pstack
backnotprop · backnotprop/pstack
A collection of modular skills for AI agents to improve engineering rigor, testing, and architectural planning.
Use pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering
Preview
What you can do with it
- Install TDD and TypeScript best practices skills to improve code reliability.
- Use the 'architect' skill to let Claude plan complex system designs.
- Apply 'unslop' to make agent-generated content more concise and professional.
Safety check
No risky patterns found in the files we scanned.
Automated scan of the repo files. Always review code you run.
From the README
pstack — standalone mirror
Mirror of cursor/plugins/pstack — kept in sync for standalone use.
Poteto's Bro Skill was created by me, backnotprop/bro
Install
pstack is a folder of plain Agent Skills (skills/<name>/SKILL.md). You don't need Cursor. The skills CLI installs them into Claude Code, Codex, Pi, Cursor, OpenCode, and other agents:
npx skills add backnotprop/pstack
The CLI shows every skill in a list you can search. Select the skills you want, then select your agents.
Skills
Cursor's original README is further down this page.
These skills don't call other pstack skills, so each one works alone:
unslop, bro, how, tdd, typescript-best-practices, arena, swarm, interrogate, reflect, show-me-your-work, figure-it-out, automate-me, correct, benchmark-checklist, in-your-own-words, sharpen, statechart
Some skills call other skills. Install these together:
| Skill | Also install |
|---|---|
teach | how, why |
why | how |
technical-writing | unslop |
architect | arena, how |
blast-radius | arena, how, why, unslop |
create-verification-skill | maintain-verification-skill |
create-formal-verification-skill | maintain-formal-verification-skill, statechart |
ketchup | bro |
ketchup-video | ketchup, bro |
poteto-mode | all principle-* skills and most of the other skills |
poteto-help | the skills you want help with |
Skills that spawn subagents point to the Subagents section of poteto-mode to pick each subagent's effort. Without poteto-mode, they use the default effort.
What this mirror changes
Many skills were Cursor-specific. They've been rewritten to work in any harness.
The mirror also carries two community fixes that aren't upstream yet:
no-commentskeeps a comment about an outside rule (a dependency, platform, or protocol) when it can't check the rule, and marks it for review instead of deleting it. A rejected review no longer stops the whole run. (#14)- The orchestrate scripts take
--basefor PR stacks that don't start atmain. (#15)
pstack
i'm poteto. i'm not a president or ceo, but i've worked with millions of lines of code at Meta, Netflix, and Cursor. i'm also on the react core team where i help build and maintain react compiler.
there's a growing sense that ai writes too much slop code. i agree. i don't want to ship like a team of twenty slop artists. throughput without quality is not a goal i aspire to. if you want to go fast, go deep first.
pstack is my answer. these are the same skills i use every day to ship high quality code at Cursor. this turns cursor into a real engineering team. the goal is not to maximize loc, in fact it's the opposite. pstack helps you write less, but higher quality code.
pstack gives you fearless parallelism. when you can go deep on one agent and trust it to write good, verifiable code, you can truly parallelize with confidence. start multiple agents up with poteto-mode and trust that they'll apply rigorous engineering principles to their work.
cursor gives you the best of all worlds. every frontier model has its strengths and weaknesses. use any model with pstack. in fact, many of my skills use multi-model workflows to take advantage of each model's unique strengths.
fork it. improve it. make it yours. PRs are welcome!
install
/add-plugin pstack
in claude code:
/plugin marketplace add cursor/plugins
/plugin install pstack@cursor-plugins
claude code leaves auto-update off for third-party marketplaces, so pstack stays on the version you installed. to turn it on, run /plugin, open the marketplaces tab, select cursor-plugins, and choose enable auto-update. to update once by hand, run claude plugin update pstack@cursor-plugins.
claude code prefixes plugin commands and agents, so /poteto-mode is /pstack:poteto-mode. the claude code adapter maps every other cursor name. in claude code, /pstack:setup-pstack writes your model choices to ~/.claude/rules/pstack-models.md, and a step that needs a cursor-only feature, such as bugbot or automations, is skipped with a one-line note.
claude code installs a generated copy of pstack, including this readme and the guide, from harness/pstack/ at the repository root. after you change pstack, run node scripts/generate-pstack-harness-trees.mjs from the repository root and commit the result. ci fails while the generated copy is out of date.
get started
two steps:
- run
/setup-pstack, pick a reasoning budget, and choose which models you want. - use
/poteto-modewhenever you're doing anything that requires rigor.
new here? the pstack guide walks you through a first real task, from setup and prompting through verification and overnight runs. stuck, or unsure which skill fits? ask /poteto-help.
that's it. the other skills are situational, and the mode skill uses them for you as needed. out of the box the mode splits work by model strength: code delegates (feature, refactoring, bug fix, perf, hillclimb) go to grok, while the hardest changes, prose, and judgment go to opus 5.5. the default panel is opus 5.5 / grok. /setup-pstack changes any of it.
usage
use /poteto-mode at the start of a task. it reads your request, picks from a set of playbooks, and runs the other skills as the steps need them.
pick `/poteto-