Skip to content
  1. Skills at a glance
  2. Start here: meet these three
  3. /pstack:setup-pstack

/pstack:setup-pstack

Call when needed

In one linePicks your models: it checks what you can use, asks your budget, and writes one config all skills share.

When to use
Run it right after installing. Run it again to switch models or save money.
Say it like this
/pstack:setup-pstack

Just asking vs. using it

The same request, typed plainly or with /pstack:setup-pstack. Here's what changes.

Just askingWith /pstack:setup-pstack
Writes a model name you can't actually use.Lists the models it can call this session and writes only those.
Writes the settings without asking you.Asks for one of four budgets, shows each role's model, and waits for your OK.
Leaves retired role lines in the file on a re-run.Drops retired roles and overwrites the whole file, so re-runs give the same result.

What the document says

9 sections, about 1050 words, 5 min to read. Click a section to read it.

OpeningIt lists where the settings file goes in Cursor, Claude Code and every other harness.

  1. 1StepsEight steps, from finding usable models to writing the file, ending with two optional offers.
  2. 2Detect available modelsLists the model names it can pass to helpers this session. If it finds none, it asks you to paste yours.
  3. 3Load current stateReads an existing file's budget and role choices as the starting point, and drops lines for retired roles.
  4. 4Budget, map, and confirmAsks for unlimited, large, medium or small, sets each model's effort to match, then shows the roles to accept or change.
  5. 5ValidateChecks every chosen model is in the detected list. If one isn't, it stops and asks again.
  6. 6Write the ruleWrites a budget line and one line per role over the whole file. The Cursor version adds alwaysApply: true.
  7. 7ConfirmTells you which file it wrote. In Cursor and Claude Code, new sessions pick it up.
  8. 8Offer a verification skill (optional)If the project has no way to drive the app, it offers once to generate one with /pstack:create-verification-skill.
  9. 9Offer a formal verification skill (optional)If there is no formal verification skill, it offers once to run /pstack:create-formal-verification-skill. On no, it moves on.

See the wording worth borrowingRead the full text

Wording worth borrowing

A few sentences from the original: what each one makes the AI do, why it works, and how you can borrow it.

  1. Write only what's confirmed

    Never write a real slug you have not confirmed is available.

    Makes the AI
    Only models you can actually use end up in the settings, never a made-up name that breaks a run.
    Why it works
    "Never" tied to a concrete step, confirming, is much harder to slip past than "be accurate".
    Borrow it
    When you ask for a price list: "List only prices you confirmed on the official site; mark the rest 'unconfirmed'."
  2. Spell out the exact options

    Offer these four options with these exact labels

    Makes the AI
    It asks about budget with the same four options every time, worded the same way.
    Why it works
    Writing the options into the prompt and asking for them verbatim stops the AI from rewording, adding or dropping one.
    Borrow it
    For a survey: "Ask about satisfaction with exactly these options: 'Satisfied', 'OK', 'Not satisfied'."
  3. Follow a rule with an example

    So unlimited turns claude-opus-5-5-xhigh into claude-opus-5-5-max.

    Makes the AI
    It swaps models for your budget correctly, such as turning xhigh into max for the biggest budget.
    Why it works
    An abstract conversion rule is easy to misread; a worked example right after lets the AI check its own answer.
    Borrow it
    Give an example with the rule: "Round amounts to the nearest hundred, so 1,260 becomes 1,300."
  4. Ask once, drop it on no

    On no, move on without pushing.

    Makes the AI
    It offers a verification skill once, and drops it if you say no.
    Why it works
    Saying how many times to ask and what to do on a no keeps the AI from pitching extras again and again.
    Borrow it
    When the AI writes for you: "You may ask once at the end whether I want images; if I say no, drop it."

Full text

The SKILL.md the AI reads, as written.

descriptionConfigure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /pstack:setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.

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 how critics, is from a retired role. Drop it.

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 four 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.

  • unlimited — max reasoning
  • 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). unlimited, large, medium, and small set the effort token of every real slug, panel entries included, to max, xhigh, high, or medium. The effort token is the last token, or the one before a trailing fast, on the ladder max > xhigh > high > medium > low. 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 unlimited turns claude-opus-5-5-xhigh into claude-opus-5-5-max. Grok slugs top out at xhigh, so under unlimited the fallback puts Grok at xhigh and keeps grok-4.7-xhigh-fast as it is. large keeps both defaults. small turns them into claude-opus-5-5-medium and grok-4.7-medium-fast.

(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 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, 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 runs one judge. It tries only values from a family other than the parent's, in list order, so order it by preference. 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. 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 a # budget line with the chosen label and its target effort, 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`). Alias entries in a panel list still count toward its fan-out.
### budget: large (xhigh)
feature, refactoring: grok-4.7-xhigh-fast
bug-fix: grok-4.7-xhigh-fast
perf-issue: grok-4.7-xhigh-fast
hillclimb: grok-4.7-xhigh-fast
judgment and prose: claude-opus-5-5-xhigh
hardest tasks: claude-opus-5-5-xhigh
how explorer: grok-4.7-xhigh-fast
how explainer: claude-opus-5-5-xhigh
why investigators: grok-4.7-xhigh-fast
why synthesizer: claude-opus-5-5-xhigh
reflect tooling: grok-4.7-xhigh-fast
reflect judgment, divergent, synthesizer: claude-opus-5-5-xhigh
arena runners: claude-opus-5-5-xhigh, grok-4.7-xhigh-fast
arena cross-judge pool: claude-opus-5-5-xhigh, grok-4.7-xhigh-fast
swarm workers: grok-4.7-xhigh-fast
architect runners: claude-opus-5-5-xhigh, grok-4.7-xhigh-fast
interrogate reviewers: claude-opus-5-5-xhigh, grok-4.7-xhigh-fast
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 /pstack:create-verification-skill." On yes, invoke /pstack: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 /pstack:create-formal-verification-skill." On yes, invoke /pstack:create-formal-verification-skill (resolves wherever pstack is installed: workspace, user, or plugin). On no, move on without pushing.

Original by Lauren Tan (poteto), MIT license. Checked against the pstack mirror at 97de40d. View on GitHub

An unofficial beginner's guide to pstack, not its official docs. pstack is made by poteto; the official repo is the source of truth for commands and behavior. The original guide source is on GitHub.

Hosted by airali. Adapted from Xiaoxiaodong's MIT-licensed guide.