Borrowing it
Nothing to install: this file belongs to s-stefanov/actual-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/s-stefanov/actual-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/s-stefanov/actual-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/s-stefanov/actual-mcp/agents-md)<a href="https://agentmods.dev/instructions/s-stefanov/actual-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/s-stefanov/actual-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80ร15 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/s-stefanov/actual-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/s-stefanov/actual-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 | $0.01711 | $0.01711 |
| Opus 5 | $0.00856 | $0.00856 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
actual-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ measured 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- actual-mcp CLAUDE.md โ 100% identical, 166 lines differ
How it starts
The opening of the file, as written. The whole thing โ 165 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
๐ Project Awareness & Context
- Follow the existing TypeScript project structure and maintain consistency with established patterns.
๐งฑ Code Structure & Modularity
- Never create a file longer than 500 lines of code. If a file approaches this limit, refactor by splitting it into modules or helper files.
- Organize code into clearly separated modules, grouped by feature or responsibility.
For Actual MCP server, this looks like:
- Main server (
src/index.ts): MCP server initialization and transport setup. - MCP Integration: Uses
@modelcontextprotocol/sdkfor server implementation. - Actual Budget API (
src/actual-api.ts): Manages the connection lifecycle to Actual Budget data. - Tools (
src/tools/): Each tool follows a consistent modular pattern:index.ts: Schema definition and main handler.input-parser.ts: Argument validation and parsing.data-fetcher.ts: Data retrieval from external API.report-generator.ts: Output formatting.types.ts: Tool-specific type definitions.
- Core Utilities (
src/core/): Shared functionality for data fetching, input handling, aggregation, and mapping.
- Main server (
- Use clear, consistent imports (prefer relative imports within packages).
- Use clear, consistent imports (prefer relative imports within packages).
- Use process.env for environment variables.
๐งช Testing & Reliability
- Always create Vitest unit tests for new features (functions, classes, modules, etc).
- Use TypeScript in tests and maintain type safety throughout test suites.
- After updating any logic, check whether existing unit tests need to be updated. If so, do it.
- Tests should be co-located with source files using
.test.tsnaming convention.- Example:
src/core/data/fetch-accounts.tsโsrc/core/data/fetch-accounts.test.ts
- Example:
- Use proper ESM module mocking with
vi.mock()for external dependencies. - Test commands available:
npm run test- Run all tests oncenpm run test:unit:watch- Run tests in watch modenpm run test:coverage- Generate coverage reportsnpm run test:ui- Open Vitest UI for interactive testing
- Code quality commands:
npm run lint- Run ESLint to check for code quality issuesnpm run lint:fix- Auto-fix ESLint issues where possiblenpm run format- Format code with Prettiernpm run format:check- Check if code is properly formattednpm run type-check- Run TypeScript type checking without compilationnpm run quality- Run full quality check (lint + format + type-check)
- Include comprehensive test coverage:
- 1 test for expected use (happy path)
- 1 edge case (boundary conditions)
- 1 failure case (error handling)
- Mock external dependencies (actual-api.js, etc.)
- Follow existing test patterns in
src/core/for consistency.
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.
- 9d ago First seen ยท 165 lines ยท 1,711 tokens per session scan A c41fa24752b9
actual-mcp AGENTS.md is an instructions file published in the GitHub repository s-stefanov/actual-mcp (224 stars, last pushed yesterday), licensed MIT. It adds 1,711 tokens to every session, about $0.0086 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.