メニュー
Configure which models pstack uses per role. Detects your available Claude models and writes a per-role override file that the user can include from their CLAUDE.md. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | setup-pstack |
| description | Configure which models pstack uses per role. Detects your available Claude models and writes a per-role override file that the user can include from their CLAUDE.md. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices. |
Write ~/.claude/pstack-models.md, a per-role model override sheet you include from your global CLAUDE.md. Each pstack skill names a default model inline; the override sheet is the layer that adapts those defaults to the models you actually have access to.
Platform note. On Codex or another non-Claude runtime, the override sheet is ~/.codex/pstack-models.md, the slugs are your Codex models (for example gpt-5.5) not claude-*, and you load it by adding the sheet's contents to ~/.codex/AGENTS.md (Codex has no @-include into a rules file). The role rows in step 5 are identical; only the slugs, the file path, and the load mechanism change. Detect Codex slugs from ~/.codex/config.toml (model = ...) plus whatever the user confirms. See codex-tools.md.
Claude Code has no auto-applied "rules" mechanism like Cursor's .mdc. Inclusion is explicit: the user adds a line to ~/.claude/CLAUDE.md (or their project CLAUDE.md) such as:
@~/.claude/pstack-models.md
so the file is loaded as context for every session.
Enumerate the model slugs you can pass to an Agent subagent in this session — that is the dependable source. Claude family currently available: Opus 4.8 (claude-opus-4-8), Fable 5 (claude-fable-5), Sonnet 5 (claude-sonnet-5), Sonnet 4.6 (claude-sonnet-4-6), Haiku 4.5 (claude-haiku-4-5). The default panels run Opus 4.8 (claude-opus-4-8), Fable 5 (claude-fable-5), and both sonnet generations (5, 4-6) for cross-family, cross-tier diversity. Ask the user to confirm or paste any additional slugs they want available. Never write a slug you have not confirmed is available.
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.
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 AskUserQuestion 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. arena cross-judge pool is also a list, but Arena selects one model from it whose family differs from the parent's when possible.
Every slug written must be in the detected set. If a chosen slug is not available, stop and ask again. An override pointing at a model the user cannot use breaks every delegation that reads it.
Write ~/.claude/pstack-models.md with the shape below. Overwrite the whole file so re-runs stay idempotent.
# pstack model configuration
Per-role model overrides for pstack skills. Each pstack SKILL.md names a default model inline; the values here override those defaults. Delete a line to fall back to the skill default.
feature, refactoring: claude-opus-4-8
bug-fix: claude-opus-4-8
perf-issue: claude-opus-4-8
hillclimb: claude-opus-4-8
judgment and prose: claude-opus-4-8
how explorer: claude-opus-4-8
how explainer: claude-opus-4-8
how critics: claude-opus-4-8, claude-sonnet-5, claude-fable-5, claude-sonnet-4-6
why investigators: claude-opus-4-8
why synthesizer: claude-opus-4-8
reflect tooling: claude-opus-4-8
reflect judgment, divergent, synthesizer: claude-opus-4-8
arena runners: claude-opus-4-8, claude-sonnet-5, claude-fable-5, claude-sonnet-4-6
arena cross-judge pool: claude-opus-4-8, claude-sonnet-5, claude-fable-5
architect runners: claude-opus-4-8, claude-sonnet-5, claude-fable-5, claude-sonnet-4-6
interrogate reviewers: claude-opus-4-8, claude-sonnet-5, claude-fable-5, claude-sonnet-4-6
If ~/.claude/CLAUDE.md does not already include ~/.claude/pstack-models.md, append the @~/.claude/pstack-models.md line so it loads on every session. If the user prefers project scope, add the include to the project's CLAUDE.md instead.
Tell the user where the override was written and how it loads (via the @ include in CLAUDE.md). Re-running this skill updates the override sheet.
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.