model-selection

Context

Before spawning an agent, the coordinator determines which model to use. This skill codifies the 4-layer hierarchy, role-to-model mappings, task complexity adjustments, and fallback chains. Applies to all agent spawns in Team Mode.

Patterns

4-Layer Hierarchy

Check these layers in order — first match wins:

Layer 1 — User Override: Did the user specify a model? ("use opus", "save costs", "use gpt-5.3-codex for this"). If yes, use that model. Session-wide directives ("always use haiku") persist until contradicted.

Layer 2 — Charter Preference: Does the agent's charter have a ## Model section with Preferred set to a specific model (not auto)? If yes, use that model.

Layer 3 — Task-Aware Auto-Selection: Use the governing principle: cost first, unless code is being written. Match the agent's task to determine output type, then select accordingly:

Role-to-model mapping (applying cost-first principle):

Task complexity adjustments (apply at most ONE — no cascading):

• Bump UP to premium: architecture proposals, reviewer gates, security audits, multi-agent coordination (output feeds 3+ agents)
• Bump DOWN to fast/cheap: typo fixes, renames, boilerplate, scaffolding, changelogs, version bumps
• Switch to code specialist (gpt-5.3-codex): large multi-file refactors, complex implementation from spec, heavy code generation (500+ lines)
• Switch to analytical diversity (gemini-3.1-pro): code reviews where a second perspective helps, security reviews, architecture reviews after a rejection

Layer 4 — Default: If nothing else matched, use gpt-5.6-luna. Cost wins when in doubt, unless code is being produced.

Fallback Chains

If a spawn fails because the selected model is unavailable (plan restriction, org policy, rate limit, deprecation, or any other reason), silently retry with the next model in the chain. Do NOT tell the user about fallback attempts. Maximum 3 retries before using the platform default fallback.

Premium:  gpt-5.6-sol → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → claude-opus-4.6 → claude-sonnet-4.6 → (omit model param)
Standard: gpt-5.6-terra → claude-sonnet-5 → claude-sonnet-4.6 → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → claude-sonnet-4.5 → gemini-3.1-pro → (omit model param)
Fast:     gpt-5.6-luna → claude-haiku-4.5 → gpt-5.4-mini → gpt-5-mini → (omit model param)

(omit model param) = call the task tool WITHOUT the model parameter. The platform uses its built-in default. This is the platform default fallback — it lets the platform choose the model.

Fallback rules:

• If the user specified a provider ("use Claude"), fall back within that provider only before using the platform default fallback
• Never fall back UP in tier — a fast/cheap task should not land on a premium model
• Log fallbacks to the orchestration log for debugging, but never surface to the user unless asked

Passing the Model to Spawns

Pass the resolved model as the model parameter on every task tool call:

agent_type: "general-purpose"
model: "{resolved_model}"
mode: "background"
description: "{emoji} {Name}: {brief task summary}"
prompt: |
  ...

Only set model when it differs from the platform default (claude-sonnet-4.6). If the resolved model IS claude-sonnet-4.6, you MAY omit the model parameter — the platform uses it as default.

If you've exhausted the fallback chain and reached the platform default fallback, omit the model parameter entirely.

Spawn Output Format

When spawning, include the model in your acknowledgment:

🔧 Agent Alpha (claude-sonnet-5) — refactoring auth module
🎨 Agent Beta (gpt-5.6-sol · vision) — designing color system
📋 Scribe (gpt-5.6-luna · fast) — logging session
⚡ Agent Gamma (gpt-5.6-sol · bumped for architecture) — reviewing proposal
📝 Agent Delta (gpt-5.6-luna · fast) — updating docs

Include tier annotation only when the model was bumped or a specialist was chosen. Default-tier spawns just show the model name.

Valid Models

Premium: gpt-5.6-sol, claude-opus-5, claude-opus-4.8, claude-opus-4.7, claude-opus-4.6 Standard: gpt-5.6-terra, claude-sonnet-5, claude-sonnet-4.6, claude-sonnet-4.5, gpt-5.5, gpt-5.4, gpt-5.3-codex, gemini-3.1-pro Fast/Cheap: gpt-5.6-luna, claude-haiku-4.5, gpt-5.4-mini, gpt-5-mini

Examples

Example 1: Backend dev writing API endpoints

• Role: Backend Dev
• Task: "implement REST endpoints for user management"
• Layer 3 decision: writing code → gpt-5.6-terra (standard tier)
• Spawn: 🔧 Agent Alpha (gpt-5.6-terra) — implementing user API endpoints

Example 2: User override

• User says: "use haiku for everything this session"
• Layer 1 overrides all other layers
• All spawns use claude-haiku-4.5 regardless of role or task

Example 3: Complex refactor

• Role: Backend Dev
• Task: "refactor 15 auth-related files to use new token system"
• Layer 3 base: gpt-5.6-terra
• Task complexity: heavy multi-file refactor → switch to gpt-5.3-codex
• Spawn: 🔧 Agent Alpha (gpt-5.3-codex · code specialist) — refactoring auth to new token system

Example 4: Scribe logging

• Role: Scribe
• Task: "log session to decisions.md"
• Layer 3: NOT writing code → gpt-5.6-luna
• Role mapping: Scribe always luna, never bump
• Spawn: 📋 Scribe (gpt-5.6-luna · fast) — logging session

Anti-Patterns

• ❌ Falling back UP in tier (fast task landing on premium model)
• ❌ Telling the user about fallback attempts ("Opus failed, trying Sonnet")
• ❌ Bumping Scribe or mechanical ops agents to higher tiers
• ❌ Using premium models for documentation or planning tasks
• ❌ Applying multiple complexity adjustments (cascading bumps)
• ❌ Forgetting to include model in spawn acknowledgment
• ❌ Downgrading vision-required tasks from the premium visual model