Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Model Selection · communitytoolkit | DecimalAI

agent toolingby communitytoolkit

Model Selection

communitytoolkit/model-selection

Source communitytoolkit/aspire ↗License MIT

Determines which LLM model to use for each agent spawn

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 9/25/2026

What it changes

Passed 20 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill91%

Checks it passed that the model alone missed

Reads .squad/config.json at session startup.
Removes the defaultModel field from .squad/config.json.
Resolves model claude-sonnet-4.6 for the refactoring task.

and 13 more in the full report

14 fixed6 passed either way2 still failing0 broke

Pass-rate lift: +64 pp
Tokens: +29%
Agent turns: 0%
Response time: -42%

Model gemini-3.6-flashMeasured 9/25/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/communitytoolkit-model-selection/SKILL.md https://app.decimal.ai/s/communitytoolkit-model-selection/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add communitytoolkit-model-selection, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/communitytoolkit-model-selection/ and pins it in .decimal/skills.lock

decimalai skills add communitytoolkit-model-selection

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/communitytoolkit-model-selection/SKILL.md https://app.decimal.ai/s/communitytoolkit-model-selection/SKILL.md

Raw file: /s/communitytoolkit-model-selection/SKILL.md ↗ · machine-readable summary at /s/communitytoolkit-model-selection.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

In .squad/config.json, defaultModel is currently set to claude-opus-4.6. The user instructs: 'use claude-sonnet-4.6 for fenster'. How should .squad/config.json be updated?

What was checked, without and with the skill
Checked	Without skill	With skill
Preserves existing defaultModel property while adding agentModelOverrides entry for fenster.	Missed	Passed

case-21 · gemini-3.6-flash · 9/25/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md117 linessingle file

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 18+ models 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
2	Charter Preference	Agent's `charter.md` → `## Model` section	Persistent (in charter)
3	Task-Aware Auto	Code → sonnet, docs → haiku, visual → opus	Computed per-spawn
4	Default	`claude-haiku-4.5`	Hardcoded fallback

Key principle: Layer 0 (persistent config) beats everything. If the user said "always use opus" and it was saved to config.json, every agent gets opus regardless of role or task type. This is intentional — the user explicitly chose quality over cost.

AGENT WORKFLOW

On Session Start

READ .squad/config.json

Track record

Benchmark

20 / 22

test cases passed, vs 6 / 22 without

Adoption

Users: 1
Times used: 15

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/31/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

communitytoolkit / aspire

examples/squad/CommunityToolkit.Aspire.Hosting.Squad.AppHost/dev-squad/.squad/templates/skills/model-selection/SKILL.md

View on GitHub ↗

License MITImported 8/31/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

github/model-selectionDetermines which LLM model to use for each agent spawnNear-identical description+61 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Model Selection

SCOPE

Context

5-Layer Model Resolution Hierarchy

AGENT WORKFLOW

On Session Start

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills