Skip to content
Back to skills

Pstack Discipline

ASecurity

Enforce high-rigor engineering discipline from the pstack / poteto framework: "Prove It Works", "Fix Root Causes", "Test Behavior, Not Implementation", and "Subtract Before You Add" during orchestration and planning.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added November 11, 2026
ai-agentsgorefactoring

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add bepaldes/heimdall-agent --skill pstack-discipline --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pstack Discipline?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Pstack Discipline
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bepaldes-pstack-discipline/badge)](https://www.skillsdirectory.com/skills/bepaldes-pstack-discipline)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: pstack-discipline
description: >
  Enforce high-rigor engineering discipline from the pstack / poteto framework:
  "Prove It Works", "Fix Root Causes", "Test Behavior, Not Implementation",
  and "Subtract Before You Add" during orchestration and planning.
---

# PStack Engineering Discipline

A distilled set of non-negotiable operational principles originated by Lauren Tan (@poteto) in the `pstack` framework, designed to prevent AI agents from generating unverified, shallow, or symptom-masking code.

---

## The 5 Core Principles

### 1. Prove It Works
* Never assume, extrapolate, or assert that a system functions without empirical proof.
* Run terminating, non-interactive verification commands (unit tests, build checks, Playwright assertions) that actively observe behavior.
* A task is incomplete until the proof is captured.

### 2. Fix Root Causes
* Never apply defensive guards that merely hide runtime exceptions or symptoms.
* Trace failures back to the originating boundary or state inconsistency.
* A patch that masks a crash without resolving why invalid state reached that point is a rejected regression.

### 3. Test Behavior, Not Implementation
* Tests must exercise the system through its public boundaries exactly as a consumer or user does.
* Avoid brittle internal mocks and spy assertions that break during internal refactorings.
* If a test suite would still pass when internal functions return dummy values or no-ops, discard the test suite.

### 4. Subtract Before You Add
* Before adding new layers, abstractions, or dependencies, evaluate what can be removed or simplified.
* Reduce reader cognitive load, shrink state scope, and eliminate dead branches first.
* The cleanest feature is one that reuses existing architecture without expanding complexity.

### 5. Sequence Work into Verifiable Units
* Break complex tasks into small, self-contained, verifiable increments.
* Complete and verify unit $N$ before beginning unit $N+1$.
* Prevent speculative parallel diffs that fail together at integration time.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.