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.
git clone --depth 1 https://github.com/minghinmatthewlam/agent-guardsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/minghinmatthewlam/agent-guards/pstack)<a href="https://agentmods.dev/plugins/minghinmatthewlam/agent-guards/pstack"><img src="https://agentmods.dev/badge/plugins/minghinmatthewlam/agent-guards/pstack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/minghinmatthewlam/agent-guards/pstack"><img src="https://agentmods.dev/badge/plugins/minghinmatthewlam/agent-guards/pstack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
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.
What it actually says
{
"name": "pstack",
"version": "0.15.17",
"description": "if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.",
"author": {
"name": "Lauren Tan"
},
"homepage": "https://github.com/cursor/plugins/tree/main/pstack",
"repository": "https://github.com/cursor/plugins",
"license": "MIT",
"keywords": [
"pstack",
"poteto-mode",
"workflow",
"principles",
"agent-style",
"subagents",
"unslop"
]
}
What it installs
The manifest is a name and a version. 55 skills, 2 agents travel with it, and installing the plugin installs all of them — 2,791 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill setup-pstack A 62 tokens
- Skill poteto-mode A 49 tokens
- Skill architect A 52 tokens
- Skill teach A 60 tokens
- Skill interrogate A 51 tokens
- Skill how A 60 tokens
- Skill swarm A 41 tokens
- Skill principle-guard-the-context-window A 46 tokens
- Skill bro A 16 tokens
- Skill reflect B 36 tokens
- Skill show-me-your-work A 75 tokens
- Skill automate-me A 70 tokens
- Skill benchmark-checklist A 53 tokens
- Skill reproduce-and-fix-issues A 48 tokens
- Skill setup-benny A 39 tokens
- Skill triage-issue-reports A 46 tokens
- Skill typescript-best-practices A 24 tokens
- Skill recall A 77 tokens
- Skill principle-type-system-discipline A 60 tokens
- Skill principle-outcome-oriented-execution A 39 tokens
- Skill blast-radius A 61 tokens
- Skill principle-experience-first A 37 tokens
- Skill tdd A 52 tokens
- Skill principle-build-the-lever A 71 tokens
- Skill principle-encode-lessons-in-structure A 49 tokens
- Skill principle-minimize-reader-load A 44 tokens
- Skill no-comments A 20 tokens
- Skill principle-explain-the-number A 59 tokens
- Skill principle-separate-before-serializing-shared-state A 50 tokens
- Skill principle-test-behavior-not-implementation A 52 tokens
- Skill why A 89 tokens
- Skill arena A 58 tokens
- Skill ketchup A 42 tokens
- Skill unslop A 14 tokens
- Skill principle-subtract-before-you-add A 39 tokens
- Skill principle-fix-root-causes A 42 tokens
- Skill principle-prove-it-works A 50 tokens
- Skill create-verification-skill A 64 tokens
- Skill maintain-verification-skill A 57 tokens
- Skill poteto-help A 40 tokens
- Skill principle-migrate-callers-then-delete-legacy-apis A 45 tokens
- Skill principle-laziness-protocol A 42 tokens
- Skill technical-writing A 52 tokens
- Skill figure-it-out A 63 tokens
- Skill correct A 68 tokens
- Skill principle-boundary-discipline A 46 tokens
- Skill principle-attack-the-premise A 51 tokens
- Skill principle-model-the-domain A 27 tokens
- Skill principle-foundational-thinking A 42 tokens
- Skill principle-make-operations-idempotent A 46 tokens
- Skill principle-sequence-verifiable-units A 68 tokens
- Skill principle-exhaust-the-design-space A 41 tokens
- Skill principle-never-block-on-the-human A 24 tokens
- Skill principle-redesign-from-first-principles A 21 tokens
- Skill make-bot-ui D 49 tokens
- Agent poteto-agent A 92 tokens
- Agent Comment Sicko A 20 tokens
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.
- 2d ago First seen · 21 lines scan A 3b674ec09745
pstack is a plugin published in the GitHub repository minghinmatthewlam/agent-guards (47 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-14.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.