<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j" -->

---
title: A deep dive into pstack | daily.dev
description: pstack is a Cursor plugin created by Lauren Tan (poteto) that turns AI coding agents into a structured engineering workflow with 23 workflow skills, 21...
canonical: https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: A deep dive into pstack | daily.dev
og:description: pstack is a Cursor plugin created by Lauren Tan (poteto) that turns AI coding agents into a structured engineering workflow with 23 workflow skills, 21...
og:url: https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j
og:image: https://api.daily.dev/og/posts/EVqBNto9J.png
og:image:alt: A deep dive into pstack
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# A deep dive into pstack

**[Flavio Copes](https://daily.dev/sources/flaviocopes)** · 22 min read · 4 upvotes · 0 comments

## Summary

pstack is a Cursor plugin created by Lauren Tan (poteto) that turns AI coding agents into a structured engineering workflow with 23 workflow skills, 21 engineering principles, 22 task playbooks, and 2 specialized subagents. The central command /poteto-mode routes a request to the right playbook (bug fix, feature, refactor, investigation, perf), copies it verbatim into a task list, and enforces runtime verification rather than accepting a passing build as proof. Other skills include /how and /why for tracing system behavior and history, /architect and /arena for design exploration, /swarm for parallel coverage work, /interrogate for multi-model code review, and /automate-me and /reflect for personalizing and refining the workflow over time. The piece walks through installation, architecture, playbook categories, verification skill generation, overnight autonomous runs, and common mistakes, plus the author's own take on when pstack is worth the overhead versus a lighter workflow like fstack.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://flaviocopes.com/pstack>

## Questions this post answers

### What is pstack and how does it work with Cursor?

pstack is a Cursor plugin created by Lauren Tan (poteto) that turns short requests into complete engineering workflows instead of raw code generation. It contains 23 workflow skills, 21 engineering principles, 22 task playbooks, 2 specialized subagents, and an optional automation pack. Most usage is through a single command, /poteto-mode, which selects a matching playbook, builds a task list, delegates to different models, and demands verification evidence before reporting success.

_Developers weighing structured AI coding workflows can track tool deep dives like this one on daily.dev._

### What is the difference between the /arena and /swarm commands in pstack?

Arena runs the same task across several models and synthesizes one result from the competing attempts, useful for comparing designs when a decision is expensive. Swarm instead splits a task into independent slices or race arms across multiple workers and returns one combined report, useful for coverage rather than comparison. Using arena when coverage is needed, or swarm when comparison is needed, is called out as a common mistake.

_Teams deciding between multi-agent review versus parallel task splitting can follow workflow comparisons like this on daily.dev._

### How does pstack verify that a change actually works instead of just passing a build?

pstack rejects a passing build as sufficient proof and instead matches verification to what changed: a command-line change runs the real command, a UI change walks the changed flow, a migration replays real input, a performance change compares traces, and a storage change reads the value back. When a repository lacks a reliable verification method, the /create-verification-skill command generates a project-local verify script covering launch, health check, driving behavior, evidence capture, and cleanup.

_Engineers building trust in AI-generated changes can follow verification practice guides like this on daily.dev._

## Similar posts on daily.dev

- [I launched fstack](https://daily.dev/posts/i-launched-fstack-sghc6fuby) · Flavio Copes · 0 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#prompt-engineering](https://daily.dev/tags/prompt-engineering), [#code-review](https://daily.dev/tags/code-review)

[View this post on daily.dev](https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"A deep dive into pstack","url":"https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j"},"datePublished":"2026-08-21T09:20:19.837Z","dateModified":"2026-09-13T20:46:38.276Z","description":"pstack is a Cursor plugin created by Lauren Tan (poteto) that turns AI coding agents into a structured engineering workflow with 23 workflow skills, 21...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a8d3fe370e187c773dd623717713edc2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a8d3fe370e187c773dd623717713edc2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Flavio Copes","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Flavio Copes","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/1f2dbd275797411bbd37bfdaaf0951a9","url":"https://daily.dev/sources/flaviocopes"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":4},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,prompt-engineering,code-review","timeRequired":"PT22M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Flavio Copes","item":"https://daily.dev/sources/flaviocopes"},{"@type":"ListItem","position":3,"name":"A deep dive into pstack"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/a-deep-dive-into-pstack-evqbnto9j#faq","mainEntity":[{"@type":"Question","name":"What is pstack and how does it work with Cursor?","acceptedAnswer":{"@type":"Answer","text":"pstack is a Cursor plugin created by Lauren Tan (poteto) that turns short requests into complete engineering workflows instead of raw code generation. It contains 23 workflow skills, 21 engineering principles, 22 task playbooks, 2 specialized subagents, and an optional automation pack. Most usage is through a single command, /poteto-mode, which selects a matching playbook, builds a task list, delegates to different models, and demands verification evidence before reporting success. Developers weighing structured AI coding workflows can track tool deep dives like this one on daily.dev."}},{"@type":"Question","name":"What is the difference between the /arena and /swarm commands in pstack?","acceptedAnswer":{"@type":"Answer","text":"Arena runs the same task across several models and synthesizes one result from the competing attempts, useful for comparing designs when a decision is expensive. Swarm instead splits a task into independent slices or race arms across multiple workers and returns one combined report, useful for coverage rather than comparison. Using arena when coverage is needed, or swarm when comparison is needed, is called out as a common mistake. Teams deciding between multi-agent review versus parallel task splitting can follow workflow comparisons like this on daily.dev."}},{"@type":"Question","name":"How does pstack verify that a change actually works instead of just passing a build?","acceptedAnswer":{"@type":"Answer","text":"pstack rejects a passing build as sufficient proof and instead matches verification to what changed: a command-line change runs the real command, a UI change walks the changed flow, a migration replays real input, a performance change compares traces, and a storage change reads the value back. When a repository lacks a reliable verification method, the /create-verification-skill command generates a project-local verify script covering launch, health check, driving behavior, evidence capture, and cleanup. Engineers building trust in AI-generated changes can follow verification practice guides like this on daily.dev."}}]}
```

