Setup pstack

Write ~/.codex/pstack-models.md, a plain file that sets pstack's model per role. The pstack skills read it; Codex does not load it on its own.

Steps

1. Detect available models

Enumerate the model slugs spawn_agent accepts in this session, from its own tool description. That is the dependable source. 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 ~/.codex/pstack-models.md 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 ask_user_question 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 gpt-6-astra into gpt-6-astra. Grok slugs top out at xhigh, so under unlimited the fallback puts Grok at xhigh and keeps gpt-6.1-sol as it is. large keeps both defaults. small turns them into gpt-6-astra and gpt-6.1-sol.

(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 ask_user_question 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.

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 ~/.codex/pstack-models.md with a # budget line naming the chosen label and its target effort, then one line per role, using the same labels poteto-mode uses. Overwrite the whole file so re-runs stay idempotent. Shape:

# 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 `model`). Alias entries in a panel list still count toward its fan-out.
# budget: large (xhigh)
feature, refactoring: gpt-6.1-sol
bug-fix: gpt-6.1-sol
perf-issue: gpt-6.1-sol
hillclimb: gpt-6.1-sol
judgment and prose: gpt-6-astra
hardest tasks: gpt-6-astra
how explorer: gpt-6.1-sol
how explainer: gpt-6-astra
why investigators: gpt-6.1-sol
why synthesizer: gpt-6-astra
reflect tooling: gpt-6.1-sol
reflect judgment, divergent, synthesizer: gpt-6-astra
arena runners: gpt-6-astra, gpt-6.1-sol
arena cross-judge pool: gpt-6-astra, gpt-6.1-sol
swarm workers: gpt-6.1-sol
architect runners: gpt-6-astra, gpt-6.1-sol
interrogate reviewers: gpt-6-astra, gpt-6.1-sol

6. Confirm

Tell the user the file was written and that the pstack skills read it from the next invocation. 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.