Borrowing it
Nothing to install: this file belongs to Orlando-Villanueva/ynab-budget-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Orlando-Villanueva/ynab-budget-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Orlando-Villanueva/ynab-budget-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/orlando-villanueva/ynab-budget-mcp/agents-md)<a href="https://agentmods.dev/instructions/orlando-villanueva/ynab-budget-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/orlando-villanueva/ynab-budget-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/orlando-villanueva/ynab-budget-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/orlando-villanueva/ynab-budget-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00566 | $0.00566 |
| Opus 5.5 | $0.00226 | $0.00226 |
| Sonnet 5.5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
ynab-budget-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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
This repository contains a local MCP server for YNAB. It lets MCP-capable agents query budgeting data through curated tools instead of raw shell commands.
Project Shape
- Runtime: Node.js 22.9+
- Language: TypeScript executed directly with Node's
--experimental-transform-types - Package manager: npm
- Test runner:
node:test - Dependencies: intentionally minimal; prefer built-in Node features unless a dependency is clearly justified
Core Files
README.md: setup, usage, MCP client configuration, and smoke-test instructionssrc/index.ts: process entrypoint that constructs the client, registers tools, and starts the stdio serversrc/mcp.ts: lightweight MCP/JSON-RPC server implementation over stdiosrc/tools.ts: publicynab_*tool definitions, input validation, summaries, and error wrappingsrc/ynab/client.ts: YNAB API client, auth, query building, delta caching, and error mappingsrc/ynab/normalize.ts: milliunit-to-currency normalization helperstest/*.test.ts: protocol, client, and tool behavior tests
Commands
- Start server:
npm run start - Run tests:
npm test
Environment
- Required env var:
YNAB_ACCESS_TOKEN - Keep secrets in
.envor local environment variables - Never hardcode tokens or include them in test fixtures, prompts, logs, or committed files
Implementation Rules
- Keep the tool surface curated and read-only by default; guarded category-assignment and category-creation preview/apply workflows are the only experimental opt-in writes
- Do not add generic raw endpoint passthrough tools unless explicitly requested
- Prefer
/v1/plansendpoints over legacy/budgetspaths - Preserve raw milliunit values and add normalized
*_currencyfields where helpful - Keep caching in-memory only unless persistent caching is explicitly requested
- Use clear structured errors for auth failures, rate limits, not founds, and upstream failures
Editing Guidance
- Prefer small, focused changes
- Maintain the current layered structure: MCP transport, tool layer, YNAB client, normalization helpers
- Add or update tests with behavior changes
- Prefer built-in Node APIs over pulling in new packages
- Avoid writing to stdout outside MCP protocol responses; use stderr for diagnostics
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.
- 1mo ago Changed · +6 tokens per session 4b9c83af7a79
- 2mo ago First seen · 59 lines · 560 tokens per session scan A 237b496c17a2
ynab-budget-mcp AGENTS.md is an instructions file published in the GitHub repository Orlando-Villanueva/ynab-budget-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 566 tokens to every session, about $0.0023 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.