Setup Pstack

Setup pstack

Write ~/.claude/pstack-models.md, an always-applied rule that sets pstack's model per role.

Steps

1. Detect available models

Enumerate the model slugs you can pass to an Agent subagent in this session. That is the dependable source. If your 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 real slug you have not confirmed is available. The aliases inherit-parent and auto are always valid even though they are not detected slugs.

2. Load current state

The default role-to-model mapping is the rule shape shown in step 5 below. If ~/.claude/pstack-models.md 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 real slug not in the detected set as needing a choice. Ask whether to accept as-is or change specific roles, offering the detected models plus inherit-parent and auto (both mean: this role runs on the parent chat model, which is how Auto users stay on Auto) as the options. Prefer AskUserQuestion over free text. For panel roles (arena runners, architect runners, interrogate reviewers) the value is a list, and one subagent runs per entry, alias entries included, so the list length sets the count. arena cross-judge pool is also a list, but Arena selects one value from it whose model family differs from the parent's when possible. swarm workers is the default model for every worker unless a race or comparison assigns another model per arm.

4. Validate

Every real slug written must be in the detected set. inherit-parent and auto always pass. If a chosen real slug is not available, stop and ask again.

5. Write the rule

Write ~/.claude/pstack-models.md with alwaysApply: true and one line per role, using the same labels poteto-mode uses. Overwrite the whole file so re-runs stay idempotent. Shape:

# pstack model configuration. One line per role. Delete a line to fall back to the skill default.
# `inherit-parent` or `auto` as a value: the role runs on the parent chat model (omit Task `model`). Alias entries in a panel list still count toward its fan-out.
feature, refactoring: grok-4.6-fast-xhigh
bug-fix: claude-fable-5-1-thinking-max
perf-issue: claude-fable-5-1-thinking-max
hillclimb: claude-fable-5-1-thinking-max
judgment and prose: claude-fable-5-1-thinking-max
hardest tasks: claude-fable-5-1-thinking-max
how explorer: grok-4.6-fast-xhigh
how explainer: claude-fable-5-1-thinking-max
why investigators: grok-4.6-fast-xhigh
why synthesizer: claude-fable-5-1-thinking-max
reflect tooling: gpt-5.6-sol-max
reflect judgment, divergent, synthesizer: claude-fable-5-1-thinking-max
arena runners: claude-fable-5-1-thinking-max, gpt-5.6-sol-max, grok-4.6-fast-xhigh, claude-opus-5-thinking-xhigh
arena cross-judge pool: claude-fable-5-1-thinking-max, gpt-5.6-sol-max, grok-4.6-fast-xhigh, claude-opus-5-thinking-xhigh
swarm workers: grok-4.6-fast-xhigh
architect runners: claude-fable-5-1-thinking-max, gpt-5.6-sol-max, grok-4.6-fast-xhigh, claude-opus-5-thinking-xhigh
interrogate reviewers: claude-fable-5-1-thinking-max, gpt-5.6-sol-max, grok-4.6-fast-xhigh, claude-opus-5-thinking-xhigh

6. Confirm

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

7. Offer a verification skill (optional)

Check whether the project has a way to drive the real app for proof (a verify-* skill, or an existing harness). If not, offer once: "want a project-local verification skill, so agents can drive the app the way a user does and prove changes work? I can generate one with /create-verification-skill." On yes, invoke /create-verification-skill (resolves wherever pstack is installed: workspace, user, or plugin). On no, move on without pushing.

Claude Code model values

The role defaults quoted above are Cursor model slugs (grok-4.6-fast-xhigh, gpt-5.6-sol-max, claude-opus-5-thinking-xhigh). None of them are valid here.

In Claude Code the only values you may write are the Agent tool's model enum:

• opus, sonnet, haiku, fable
• plus the inherit-parent and auto aliases

Reasoning effort is a separate axis in Claude Code (effort), not part of the model name, so it cannot be expressed in ~/.claude/pstack-models.md. Drop the -thinking-xhigh / -max suffixes rather than trying to encode them.

Panel roles take a list, and the list length sets the fan-out — one subagent per entry. A single-model panel defeats the point of cross-judging, so keep at least two families in any list.