asc-model-setup

Files (2)

• ATTRIBUTION.md
• SKILL.md

SKILL.md (first lines)

# ASC model setup

Write the always-applied ASC model rule, which sets the asc skills' model per role. The skills read it and fall back to their inline defaults when a line is absent, so this is an override layer, not a requirement.

## Steps

### 1. Detect available models

Enumerate the model slugs you can pass to a `Task` subagent in this session; that is the dependable source. If the host also exposes a models API or CLI that lists the user's entitled models, prefer it for completeness. If you cannot detect any, ask the user to paste the slugs they have access to. Never write a slug you have not confirmed is available.

### 2. Load current state

The default role-to-model mapping is the rule shape shown in step 5 below. If the rule already exists, read it and treat its values as the current choices. Otherwise start from those defaults.

### 3. Map and confirm

Show every role with its current model, marking any whose model is not in the detected set as needing a choice. Ask whether to accept as-is or change specific roles, offering the detected models as the options. Prefer AskQuestion over free text. For panel roles (how critics, arena runners, architect runners, interrogate reviewers) the value is a list, and one subagent runs per model, so the list length sets the count.

### 4. Validate

Every slug written must be in the detected set. If a chosen slug is not available, stop and ask again. A rule pointing at a model the user cannot use breaks every delegation that reads it.

### 5. Write the rule

Write the always-applied ASC model rule with `alwaysApply: true` and one line per role, using generic role descriptors rather than harness-specific model labels. Overwrite the whole file so re-runs stay idempotent. Shape:

```
---
description: asc per-role model choices (overrides skill defaults)
alwaysApply: true
---
# ASC model configuration. One line per role. Delete a line to fall back to the skill default.
feature, refactoring: fast code model
bug-fix: stronger reasoning model
perf-issue: stronger reasoning model
hillclimb: stronger reasoning model
judgment and prose: strongest reasoning model
how explorer: fast code model
how explainer: strongest reasoning model
how critics: strongest reasoning model, mid reasoning model, fast code model
why investigators: fast code model
why synthesizer: strongest reasoning model
reflect tooling: fast code model
reflect judgment, divergent, synthesizer: strongest reasoning model
arena runners: strongest reasoning model, mid reasoning model, fast code model
architect runners: strongest reasoning model, mid reasoning model, fast code model
interrogate reviewers: strongest reasoning model, mid reasoning model, fast code model
```

### 6. Confirm

Tell the user the rule was written and that it applies to new sessions. Re-running this skill updates it.

From cavaunpeu/agent-skills-closet, MIT.

More from cavaunpeu/agent-skills-closet