backnotprop/pstack

setup-pstack

Configure which models pstack uses per role and at what reasoning budget.

Ver código-fonte

Como usar

  1. Copie o comando e verifique o pacote antes de instalar no seu ambiente de agente.
  2. Consulte no original as ferramentas, credenciais e ambientes necessários.
  3. Descreva os dados de entrada e a entrega esperada; confira a saída com as fontes.
npx skills add https://github.com/backnotprop/pstack --skill setup-pstack

Antes de começar

  • A instalação não inclui assinatura de modelo, franquia API ou acesso aos seus arquivos.
  • Estrelas e instalações indicam atividade, não um teste independente de qualidade ou segurança.
Documento original do Skill

Renderizado do repositório de origem, preservando títulos, exemplos, código, tabelas, links e imagens.

Setup pstack

Write pstack's model settings, one model per role:

  • Cursor: ~/.cursor/rules/pstack-models.mdc, an always-applied rule.
  • Claude Code: ~/.claude/rules/pstack-models.md. Claude Code loads every file in ~/.claude/rules/ into each new session.
  • Every other harness (Codex, Pi, OpenCode, and others): ~/.agents/pstack-models.md. These harnesses don't load it on their own, so pstack skills read this file when they pick a model.

"The settings file" below means the file for your harness. In Claude Code, if that file is missing, read ~/.agents/pstack-models.md instead, where older versions of this skill wrote it.

Steps

1. Detect available models

Enumerate the model slugs you can pass to a subagent in this session (Cursor Task, Claude Code Agent, OpenCode task, Codex spawn_agent). That is the dependable source. If your harness also has a command that lists the user's models, prefer it for completeness (for example opencode models or pi --list-models). 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 the settings file already exists, read it and treat its # budget line and its role values as the current choices. Otherwise start from those defaults. A line whose role is not in step 5, such as hardest tasks, architect runners, reflect tooling, or why investigators, is from a retired role. Drop it.

A settings file without the # defaults: 3 line comes from an older setup. That setup wrote a line for every role, so some of its values are old defaults, not choices. Before step 3, replace these values:

  • An arena cross-judge pool list of exactly one claude-fable-* entry, one claude-opus-* entry, and one gemini-* entry, in any order, takes the role's step 5 list. Fable and Opus are one vendor, so the Fable entry could judge only where the Opus entry also could.
  • A # budget: unlimited line becomes large, because no role runs above xhigh.
  • If the settings file has no # defaults: 2 line either, an old slug is one that matches grok-*. An old slug in feature, refactoring, bug-fix, perf-issue, hillclimb, or swarm workers takes the role's step 5 default. In a panel role (arena runners, arena cross-judge pool, interrogate reviewers), a list of exactly one claude-opus-* entry and one old slug, in either order, takes the role's step 5 list. In any other list, each old slug becomes claude-opus-5-5-high-fast.

Every other value is the user's choice and stays, including an old slug in any other role and every inherit-parent or auto value. Tell the user which values you replaced.

3. Budget, map, and confirm

(a) Ask for a budget. Prefer your structured-question tool (AskQuestion in Cursor, AskUserQuestion in Claude Code, question in OpenCode) over free text. Offer these three options with these exact labels, and name the current budget when the rule records one. With no rule, say that large matches the skill defaults.

  • large — xhigh reasoning
  • medium — high reasoning
  • small — medium reasoning

(b) Apply it. Build the working table from the skill defaults, and on a re-run keep any role you changed by family, list, or alias (inherit-parent, auto). Families are the ones Phase A of the arena skill defines, so Fable is its own family. Each role has a target effort, which is its default's effort moved by the budget. large keeps it, medium lowers it one step, and small lowers it two steps, on the ladder xhigh > high > medium > low. No role runs above xhigh, and a target at the bottom of the ladder stays there. Most defaults are at xhigh, and each budget label names where those land. Set the effort token of every real slug in the role, panel entries included, to the role's target. The effort token is the last token, or the one before a trailing fast. If the result is not a detected slug, use the same family's detected slug with the highest effort at or below the target, else mark the role as needing a choice. inherit-parent and auto do not change. So medium turns claude-opus-5-5-xhigh-fast into claude-opus-5-5-high-fast and claude-opus-5-5-high-fast into claude-opus-5-5-medium-fast, and small turns them into claude-opus-5-5-medium-fast and claude-opus-5-5-low-fast. Opus 5.5 always runs its -fast slug, so every Opus 5.5 value ends in -fast. Fable 5.2 and Gemini have no fast slug, so never write one. Gemini tops out at high, so a Gemini entry runs at high when its role's target is xhigh.

(c) Show the roles and confirm. Show every role with its model, marking any real slug not in the detected set as needing a choice. Also list each line step 2 dropped. Ask whether to accept as-is or change specific roles, offering the detected models at xhigh or below 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 your structured-question tool over free text. For panel roles (arena 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 runs one judge. It tries only values from a vendor other than the parent's, in list order, so order it by preference. Fable and the other Claude models are one vendor. An inherit-parent or auto value never judges. 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 and at xhigh or below. inherit-parent and auto always pass. If a chosen real slug is not available, stop and ask again.

5. Write the rule

Write the settings file with the # defaults: 3 line, a # budget line with the chosen label and the effort that label names, and one line per role, using the same labels poteto-mode uses. In Cursor, include the frontmatter below with alwaysApply: true. In other harnesses, write the settings file without the frontmatter (start at the first # line). Overwrite the whole file so re-runs stay idempotent. Shape:

---
description: pstack per-role model choices (overrides skill defaults)
alwaysApply: true
---
# 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 the subagent `model` and spawn a general-purpose subagent). Alias entries in a panel list still count toward its fan-out.
# defaults: 3
# budget: large (xhigh)
feature, refactoring: claude-opus-5-5-xhigh-fast
bug-fix: claude-opus-5-5-xhigh-fast
perf-issue: claude-opus-5-5-xhigh-fast
hillclimb: claude-opus-5-5-xhigh-fast
judgment and prose: claude-opus-5-5-xhigh-fast
arena runners: claude-fable-5-2-high, claude-opus-5-5-high-fast, gemini-4-carbon-high
arena cross-judge pool: claude-opus-5-5-high-fast, gemini-4-carbon-high
swarm workers: claude-opus-5-5-high-fast
interrogate reviewers: claude-fable-5-2-high, claude-opus-5-5-high-fast, gemini-4-carbon-high

6. Confirm

Tell the user which file was written. In Cursor and Claude Code, it applies to new sessions. In other harnesses, pstack skills read ~/.agents/pstack-models.md when they pick a model. 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.

8. Offer a formal verification skill (optional)

Check whether the project already has a formal verification skill (a project skill that runs a model checker, a proof, or another verifier against the code). If not, offer once: "want a formal verification skill, so agents can prove a key property of your code holds in every case in scope, not only the cases tests reach? I can generate one with /create-formal-verification-skill." On yes, invoke /create-formal-verification-skill (resolves wherever pstack is installed: workspace, user, or plugin). On no, move on without pushing.

do mesmo repositório

Mais Skills

Todos os Skills