paperpress: Instructions file for Claude Code

CLAUDE.md

paperpress CLAUDE.md is an instructions file for Claude Code from rozetyp/paperpress. It costs 2,081 tokens per session, scanned A, original, MIT.

Repository guidance for Claude Code describes a Fastify server that detects a company's branding from its website and turns Markdown into a branded PDF through one HTTP request. It also documents the server's commands and architecture.

In plain words
What is it for?
Use it when changing this TypeScript API, checking its types, building or starting it, or working with its Prisma database schema.
Why use it?
It gives the coding agent project-specific rules and commands, including known gaps such as the lack of an automated test suite. This helps avoid inventing unsupported features or test commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is rozetyp/paperpress's own configuration. It tells Claude Code how to work on paperpress itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paperpress configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rozetyp/paperpress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rozetyp/paperpress/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rozetyp/paperpress

Made for: Claude Code.

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 paperpress CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rozetyp/paperpress/claude-md/github.svg)](https://agentmods.dev/instructions/rozetyp/paperpress/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rozetyp/paperpress/claude-md"><img src="https://agentmods.dev/badge/instructions/rozetyp/paperpress/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.

agentmods 80×15 button for paperpress CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rozetyp/paperpress/claude-md"><img src="https://agentmods.dev/badge/instructions/rozetyp/paperpress/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,081 This file is loaded in full into every session.
When invoked 2,081 The same file — it is already loaded in full.
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 $0.02081 $0.02081
Opus 5.5 $0.00832 $0.00832
Sonnet 5.5 $0.00416 $0.00416
Haiku 4.5 $0.00208 $0.00208

Measured 16d ago against content hash a80d49374d6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paperpress 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 16d 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.

CLAUDE.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 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 with code in this repository.

What this is

An API that detects a company's brand (logo, color, font) from its live URL and renders markdown into a PDF styled in that brand, in one HTTP call. A single Fastify process — REST API plus a hosted MCP endpoint (src/routes/mcp.ts), no separate package or install step.

Deliberately kept as a lean skeleton: this server, callable, nothing else. No accounts, no API keys, no database — every endpoint is anonymous and bounded by per-IP rate limits. No automated test suite. Don't add features toward a 1.0 unless explicitly asked — bug fixes and code-quality work are the useful contributions here.

Commands

npm run dev              # tsx watch src/index.ts — local dev server
npm run build             # tsc -> dist/
npm start                 # node dist/index.js (run build first)
npx tsc --noEmit          # typecheck only, no test suite exists — use this to verify changes

There is no test command — don't invent one; npx tsc --noEmit plus manual verification (see samples below) is the actual verification loop this repo uses.

Regenerating the example renders in samples/ (useful after touching src/render/):

npx tsx scripts/preview.ts              # renders samples/sample.md across all 5 themes + a few brand kits
npx tsx scripts/detect.ts <url> [...]    # CLI brand-detection debug; add RENDER_SAMPLE=1 to also render a PDF per URL

Architecture

Render pipeline (src/render/): markdown.ts (remark/rehype, allowDangerousHtml: false) produces HTML → a theme from themes/ (clean/executive/academic/technical/marketing, plus an optional per-request BrandKit) supplies the CSS → pdf.ts prints it with Playwright. detect.ts is the other consumer of the render layer: it navigates a URL and reads computed styles/DOM signals (CSS custom properties, CTA background colors, scored logo <img> candidates, computed font-family) to produce a BrandKit — no LLM or image analysis involved, it reads values the browser already computed.

Read the full file on GitHub · 51 lines

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. 16d ago Changed · -1 lines · +374 tokens per session a80d49374d6c
  2. 2mo ago First seen · 52 lines · 1,707 tokens per session scan A d82f876f8409

Subscribe to this mod's changes

paperpress CLAUDE.md is an instructions file published in the GitHub repository rozetyp/paperpress (0 stars, last pushed 17d ago), licensed MIT. It adds 2,081 tokens to every session, about $0.0083 per session on Opus 5.5. 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 2026-09-18.

Related

paperpress CLAUDE.md compared with instructions from other repositories

paperpress CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
paperpress CLAUDE.mdrozetyp/paperpressInstructions file017d agoMITA2,081Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150kyesterdayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283kyesterdayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot