pstack for Claude Code 🤖 Agent Open source
Port of Cursor's pstack playbooks for verified bug fixes and features
- GitHub stars
- 759
- Stars this week
- +168
- Forks
- 97
- Licence
- MIT
- Last push
- 2026-10-02
- Maintainer
- michael-denyer
/plugin marketplace add michael-denyer/pstack-claudeThird-party subagents & agents run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
About pstack for Claude Code
What it does
pstack-claude, by Michael Denyer, ports Lauren Tan's pstack to agents other than Cursor. pstack is an opinionated stack of skills for getting concise, verified work out of a coding agent. You tell its poteto-mode entry point your goal, and it picks a playbook: for a bug it reproduces the failure, investigates, delegates the fix, and reruns the failing case so you get both failing and passing evidence. If a fix crosses a function boundary it brings in an architecture step first.
What is inside
The plugin bundles the poteto-mode router, playbooks for planning, features, refactoring, performance, investigations, prototypes, PR maintenance and shipping, and supporting skills such as how, why, architect, interrogate and unslop. Some Cursor primitives are translated into equivalents for each harness, and some skills from Cursor's team kit are included under their own licence. A setup-pstack command changes model defaults or turns automatic routing off. On Claude Code and Codex the plugin installs a routing hook; Codex asks you to trust it through /hooks first.
Works with
The README gives plugin installs for Claude Code and Codex, and points to shared skills-only instructions for OpenCode, Gemini CLI and Prime Agent. Cursor users should use the original pstack instead.
How to install
/plugin marketplace add michael-denyer/pstack-claude
/plugin install pstack@pstack-claude
codex plugin marketplace add michael-denyer/pstack-claude
codex plugin add pstack@pstack-claude
Maintenance and safety
MIT licensed with the original authors credited in separate licence and notice files, and pushed recently. It has a security policy and contributing guide. The weakness is that it is a port: its value depends on how closely it tracks upstream pstack, and the README itself is brief, pushing most detail into a reference doc.
Who should use it
Claude Code or Codex users who liked pstack's disciplined bug and feature playbooks in Cursor and want the same behaviour elsewhere. If you already use a different workflow pack, compare before stacking them.
Pros
- Playbooks demand reproduction and passing evidence for fixes
- Plugin installs for Claude Code and Codex, skills-only for others
Cons
- A port of an existing Cursor plugin, so it depends on tracking upstream
- Brief README with most detail in a reference doc
Similar subagents & agents
All agent workflows & frameworks →Spec Kit 🤖 AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master 🤖 AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent 🤖 AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec 🤖 AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net 🤖 AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
BMAD Method 🤖 AgentFree
Agile AI-driven development with analyst, PM, architect, developer and UX agents