model-selection SKILL.md skillA

model-selection from bradygaster/squad is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bradygaster/squad/model-selection@git:20261016.89d6302

Pins git:20261016.89d6302 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bradygaster/squad
Path
packages/squad-cli/templates/skills/model-selection/SKILL.md
Versions recorded
5
Latest version
git:20261016.89d6302, committed Oct 16, 2026
First version recorded
Jul 13, 2026
Size
8,082 bytes
Repository stars
3,298
License
MIT

Determines which LLM model to use for each agent spawn.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Model Selection

> Determines which LLM model to use for each agent spawn.

## SCOPE

✅ THIS SKILL PRODUCES:
- A resolved `model` parameter for every `task` tool call
- Persistent model preferences in `.squad/config.json`
- Spawn acknowledgments that include the resolved model

❌ THIS SKILL DOES NOT PRODUCE:
- Code, tests, or documentation
- Model performance benchmarks
- Cost reports or billing artifacts

## Context

Squad supports a curated model catalog across three tiers (premium, standard, fast). The coordinator must select the right model for each agent spawn. Users can set persistent preferences that survive across sessions.

## 5-Layer Model Resolution Hierarchy

Resolution is **first-match-wins** — the highest layer with a value wins.

| Layer | Name | Source | Persistence |
|-------|------|--------|-------------|
| **0a** | Per-Agent Config | `.squad/config.json` → `agentModelOverrides.{name}` | Persistent (survives sessions) |
| **0b** | Global Config | `.squad/config.json` → `defaultModel` | Persistent (survives sessions) |
| **1** | Session Directive | User said "use X" in current session | Session-only |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bradygaster/squad/model-selection@sha256:7b595da2213199b1

The line at the top of this page pins the label git:20261016.89d6302, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xevzg6qxlc7ptnrw.svg)](https://markdownregistry.com/a/art_xevzg6qxlc7ptnrw)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jul 13, 2026 and Oct 16, 2026, about one every 24 days.

versioncommittedcommitsizeaudit
git:20261016.89d6302 latest2026-10-16 89d6302 8,082 BA view · diff
git:20260910.61e2f812026-09-10 61e2f81 5,145 BA view · diff
git:20260823.3699cb82026-08-23 3699cb8 5,138 BA view · diff
git:20260713.b970d042026-07-13 b970d04 5,139 BA view · diff
git:20260713.d1160992026-07-13 d116099 5,009 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8082 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

bradygaster/squad · 3,298 stars · license MIT · pushed 2026-10-22 · branch dev

API

GET https://markdownregistry.com/api/v1/artifacts/art_xevzg6qxlc7ptnrw
GET https://markdownregistry.com/api/v1/resolve?ref=bradygaster/squad/model-selection
GET https://markdownregistry.com/api/v1/blob/7b595da2213199b132360c67240a6c070c9f1c30834c21b8365a01e047a9ee67

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from bradygaster/squad

action-skill-contracts SKILL.md skill
bradygaster/squad · .copilot/skills/action-skill-contracts/SKILL.md · Author deterministic skills for operations that change state or invoke external tools
git:20260911.f640e80 · audit A · 3,298 stars
agent-collaboration SKILL.md skill
bradygaster/squad · .copilot/skills/agent-collaboration/SKILL.md · Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
git:20260320.9081840 · audit A · 3,298 stars
agent-conduct SKILL.md skill
bradygaster/squad · .copilot/skills/agent-conduct/SKILL.md · Shared hard rules enforced across all squad agents
git:20260320.9081840 · audit A · 3,298 stars
architectural-proposals SKILL.md skill
bradygaster/squad · .copilot/skills/architectural-proposals/SKILL.md · How to write comprehensive architectural proposals that drive alignment before code is written
git:20260910.61e2f81 · audit A · 3,298 stars
architectural-review SKILL.md skill
bradygaster/squad · .copilot/skills/architectural-review/SKILL.md · How to review PRs for architectural quality — module boundaries, dependency direction, export surface, pattern…
git:20260403.003f05f · audit A · 3,298 stars
archival-integrity SKILL.md skill
bradygaster/squad · .copilot/skills/archival-integrity/SKILL.md · Preserve content when moving entries between tracked Squad state files
git:20260911.f640e80 · audit A · 3,298 stars
ci-validation-gates SKILL.md skill
bradygaster/squad · .copilot/skills/ci-validation-gates/SKILL.md · Defensive CI/CD patterns: semver validation, token checks, retry logic, and draft detection
git:20260911.f640e80 · audit A · 3,298 stars
cli-wiring SKILL.md skill
bradygaster/squad · .copilot/skills/cli-wiring/SKILL.md · Checklist and patterns for wiring new CLI commands into cli-entry.ts
git:20260626.62c5249 · audit A · 3,298 stars
client-compatibility SKILL.md skill
bradygaster/squad · .copilot/skills/client-compatibility/SKILL.md · Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces
git:20260911.f640e80 · audit A · 3,298 stars
content-scope SKILL.md skill
bradygaster/squad · .copilot/skills/content-scope/SKILL.md · Keep Squad documentation focused on shipped behavior and clearly bounded integrations
git:20260911.f640e80 · audit A · 3,298 stars
distributed-mesh SKILL.md skill
bradygaster/squad · .copilot/skills/distributed-mesh/SKILL.md · How to coordinate with squads on different machines using git as transport
git:20260320.9081840 · audit A · 3,298 stars
documentation-maintenance SKILL.md skill
bradygaster/squad · .copilot/skills/documentation-maintenance/SKILL.md · Maintain accurate, scannable Squad documentation with validated inventory and links
git:20260911.f640e80 · audit A · 3,298 stars

Every file in bradygaster/squad

Other files named model-selection

model-selection SKILL.md skill
bradygaster/squad · .squad-templates/skills/model-selection/SKILL.md · Determines which LLM model to use for each agent spawn
git:20260910.61e2f81 · audit A · 3,298 stars
model-selection SKILL.md skill
bradygaster/squad · .copilot/skills/model-selection/SKILL.md · Per-agent model selection with 4-layer hierarchy and fallback chains
git:20260910.61e2f81 · audit B · 3,298 stars
model-selection SKILL.md skill
bradygaster/squad · .squad/skills/model-selection/SKILL.md · Resolve explicit and persistent model preferences for Squad spawns without pinning stale defaults
git:20260913.8b79211 · audit A · 3,298 stars
model-selection SKILL.md skill
aperivue/medsci-skills · skills/model-selection/SKILL.md · Use when choosing the model for a medical-imaging study. Picks a paper-grounded architecture family (CNN/ViT…
git:20261002.0400856 · audit A · 346 stars

Browse by kind, by grade A, or by owner.