pstack-setup

Configures how your Pstack agent works, including roles, effort limits and where it finds information.

Installation
Run `npx skills add "https://github.com/christofferbergj/agent-skills" --skill "pstack-setup"` to install this skill, then follow its SKILL.md instructions for my next request.

Paste this into Claude Code, Cursor, or any agent that can run commands.

SKILL.mdShow the author's original SKILL.md
---
name: pstack-setup
description: "Use when configuring Pstack model roles, effort budgets, optional review providers, or source locations."
---

# Set up Pstack

1. Inspect installed skills, the current host's exposed model choices, optional other CLI availability, and existing configuration. Honor the host's schema and current defaults; `auto` and `inherit-parent` omit overrides. If no model choices can be detected, ask the user which models they can use. Complete when capabilities and unavailable integrations are explicit.
2. Load `~/.config/pstack/config.json`, or the explicit `PSTACK_CONFIG` path, if present. Keep Codex and Claude Code role settings in separate sections of this one personal file. Read repository overrides only when explicitly configured. Drop every entry /swarm's `scripts/target.py --help` doesn't list, except the schema version and source location step 4 writes, such as a retired role, `codexUsage.fastWhileLeft`, or a review timeout, and list them in the summary. Complete when current choices are known without altering global host settings.
3. Ask only for missing preferences: task budget, model roles the user wants to override, such as a cheaper explorer or a stronger code delegate, optional cross-vendor reviews, the counterpart reviewer's provider instance, model, full and delta review effort, and Codex speed; the Computer Use delegate's model, routine and hard effort, and speed; the hours of lead on even pace Codex delegates may take before leaving fast mode, and the percent of Codex usage left below which they skip Codex; and the source repository for learning-driven changes. /swarm's `scripts/target.py --help` shows the keys that hold each. Offer the default `target.py` prints for each role. Map effort through actual supported options rather than editing model-slug strings. Complete when every explicit override is available and within the user's choices.
4. Write the agreed personal configuration atomically outside installed instructions. Include a schema version, host role sections, and source location. Keep credentials in the providers' existing stores, not this file. Complete when the file can be read back and matches the agreed choices.
5. Summarize the location, overrides, dropped entries, prerequisite gaps, and how to return a role to /swarm's default. Offer /create-verification-skill once when the repository lacks a way to prove behavior. When consequential properties need checks beyond ordinary test coverage and no formal verification skill exists, offer the user the explicit /create-formal-verification-skill entrypoint once. On a no, continue without pressing. Complete when setup status is verifiable without claiming that installation activated the mode.

Ships with 3 supporting files:

  • agents/openai.yaml
  • LICENSE
  • UPSTREAM.md

Mirrored from the author's public source. Install counts from the open skills registry.

The systems behind these skills get built for partners every week.

Partner with us