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/jinzcdev/markmap-mcp-server/agents-mdgit clone --depth 1 https://github.com/jinzcdev/markmap-mcp-serverWhat 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 | $0.01006 | $0.01006 |
| Opus 5 | $0.00503 | $0.00503 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
markmap-mcp-server 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to agents when working with code in this repository.
Commands
# Build (TypeScript → build/)
npm run build
# Run tests
npm test # vitest run (single pass)
npm run test:watch # vitest in watch mode
# Development
npm run dev # tsc-watch → auto-restart on changes
# Formatting
npm run format # prettier --write (also runs via lint-staged on commit)
# Run the server locally
node build/index.js
# With options:
node build/index.js --output /tmp/markmap --open always --return-mode both --offline
Architecture
This is an MCP server (Model Context Protocol) that converts Markdown to interactive mind maps using the markmap family of libraries. It runs over stdio transport.
Entry point: src/index.ts
- Parses CLI args (
minimist) and env vars into aMarkmapMcpContext(output dir, open mode, return mode, offline flag) - Creates an
McpServerinstance, registers tools viaregisterMarkmapTools(), and connects toStdioServerTransport
Tool registration: src/mcp/tools/
context.ts— Type definitions forMarkmapMcpContext,OpenMode("always" | "never" | "agent"),ReturnMode("path" | "content" | "both")registry-base.ts— AbstractRegistryBasewithregister()methodtool-registry.ts—ToolRegistry extends RegistryBase, addsregisterTools()wrappermarkmap-tools.ts—MarkmapToolRegistryimplements 4 tools and 1 prompt:markdown_to_mindmap— main conversion tool (html/png/svg/jpg)list_mindmaps— list generated filesget_mindmap— retrieve a single file by path (with path traversal protection)cleanup_mindmaps— delete old/all filesmindmap_from_content— prompt that asks the LLM to structure content before calling the tool
Core markmap logic: src/markmap/
createMarkmap.ts— Usesmarkmap-lib(Transformer) andmarkmap-render(fillTemplate) to convert Markdown → HTML. Injects themarkmap-toolbar, an export toolbar (PNG/JPG/SVG/Copy Markdown viahtml-to-image), and the original markdown source. In--offlinemode, inlines all JS/CSS assets.exportImage.ts— Launches headless Chromium via Playwright to render HTML → PNG/JPG/SVG. Requiresplaywrightoptional dependency.lifecycle.ts— File listing, retrieval (with path traversal check), and cleanup for the output directory.escape.ts— HTML/text escaping for safe embedding.i18n.ts— English toolbar labels used in the generated HTML.
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 · 79 lines · 1,006 tokens per session scan A edc2a50e8f02
markmap-mcp-server AGENTS.md is an instructions file published in the GitHub repository jinzcdev/markmap-mcp-server (281 stars, last pushed 28d ago), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 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
openwebui-extensions copilot-instructions.md
Instructions for Fu-Jie/openwebui-extensions, covering copilot instructions for openwebui-extensions, 🏗️ 项目结构与命名 (project structure & naming), 1. 语言与代码规范 (language & code requirements), 2. 插件目录结构 (plugin directory structure) and 3. 文档字符串规范 (docstring standard).
Plugin Documentation
Use when writing or updating plugin README files, mirrored docs pages, bilingual release notes, or other user-facing documentation for plugins.
openwebui-extensions GEMINI.md
Instructions for Fu-Jie/openwebui-extensions, covering openwebui extensions — gemini cli project context, project overview, non-negotiable rules, plugin file contract and docstring (required fields).
Commit Message
Comprehensive Conventional Commits guidelines for openwebui-extensions.
Test Generation
Comprehensive Pytest conventions, mocking strategies, and model usage rules for OpenWebUI plugins.
Siftly CLAUDE.md
Instructions for viperrcrypto/Siftly, covering siftly, quick setup, ai authentication — no api key needed, key commands and project structure.