security-design-review

security-design-review is a skill for Claude Code from pi-sloane/claude-plugin. It costs 39 tokens per session (458 once invoked), scanned A, original, MIT.

A workflow for starting a Pi Security design review from a supported Confluence or Notion document URL or from Markdown text supplied in the conversation. A design review examines a proposed system for security concerns.

In plain words
What is it for?
Use it to submit an eligible design document for a Pi Security review. Provide either a Confluence or Notion URL or inline Markdown content.
Why use it?
It limits reviews to the input types this workflow can process and requires the user to confirm before the review starts. Local files, attachments, PDFs, DOCX files, images, and unsupported URLs are not accepted.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pi-security plugin — 6 skills, 1 MCP server shipped together

Good fit Use it to submit an eligible design document for a Pi Security review. Provide either a Confluence or Notion URL or inline Markdown content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pi-sloane/claude-plugin/security-design-review
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.

Any agent
npx skills add pi-sloane/claude-plugin --skill security-design-review
Clone the repo
git clone --depth 1 https://github.com/pi-sloane/claude-plugin

Made for: Claude Code.

Or install pi-security, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

Wrote 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.

agentmods badge for security-design-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pi-sloane/claude-plugin/security-design-review/github.svg)](https://agentmods.dev/skills/pi-sloane/claude-plugin/security-design-review)
Your own site
<a href="https://agentmods.dev/skills/pi-sloane/claude-plugin/security-design-review"><img src="https://agentmods.dev/badge/skills/pi-sloane/claude-plugin/security-design-review/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.

agentmods 80×15 button for security-design-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/pi-sloane/claude-plugin/security-design-review"><img src="https://agentmods.dev/badge/skills/pi-sloane/claude-plugin/security-design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00458
Opus 5 $0.00019 $0.00229
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 9d ago against content hash a01fc87356f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-design-review 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 9d 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.

skills/security-design-review/SKILL.md · 42 lines

What it actually says

Start a Pi design review

Use this skill only when the user explicitly asks to start a Pi Security design review of a design document.

Tools

Both are state-changing and require confirmation:

  • pi_design_review_url_create - starts a design review for a supported Confluence or Notion document URL (url, http/https only).
  • pi_design_review_markdown_create - starts a design review from inline Markdown design-document content (content, up to 5 MiB).

Accepted inputs

  • A Confluence or Notion document URL, or
  • Design-document content provided inline as Markdown or plain text in the conversation.

Rejected inputs

Do not accept, convert, or promote any of the following into a design-review call:

  • Local file paths or file:// URIs
  • Chat attachments
  • PDFs, DOCX files, images, or any binary content
  • URLs other than supported Confluence or Notion document URLs

If the user offers one of these, explain that this workflow takes a supported Confluence/Notion URL or inline Markdown, and that other document types are handled in the Pi web app.

Before calling either tool

  1. Validate the input: a well-formed https Confluence/Notion document URL, or non-empty inline Markdown.
  2. Show the user exactly what will be submitted: the URL, or the document title plus approximate length for inline Markdown.
  3. Explain the effect: Pi will start a design review of this document in the authenticated tenant.
  4. Ask for confirmation and proceed only on an explicit yes in the current turn.
  5. Call the tool once.
  6. Report exactly what Pi returned: if the review started, give its status and review ID; otherwise report the returned status as-is. Started or queued means the review is in progress, not finished. Never invent results or completion.
  7. If the call fails or times out ambiguously, report that and stop. Do not retry automatically, since a retry could start a duplicate review.
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. 9d ago First seen · 42 lines · 39 tokens per session scan A a01fc87356f2

Subscribe to this mod's changes

security-design-review is a skill published in the GitHub repository pi-sloane/claude-plugin (12 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 458 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens