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.
npx agentmods add instructions/mrslbt/pdf-it/agents-mdgit clone --depth 1 https://github.com/mrslbt/pdf-itWrote 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/mrslbt/pdf-it/agents-md)<a href="https://agentmods.dev/instructions/mrslbt/pdf-it/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslbt/pdf-it/agents-md.svg" alt="Measured on agentmods" 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 | $0.01527 | $0.01527 |
| Opus 5 | $0.00763 | $0.00763 |
| Sonnet 5 | $0.00305 | $0.00305 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
pdf-it AGENTS.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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project contract for AI coding agents (Cursor, Codex, Continue.dev, Claude Code, etc.) working in this repo. Read this before making changes.
What this project is
pdf-it-mcp is an MCP server + Claude Code skill that converts markdown into designed PDFs. v2.0.0 is a native renderer: @react-pdf/renderer + remark, no Chrome, no Puppeteer, no external runtime at render time. Fonts are embedded.
Two templates ship: research-report (cover + auto-TOC + footer) and plain (body only). Two tools: generate_pdf, list_templates.
Source of truth
src/templates/design-tokens.ts is the single source for colors, type sizes, leadings, mm/pt conversion, and cover positioning. Every component reads from this file. Do not hardcode design values anywhere else.
If a component needs a value not yet in design-tokens.ts, add it to design-tokens.ts first, then read it from the component. No exceptions.
Architecture
src/
index.ts MCP server entry (low-level SDK Server)
generator.tsx generatePdf() — picks template, calls renderToFile
types.ts GeneratePdfOptions / Result
utils.ts slugify only
prompts.ts MCP prompts: research_report, quick_note, pdf_outline
resources.ts MCP resources: pdf-it://templates/* + style-guide + cheatsheet
markdown/render.tsx remark mdast → React component tree + TOC entry list
templates/
index.ts template registry { "research-report", "plain" }
ResearchReport.tsx Cover + TOC + Body Page with Footer
Plain.tsx Body Page only, optional Footer
design-tokens.ts single source of truth
fonts.ts registerFonts() — call once before render
components/
Cover.tsx type-only cover
TOC.tsx "Contents" + entry list, in-PDF anchor Links
Footer.tsx fixed footer, JetBrains Mono page numbers
body.tsx H1/H2/H3, P, Strong/Em, A, InlineCode, CodeBlock,
Blockquote, UL/OL, HR, Tbl + mm() helper
charts/
HorizontalBarChart.tsx first chart primitive (monochrome, hairline)
assets/fonts/ ships into dist via npm run build:assets
preview-*.tsx dev-only — excluded from tsconfig, not in dist
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.
- 4d ago First seen · 101 lines · 1,527 tokens per session scan A db872bd2ab8b
pdf-it AGENTS.md is an instructions file published in the GitHub repository mrslbt/pdf-it (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,527 tokens to every session, about $0.0076 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 2026-08-31.
Other instructions, from other repositories
Unity-MCP copilot-instructions.md
Copilot instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.
mcp-erpnext AGENTS.md
AGENTS.md instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
mcp-erpnext CLAUDE.md
Claude Code instructions for Casys-AI/mcp-erpnext: See AGENTS.md for all repository guidelines, architecture, conventions, and task recipes.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
powerbi-mcp CLAUDE.md
Instructions for sulaiman013/powerbi-mcp, covering claude.md and developer notes.