How do I install the Setup Pstack skill?

Run npx skillmds@latest add scaryrawr/setup-pstack in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Setup Pstack safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Setup Pstack?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Setup Pstack free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Setup Pstack?

scaryrawr (@scaryrawr) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Setup Pstack by scaryrawr — Agent Skill

Name: Setup Pstack
Author: scaryrawr

Setup Pstack

Configure which models pstack uses per role. Detect available Copilot Task models and write an always-applied user instruction in Copilot home. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.

scaryrawr bc6e195 2.9 KB Updated Sep 17, 2026

File contents

Setup pstack

Write instructions/pstack-models.instructions.md in the user's Copilot home directory. Resolve Copilot home from $COPILOT_HOME when set, otherwise use $HOME/.copilot. The applyTo: "**" instruction makes the role mapping available across repositories, matching upstream pstack's always-applied user rule. The file is an override layer, not a requirement. When it is absent, omit the Task model argument and let Copilot choose the agent's default.

Steps

1. Detect available models

Read the current Task tool schema or another first-party Copilot model listing when the host exposes one. Treat it as authoritative for this session. When no first-party listing is available, keep every role at auto and do not invent explicit model IDs. auto and inherit-parent both mean to omit the Task model argument.

2. Load current state

Read instructions/pstack-models.instructions.md from Copilot home when it exists. Otherwise start every scalar role at auto and each panel at a single auto entry.

3. Map and confirm

Show every role with its current value. Mark unavailable IDs. Ask one focused ask_user question at a time when a choice is needed. Offer only detected model IDs plus auto.

Panel values are comma-separated lists. One subagent runs per entry, so the list length sets panel size. Recommend models from different families for judgment panels only when those models are available.

4. Validate

Every non-alias model ID must appear in the detected set. Stop before writing if any value is invalid.

5. Write the configuration

Create the Copilot home instructions directory when needed, then overwrite pstack-models.instructions.md so reruns are idempotent:

---
applyTo: "**"
---

# pstack model configuration

Use `auto` or `inherit-parent` to omit the Task `model` argument.

feature, refactoring: auto
bug-fix: auto
perf-issue: auto
hillclimb: auto
judgment and prose: auto
hardest tasks: auto
how explorer: auto
how explainer: auto
why investigators: auto
why synthesizer: auto
reflect tooling: auto
reflect judgment, divergent, synthesizer: auto
arena runners: auto
arena cross-judge pool: auto
swarm workers: auto
architect runners: auto
interrogate reviewers: auto

Replace aliases with validated IDs only when the user chooses explicit models.

6. Confirm

Tell the user which user-level configuration was written and which roles use explicit models. Explain that Copilot loads the change in new or resumed sessions.

7. Offer a verification skill

Check whether the project already has a verify-* skill or an equivalent runtime harness. If not, offer /create-verification-skill once. Do not push after a no.

---name: setup-pstackdescription: Configure which models pstack uses per role. Detect available Copilot Task models and write an always-applied user instruction in Copilot home. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.---# Setup pstackWrite `instructions/pstack-models.instructions.md` in the user's Copilot home directory. Resolve Copilot home from `$COPILOT_HOME` when set, otherwise use `$HOME/.copilot`. The `applyTo: "**"` instruction makes the role mapping available across repositories, matching upstream pstack's always-applied user rule. The file is an override layer, not a requirement. When it is absent, omit the Task `model` argument and let Copilot choose the agent's default.## Steps### 1. Detect available modelsRead the current Task tool schema or another first-party Copilot model listing when the host exposes one. Treat it as authoritative for this session. When no first-party listing is available, keep every role at `auto` and do not invent explicit model IDs. `auto` and `inherit-parent` both mean to omit the Task `model` argument.### 2. Load current stateRead `instructions/pstack-models.instructions.md` from Copilot home when it exists. Otherwise start every scalar role at `auto` and each panel at a single `auto` entry.### 3. Map and confirmShow every role with its current value. Mark unavailable IDs. Ask one focused `ask_user` question at a time when a choice is needed. Offer only detected model IDs plus `auto`.Panel values are comma-separated lists. One subagent runs per entry, so the list length sets panel size. Recommend models from different families for judgment panels only when those models are available.### 4. ValidateEvery non-alias model ID must appear in the detected set. Stop before writing if any value is invalid.### 5. Write the configurationCreate the Copilot home `instructions` directory when needed, then overwrite `pstack-models.instructions.md` so reruns are idempotent:```markdown---applyTo: "**"---# pstack model configurationUse `auto` or `inherit-parent` to omit the Task `model` argument.feature, refactoring: autobug-fix: autoperf-issue: autohillclimb: autojudgment and prose: autohardest tasks: autohow explorer: autohow explainer: autowhy investigators: autowhy synthesizer: autoreflect tooling: autoreflect judgment, divergent, synthesizer: autoarena runners: autoarena cross-judge pool: autoswarm workers: autoarchitect runners: autointerrogate reviewers: auto```Replace aliases with validated IDs only when the user chooses explicit models.### 6. ConfirmTell the user which user-level configuration was written and which roles use explicit models. Explain that Copilot loads the change in new or resumed sessions.### 7. Offer a verification skillCheck whether the project already has a `verify-*` skill or an equivalent runtime harness. If not, offer `/create-verification-skill` once. Do not push after a no.

Frequently asked questions