pstack

A rigorous engineering workflow for substantial coding tasks such as architecture changes, bug fixes, and refactors. It combines named principles with smaller, focused practices.

In plain words
What is it for?
Use it when a task needs careful design, verification, or review, especially for real bugs, refactors, and architecture decisions.
Why use it?
It helps developers make fewer unnecessary changes and provide evidence that the resulting code works.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/sma1lboy/rove/pstack
Any agent
npx skills add Sma1lboy/rove --skill pstack
Clone the repo
git clone --depth 1 https://github.com/Sma1lboy/rove

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00093 $0.01855
Opus 5 $0.00046 $0.00928
Sonnet 5 $0.00019 $0.00371
Haiku 4.5 $0.00009 $0.00186

Measured 2d ago against content hash 9a16f67f2692, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pstack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (skills/show-me-your-work/scripts/log.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/pstack/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pstack

Rigor over throughput. The point is to write less code, and to be able to prove the code you wrote works.

Original by Lauren Tan (poteto), MIT, from the Cursor plugin marketplace. This is a port: the principles and general skills are upstream's, the orchestration around them is rewritten for Claude Code and this repo. What changed and why: ATTRIBUTION.md.

How to use it

Read the principles below. Name the ones that shaped a decision, and say which choice each one changed. A citation with no decision behind it means you did not actually apply it — that is worse than not citing, because it reads as rigor without being rigor.

For any principle you actually apply, read its leaf skill in full (skills/principle-<name>/SKILL.md). The one-liners here are an index, not the content.

Principles

Core

  • Laziness Protocol (principle-laziness-protocol). Refactoring, sizing a diff, or tempted to add abstractions, layers, or signal threading. Bias to deletion and the smallest change that solves the problem.
  • Foundational Thinking (principle-foundational-thinking). Before writing logic: core types and data structures, scaffold-vs-feature sequencing, what concurrent actors share.
  • Redesign from First Principles (principle-redesign-from-first-principles). Integrating a new requirement into an existing design. Redesign as if it had been foundational from day one.
  • Subtract Before You Add (principle-subtract-before-you-add). Sequencing an addition, refactor, or rewrite. Remove dead weight first, then build on the simpler base.
  • Minimize Reader Load (principle-minimize-reader-load). Reviewing or shaping code that's hard to trace. Count layers and hidden state, collapse one-caller wrappers, shrink mutable scope.
  • Outcome-Oriented Execution (principle-outcome-oriented-execution). Planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture, don't preserve throwaway compatibility states.
  • Experience First (principle-experience-first). Product, UX, or feature-scope tradeoffs. Choose user delight over implementation convenience.
  • Exhaust the Design Space (principle-exhaust-the-design-space). A novel interaction or architectural decision with no precedent. Build 2-3 competing prototypes and compare before committing.
  • Build the Lever (principle-build-the-lever). Any non-trivial work. Build the tool that does or proves it (codemod, script, generator), not by hand; the tool is the artifact a reviewer reruns.

Read the full file on GitHub · 109 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 109 lines · 93 tokens per session scan A 9a16f67f2692

Subscribe to this mod's changes

pstack is a skill published in the GitHub repository Sma1lboy/rove (114 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 1,855 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

token-saver-config

Configure and diagnose token-saver compression settings. Use when the user asks about adjusting compression levels, checking processor status, debugging hook issues, or reviewing savings statistics.

ppgranger/token-saver · 37 tokens

omd-grill

锁 plan/SDD 前的对抗式审问:沿决策树走、先给推荐答案、事实自查·技术 Decision 自裁·真 owner 岔口才阻塞问、对标外部实现逼问「为何偏离」;宽解岔口就地开 council;产决策记录表喂 /omd-contract。审议纪律:只讨论不动手。Trigger:/omd-grill、审问、盘问这个方案、把这事讨论清楚、压测计划、stress-test。.

AbyssCN/oh-my-dag · 122 tokens

omd-note

把定型的决策/参考资料轻量记进持久台账 docs/plan/NOTES.md,供 /omd-contract 收割。记 why 不复制内容、遮敏感信息、追加不覆盖。含 ref 职能。Trigger:/omd-note、记下来、这个决定记一下、留个引用。.

AbyssCN/oh-my-dag · 76 tokens

omd-recall

主动召回 omd 自记忆:推理/写作/决策卡住时主动查既有事实,不等被动触发。经 memoryrecall 语义+词法混合检索,回带 confidence + source。Trigger:/omd-recall、查历史、以前怎么做的、翻一下记忆、有没有先例。.

AbyssCN/oh-my-dag · 83 tokens

vf-ext-development

Use when creating, modifying, testing, or publishing a Veryfront extension under extensions/ — covers manifest/factory parity, capability types, contract registration, teardown hygiene, and CI lint checks.

veryfront/veryfront-code · 41 tokens

vf-error-handling

Use when creating new errors, migrating error classes to registry, catching/handling errors, or working with the VeryfrontError system.

veryfront/veryfront-code · 30 tokens