Borrowing it
Nothing to install: this file belongs to jpoindexter/design-md-extractor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jpoindexter/design-md-extractor/main/CLAUDE.mdgit clone --depth 1 https://github.com/jpoindexter/design-md-extractorWrote 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/instructions/jpoindexter/design-md-extractor/claude-md)<a href="https://agentmods.dev/instructions/jpoindexter/design-md-extractor/claude-md"><img src="https://agentmods.dev/badge/instructions/jpoindexter/design-md-extractor/claude-md/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/instructions/jpoindexter/design-md-extractor/claude-md"><img src="https://agentmods.dev/badge/instructions/jpoindexter/design-md-extractor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01039 | $0.01039 |
| Opus 5 | $0.00519 | $0.00519 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
design-md-extractor CLAUDE.md 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working in this repository.
Commands
npm run build # tsc compile src/ → dist/
npm run gui # build + launch GUI at http://127.0.0.1:4317
npm test # vitest run (all tests)
npm run test:watch # vitest watch mode
npm run lint # eslint
npm run format # prettier --write .
npm run check # build + lint + test (pre-merge gate)
# Run a single test file
npx vitest run tests/unit/normalizeEvidence.test.ts
# CLI usage (after build)
node dist/cli.js extract https://example.com --out ./out/example
Architecture
Dual entry points compile to two binaries: dist/cli.js (CLI) and dist/gui.js (local HTTP server). Both converge on the same extraction pipeline.
Extraction pipeline
URL
└─ discoverStylePages (separate Chromium launch, scrapes <a href> links)
└─ runExtraction (orchestrates browser session across URLs × viewports)
├─ newLoadedPage (Playwright page load + settle)
├─ collectPageEvidence (page.evaluate — runs in browser context)
│ ├─ color extraction (computed styles → hex/rgba normalization)
│ ├─ typography sampling (all visible elements)
│ └─ component detection (scoring heuristic: button/card/nav/input/badge)
└─ normalizeEvidence (dedup + rank raw evidence into structured tokens)
└─ EvidenceSchema.parse (Zod validation — hard boundary)
└─ writeArtifacts → evidence.json, DESIGN.md, preview.html, screenshots/
Source layout
| Path | Responsibility |
|---|---|
src/config/ |
CLI arg parsing (parseArgs.ts), viewport presets (viewports.ts) |
src/crawl/ |
Browser lifecycle (browserSession.ts), page loading/settling (pageLoader.ts), page discovery (discoverPages.ts), extraction orchestrator (runExtraction.ts) |
src/extract/ |
collectPageEvidence.ts — entire implementation runs inside page.evaluate() |
src/evidence/ |
Zod schema (evidenceSchema.ts), normalization/dedup/scoring (normalizeEvidence.ts), confidence thresholds (confidence.ts) |
src/generate/ |
DESIGN.md renderer (generateDesignMd.ts), preview HTML (generatePreviewHtml.ts), style CSS (generateStyleCss.ts) |
src/io/ |
Artifact writing, path sanitization |
src/gui/ |
Pure Node.js HTTP server (no framework), GUI extraction runner (runGuiExtraction.ts), SSR SPA shell (appHtml.ts) |
src/types/ |
Evidence type (inferred from EvidenceSchema) |
skill/ |
Claude Code skill (SKILL.md) + references for LLM agents consuming DESIGN.md output |
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.
- 10d ago First seen · 80 lines · 1,039 tokens per session scan A 58a7ab5b21b6
design-md-extractor CLAUDE.md is an instructions file published in the GitHub repository jpoindexter/design-md-extractor (61 stars, last pushed 3mo ago), licensed MIT. It adds 1,039 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.