Setup Pstack logo

Setup Pstack

CommunityPopular
michael-denyer
setup-pstack

Configure which models pstack uses per role. Detects available models and writes the current runtime's override sheet. Use for /setup-pstack, "configure pstack models", changing pstack's model choices, or turning the SessionStart hook on or off.

Overview

Publishermichael-denyer
Repositorypstack-claude
Skill namesetup-pstack
Stars
1.2K
Forks
139
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by michael-denyer on GitHub. Read the source before you install it.

Installation

Install the Setup Pstack AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/michael-denyer/pstack-claude/tree/main/plugins/pstack/skills/setup-pstack
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/michael-denyer/pstack-claude.git /tmp/pstack-claude
mkdir -p .claude/skills
cp -r /tmp/pstack-claude/plugins/pstack/skills/setup-pstack .claude/skills/setup-pstack
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Setup Pstack in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Setup Pstack on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Setup Pstack is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Setup pstack

On Codex, read the platform mapping, including its per-skill notes, before following this skill.

On another runtime, read Other runtimes below for where the sheet lives and how it loads; the steps are the same.

Write the current runtime's per-role model override sheet, using the path in Other runtimes. Each pstack skill names a default model inline; the override sheet adapts those defaults to the models you actually have access to.

Claude Code has no auto-applied "rules" mechanism like Cursor's .mdc. The Claude Code config directory is $CLAUDE_CONFIG_DIR when that variable is set and ~/.claude otherwise. This skill calls it <config>. Inclusion is explicit: the user adds a line to <config>/CLAUDE.md (or their project CLAUDE.md) such as:

text
@<config>/pstack-models.md

with <config> written as the resolved path, so the file is loaded as context for every session.

The Codex home directory is $CODEX_HOME when that variable is set and ~/.codex otherwise. This skill calls it <codex-home>.

Steps

1. Detect available models

Enumerate the model names the Agent tool's model parameter accepts in this session. That is the dependable source. On Claude Code they are the family names listed in Models below, each running that family's current model, and a full model ID is rejected. The default panel is listed there too. The panel is chosen for cross-family diversity. Ask the user to confirm or paste any additional slugs they want available. 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. Both mean the role runs on the parent session's model, which the Agent call expresses by omitting model.

2. Load current state

The default role-to-model mapping is the rule shape shown in the Write the override sheet step below. If the current runtime's sheet already exists, read it and treat its values as the current choices. Otherwise start from those defaults. A line whose role is not in that shape, such as how critics, is from a retired role. Drop it. An older sheet may name full model IDs that start with claude-, which the Agent tool rejects. Replace each with its family name, the word after claude-.

3. Map and confirm

Show every role with its current model, marking any real slug not in the detected set as needing a choice. Also list each line step 2 dropped or rewrote. Ask whether to accept as-is or change specific roles, offering the detected models plus inherit-parent and 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.

Then ask for the default reasoning effort, the default effort line. It is session, which keeps the parent session's effort, or one of the levels in Models. Start from the default listed there. Every role value without a suffix runs at it. Then ask whether any role should run at another level. On Claude Code a role value may carry one after its slug, as in <slug> @xhigh; panel entries take their own, as in <slug> @xhigh, <slug> @max. Each level dispatches through the plugin's effort agent of that level, so the choice holds without changing the session. Leave the suffix off for the default effort.

4. Choose whether the session hook routes tasks

On Claude Code and Codex, the plugin's SessionStart hook injects the poteto-mode mandate on startup, resume, clear, and compact. Codex asks the user to trust plugin hooks through /hooks before running them. Ask whether to keep the hook. The default is on. The answer is the session hook line in the current runtime's sheet: on or off. With no sheet or no line, the hook injects. The line is inert on other runtimes.

5. Validate

Every real slug written must be in the detected set. inherit-parent and auto always pass. Validate the slug without any @<level> suffix, and the level against the effort levels in Models. The default effort value is one of those levels or session. On Codex, the levels are the reasoning_effort values your Codex models accept instead. If a chosen real slug or level is not available, stop and ask again.

6. Write the override sheet

Write the current runtime's sheet with the shape below. Overwrite the whole file so re-runs stay idempotent.

markdown
# pstack model configuration

Per-role model overrides for pstack skills. Each pstack SKILL.md names its defaults in a Models section; the values here override those defaults. Delete a line to fall back to the skill default. A value of `inherit-parent` or `auto` runs that role on the parent session's model (the `Agent` call omits `model`); an alias entry in a panel list still counts toward that panel's fan-out. A model may carry a reasoning effort, as in `opus @xhigh` (levels: low, medium, high, xhigh, max); the role then runs through the pstack effort agent of that level, each entry of a panel list on its own. `default effort` sets the level for a value without one; `session` keeps the parent session's effort. `session hook: off` stops the Claude Code or Codex SessionStart hook from injecting the poteto-mode mandate; any other value, or no line, leaves it on.

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

default effort: session
session hook: on

7. Wire it in

On Claude Code, if <config>/CLAUDE.md does not already include <config>/pstack-models.md, append an @ line naming the sheet's resolved path, such as @~/.claude/pstack-models.md, so the model rows load on every session. If the user prefers project scope, add the include to the project's CLAUDE.md instead.

On Codex, paste the model rows and the default effort line into <codex-home>/AGENTS.md; Codex has no @ include. Do not paste the session hook line there: the plugin hook reads it directly from <codex-home>/pstack-models.md.

8. Confirm

Tell the user where the override was written, how its model rows load, and whether the plugin hook is on. Re-running this skill updates the override sheet.

Other runtimes

The role lines are the same everywhere. What differs is the sheet path, how the runtime loads it, and how you list models. Detect models with the runtime's own tool and never write a slug you have not seen listed. A runtime whose subagent call has no model parameter still gets the sheet, as the record of the user's choice, and applies it where it can. The session hook line applies to the Claude Code and Codex plugins.

RuntimeSheetLoadList modelsStatus
Claude Code<config>/pstack-models.md@<config>/pstack-models.md in <config>/CLAUDE.mdthe Agent tool's model parameterverified live
Codex<codex-home>/pstack-models.mdmodel rows: paste into <codex-home>/AGENTS.md; hook setting: read by the pluginyour configured Codex models, see codex-tools.mdhook contract tested; discovery verified
Pipstack-models.md in the Pi agent directory, $PI_CODING_AGENT_DIR or ~/.pi/agentread by the pstack Pi extension, model rows and hook setting both; no include linepi --list-models, see pi-tools.md and its setup-pstack noteextension contract tested offline; live results in the repository's docs/pi-equivalence.md
opencode~/.config/opencode/pstack-models.mdadd the path to the instructions array in opencode.jsonthe models slash command in the sessionfrom published docs, no live session
Gemini CLI~/.gemini/pstack-models.md@~/.gemini/pstack-models.md in ~/.gemini/GEMINI.mdthe model slash command in the sessionfrom published docs, no live session
Prime Agentno documented sheet path; Prime's configuration chooses modelsno live session

Models

Stamped from plugins/pstack/models.json (edit there, rerun tools/generate.mjs).

  • Available Claude models: opus, fable, sonnet, haiku
  • Default panel: opus, fable, sonnet
  • Reasoning effort levels: low, medium, high, xhigh, max
  • Default reasoning effort: session
  • Single-role default: opus

Frequently asked questions

What does the Setup Pstack AI skill do?

Configure which models pstack uses per role. Detects available models and writes the current runtime's override sheet. Use for /setup-pstack, "configure pstack models", changing pstack's model choices, or turning the SessionStart hook on or off.

Why use Setup Pstack on TypingMind?

Because you install it once and use it with any model. Setup Pstack is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Setup Pstack in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/michael-denyer/pstack-claude/tree/main/plugins/pstack/skills/setup-pstack. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Setup Pstack?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Setup Pstack?

As many as you like. As long as a model supports skills, you can use Setup Pstack with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Setup Pstack AI skill free?

Yes. It is published on GitHub by michael-denyer under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇