Back to directory

pstack

pstack ports Lauren Tan's opinionated Cursor skill stack, poteto-mode, to Claude Code, Codex and other agent harnesses, routing a stated goal to the right workflow to keep changes concise, simple and independently verified.

pstack

pstack is a faithful port of an existing Cursor skill stack, poteto-mode, to Claude Code, Codex and other agent harnesses. Given a goal, it selects the matching workflow: for a bug it reproduces the failure, investigates how and why it happens, delegates the fix, and reruns the failing case, pulling in a separate architect role first if the fix crosses a function boundary. Other playbooks cover planning, features, refactoring, performance issues, investigations, prototypes, pull-request maintenance, shipping and longer projects.

A setup command lets a user change the model used for each role, set a reasoning-effort level per role, or turn its automatic routing off; Claude Code dispatches roles through the plugin's own effort- and agent-specific subagents, while Codex requires explicitly trusting the routing hook.

It installs as a plugin for Claude Code or Codex and is written in TypeScript, released under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.