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/beel-es/beel-mcp/agents-mdgit clone --depth 1 https://github.com/beel-es/beel-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/beel-es/beel-mcp/agents-md)<a href="https://agentmods.dev/instructions/beel-es/beel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/beel-es/beel-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 | $0.00880 | $0.00880 |
| Opus 5 | $0.00440 | $0.00440 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
beel-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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working on this repository with a coding agent
This is the BeeL MCP server: Spanish e-invoicing (VeriFactu) tools for LLM agents,
derived from the public OpenAPI contract. Read README.md for what it does and
CONTRIBUTING.md for the rules; this file is the short version an agent needs before
touching code.
Commands
npm ci
npm test # vitest — must stay green
npm run typecheck # tsc for both the Node and the Worker configs
npm run lint # eslint
npm run format # prettier --write (CI runs format:check)
npm run build # tsup + the MCP App bundle (dist/mcpapp/invoice-pdf.html)
npm run smoke # boots dist/index.js and asserts tools/list
npm run tools:list # every tool the server exposes, with its scopes
Where things live
src/spec/— loads the OpenAPI contract (openapi/public-api.yaml) and derives the operation manifest. The contract is synced from the API, never edited by hand.src/policy/— which operations become tools (tool-policy.ts) and which scopes they need (scopes.ts). Least privilege: never add a scope no tool uses.src/guardrails/— the fiscal invariants checked before a request leaves (validate.ts), the rules as markdown (rules/), and the error catalogue (catalog.ts).src/tools/— API tools, docs tools, workflow tools;src/prompts/— the workflow prompts.src/server.ts— the MCP server (stdio and remote share it);src/index.ts— the stdio entrypoint.src/cf/— the Cloudflare Worker: OAuth bridge (beel-handler.ts), public discovery, token exchange, PDF relay. Deployment notes inDEPLOY.md.src/mcpapp/— the invoice viewer MCP App and its CSP contract.tests/— vitest; one file per module. A behaviour change without a test is not done.
Rules that are not negotiable
- The API is the authority. A guardrail mirrors a rejection the API already makes; never invent fiscal rules here.
- No secrets, no infrastructure in code. Credentials come from the environment (
src/shared/defaults.tslists every variable);wrangler.jsoncholds only non-secret configuration. - Do not hand-edit the contract or the lock.
npm run sync:specandnpm run spec:lockare the only way it changes. - Every string an agent reads is product copy. Tool descriptions, guardrail hints and error remedies must be precise and short; no marketing.
- Conventional Commits. Releases are cut by release-please from the commit history.
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 · 61 lines · 880 tokens per session scan A 32d36caa6903
beel-mcp AGENTS.md is an instructions file published in the GitHub repository beel-es/beel-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 880 tokens to every session, about $0.0044 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
ZATCA AGENTS.md
AGENTS.md instructions for SallaApp/ZATCA: See CLAUDE.md for the full guide. Quick facts.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
mcpelevator CLAUDE.md
Claude Code instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.
mcp-execution mcp-wasm-runtime.instructions.md
Instructions for bug-ops/mcp-execution, covering copilot instructions: mcp-wasm-runtime, security - critical, security principles, security configuration and host function safety.
cortex AGENTS.md
AGENTS.md instructions for tools-for-agents/cortex, covering agents.md — cortex, setup, the rules this repo is built on, tests and ci.