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/markpdfdown/markpdfdown-desktop/agents-mdgit clone --depth 1 https://github.com/MarkPDFdown/markpdfdown-desktopWhat 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 | $0.03474 | $0.03474 |
| Opus 5 | $0.01737 | $0.01737 |
| Sonnet 5 | $0.00695 | $0.00695 |
| Haiku 4.5 | $0.00347 | $0.00347 |
Grade A, and why
markpdfdown-desktop 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 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - MarkPDFdown Desktop Development Guide
Build Commands
# Development
npm run dev # Run full dev environment (generates Prisma, starts Electron with IPC)
# Production Build
npm run build # Full production build (generates Prisma + builds Electron app)
npm run start # Preview production build (generates Prisma + previews Electron)
# Platform-specific builds (must run npm run build first)
npm run build:win # Build Windows NSIS installer (x64 + arm64)
npm run build:mac # Build macOS DMG (x64 + arm64)
npm run build:linux # Build Linux AppImage (x64 + arm64)
# Database
npm run generate # Generate Prisma client (required after schema changes)
npm run migrate:dev # Run migrations in development (creates/updates database)
npm run migrate:reset # Reset database and re-run all migrations (WARNING: deletes all data)
# Other
npm run lint # Run ESLint with auto-fix on all .js/.jsx/.ts/.tsx files
npm run logo # Generate app icons from src/renderer/assets/logo.png to public/icons/
Environment Setup
Prerequisites
- Node.js: v18+ recommended (ESM support required)
- npm: v8+ (comes with Node.js)
- Git: For version control
- Platform-specific tools:
- Windows: No additional tools needed
- macOS: Xcode Command Line Tools
- Linux: Standard build tools (
build-essentialon Debian/Ubuntu)
First-time Setup
# Clone repository
git clone <repository-url>
cd markpdfdown-desktop
# Install dependencies
npm install
# Generate Prisma client
npm run generate
# Run database migrations
npm run migrate:dev
# Start development server
npm run dev
Testing
本项目已配置完整的测试套件,使用 Vitest 作为测试框架。
测试命令
# 运行所有测试
npm test
# 运行单元测试(main/server)
npm run test:unit
# 运行渲染进程测试(React 组件)
npm run test:renderer
# 监听模式(开发时使用)
npm run test:watch
# 生成覆盖率报告
npm run test:coverage
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 · 303 lines · 3,474 tokens per session scan A 409e641fdf03
markpdfdown-desktop AGENTS.md is an instructions file published in the GitHub repository MarkPDFdown/markpdfdown-desktop (58 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 3,474 tokens to every session, about $0.0174 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
flexberry-markitdown-mcp CLAUDE.md
Claude Code instructions for Flexberry/flexberry-markitdown-mcp, covering claude.md, project overview, commands, install in development mode (all test/lint deps) and install with both pdf backends.
firecrawl CLAUDE.md
Claude Code instructions for firecrawl/firecrawl: Firecrawl is a web scraper API. The directory you have access to is a monorepo.
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
kipi-system AGENTS.md
AGENTS.md instructions for assafkip/kipi-system, covering q entrepreneur os, project structure, conventions, commands and build and test.