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/j0hanz/fetch-url-mcp/agents-mdgit clone --depth 1 https://github.com/j0hanz/fetch-url-mcpWrote 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/j0hanz/fetch-url-mcp/agents-md)<a href="https://agentmods.dev/instructions/j0hanz/fetch-url-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/j0hanz/fetch-url-mcp/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 5.1 | $0.00756 | $0.00756 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
fetch-url-mcp 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 5d 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
An MCP server that fetches web pages and converts them to clean, readable Markdown.
Tooling
- Manager: npm
- Language: TypeScript (ESM, Node >=24)
- Linting: ESLint (sonarjs, unicorn, unused-imports, de-morgan, depend)
- Formatting: Prettier (@trivago/prettier-plugin-sort-imports)
Architecture
- Tool-based MCP server (MCP SDK v2 alpha)
- HTTP fetch → HTML parse (linkedom + @mozilla/readability) → Markdown conversion (node-html-markdown)
- Task system for async tool execution
Testing Strategy
- 30 test files in
__tests__/(colocated), run via Node.js built-in test runner npm run testfor all tests;npm run test:coveragefor coverage
Commands
- Dev:
npm run dev - Test:
npm run test - Lint:
npm run lint - Deploy:
npm run prepublishOnly
Safety Boundaries
- Always:
npm run lint,npm run type-check,npm run test - Ask First:
installing dependencies,deleting files,running full builds or e2e suites,database/schema migrations,deploy or infrastructure changes,git push / force push,npm run build,npm run test:coverage,npm run prepublishOnly,git push origin master --follow-tags,npm publish --access public --provenance --ignore-scripts - Never: commit or expose secrets/credentials; edit vendor/generated directories (
dist/,.git/,node_modules/); change production config without approval
Directory Overview
.
├── __tests__/ # test suites
├── .agents/ # agent skills and config
├── .github/ # CI/workflows (release, docker-republish)
├── assets/ # static assets
├── memory_db/ # persistent memory store
├── scripts/ # automation scripts
├── src/ # application source
├── .prettierignore # formatter config
├── .prettierrc # formatter config
├── docker-compose.yml # local container orchestration
├── Dockerfile # container image build
├── eslint.config.mjs # lint config
├── package.json # scripts and dependencies
├── README.md # usage and setup docs
└── server.json # published server metadata
└── ... # 3 more top-level items omitted
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.
- 5d ago First seen · 79 lines · 756 tokens per session scan A 0d5aae878dd7
fetch-url-mcp AGENTS.md is an instructions file published in the GitHub repository j0hanz/fetch-url-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 756 tokens to every session, about $0.0038 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
mcp-server-amazon CLAUDE.md
Instructions for rigwild/mcp-server-amazon, covering claude.md, development commands, install dependencies (use -d flag for puppeteer), build typescript to javascript and clean mock html files.
mcp-chrome-debugger-protocol CLAUDE.md
Instructions for VitalyOstanin/mcp-chrome-debugger-protocol, covering claude memory for mcp chrome debugger protocol, project rules, project structure, key implementation details and coordinate system.
axon AGENTS.md
AGENTS.md instructions for dinglebear-ai/axon, a project described as: Self-hosted RAG stack for crawl, scrape, search, ingest, query, and ask workflows with Qdrant, TEI embeddings, Chrome rendering, MCP/CLI/REST, and Gemini synthesis.
axon GEMINI.md
Gemini CLI instructions for dinglebear-ai/axon, a project described as: Self-hosted RAG stack for crawl, scrape, search, ingest, query, and ask workflows with Qdrant, TEI embeddings, Chrome rendering, MCP/CLI/REST, and Gemini synthesis.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.