agentleFS
christofferbergjchristofferbergj/agent-skills/skills/agents/pstack-setup/SKILL.md

pstack-setup

Skill1 starsChanged 22 days agoMITView on GitHub

Use when configuring Pstack model roles, effort budgets, optional review providers, or source locations.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the agreed personal configuration atomically outside installed instructions.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 entries for roles that no longer exist, and codexUsage keys that /swarm's scripts/target.py --help no longer lists, such as fastWhileLeft, 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, optional review timeout, 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.