deciding which model an agent or subagent should run on, or reviewing an existing assignment. Triggers on "which model should this agent use", "assign a model", "is haiku enough for this agent", "should this be opus", "model frontmatter", "agent is too slow", "agent is too expensive", "subagent keeps losing track", "cut agent costs", or when writing a new agent's frontmatter. Applies a constraints-first decision procedure and explains the cost, speed, and reliability tradeoffs behind each tier.

## Facts
- Page: https://tashan.sh/capability/skill-dotknewt-agent-model-assignment
- tashan id: skill:dotknewt/agent-model-assignment
- Source: https://github.com/dotknewt/awesome-agency
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 96.0
- Freshness: 92.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r agent-model-assignment ~/.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 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.