agentmods.dev

moneys3-mcp: Instructions file for Codex

AGENTS.md

moneys3-mcp AGENTS.md is an instructions file for Codex, OpenCode from hlebtkachenko/moneys3-mcp. It costs 424 tokens per session, scanned A, original, MIT.

A set of project instructions for a TypeScript MCP server that connects accounting software to the Money S3 GraphQL API. MCP is a way for an AI tool to call external services through defined tools.

In plain words
What is it for?
Use it when adding or changing Money S3 tools, validating GraphQL against the documented schema, running tests, or updating the README tool tables.
Why use it?
It gives contributors rules for changing GraphQL requests, handling writes, testing tools, and keeping the server's documentation and registrations consistent.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is hlebtkachenko/moneys3-mcp's own configuration. It tells Codex and OpenCode how to work on moneys3-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything moneys3-mcp configures →

not rated 2repo changed 19d ago A scan 424 tokens original MIT
View source ↗ hlebtkachenko/moneys3-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to hlebtkachenko/moneys3-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.

Copy the file
curl -O https://raw.githubusercontent.com/hlebtkachenko/moneys3-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hlebtkachenko/moneys3-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for moneys3-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hlebtkachenko/moneys3-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/hlebtkachenko/moneys3-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hlebtkachenko/moneys3-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hlebtkachenko/moneys3-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.

agentmods 80×15 button for moneys3-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hlebtkachenko/moneys3-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hlebtkachenko/moneys3-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 424 This file is loaded in full into every session.
When invoked 424 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00424 $0.00424
Opus 5.5 $0.00170 $0.00170
Sonnet 5.5 $0.00085 $0.00085
Haiku 4.5 $0.00042 $0.00042

Measured 19d ago against content hash 7b4c38adcca3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

moneys3-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 19d 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.

AGENTS.md · 24 lines

What it actually says

AGENTS.md

MCP server for Money S3 (Seyfor) accounting via the Money S3 GraphQL API. TypeScript, Node 22+, stdio transport. Layout and design: ARCHITECTURE.md.

Commands

npm ci
npm run build           # tsc -> dist/
npm test                # build + node:test suite (fake Money S3 transport, no server needed)
npm run check:contract  # validate every tool's GraphQL against docs/schema.graphql
MONEYS3_DOMAIN=yourcompany npm run introspect  # refresh docs/schema.graphql from a live S3Api

Rules

  • Any change to the GraphQL a tool sends must pass npm run check:contract. Take field, input and enum names from docs/schema.graphql, not from memory. Avoid fields marked @legislationDirective(legislationType: SK) unless the tool is for Slovak agendas (SK_TOOLS in scripts/contract-lib.mjs).
  • Schema-valid is not proof a query works: replay a changed read query through m3_graphql on a demo agenda. Never test writes against a real company agenda.
  • Build mutation input with gqlValue/runMutation from src/tools/helpers.ts; never interpolate tool arguments into GraphQL text.
  • Every tool has annotations (READ, CREATE, UPDATE, DELETE, RAW). Writes report isSuccess=false as an error. Register updates with updateTool (helpers.ts).
  • New tools: register in the matching src/tools/*.ts, add the root field to ROOTS in test/server.test.mjs, list them in the README tool tables (a test checks the tables match).
  • Synthetic data only in tests and docs: no real company names, IČO, agenda GUIDs or documents. Use 12345678 as a placeholder IČO.
  • Never commit credentials; configuration is env-only (README lists the variables).
Changes

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.

  1. 19d ago Changed · +2 lines · +92 tokens per session 7b4c38adcca3
  2. 29d ago First seen · 22 lines · 332 tokens per session scan A 970324b712e3

Subscribe to this mod's changes

moneys3-mcp AGENTS.md is an instructions file published in the GitHub repository hlebtkachenko/moneys3-mcp (2 stars, last pushed 19d ago), licensed MIT. It adds 424 tokens to every session, about $0.0017 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 2026-10-08.

Backend and APIsFinance and fintechaccountingczechgraphqlinvoicesmcpmcp-server
Related

moneys3-mcp AGENTS.md compared with instructions from other repositories

moneys3-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
moneys3-mcp AGENTS.mdhlebtkachenko/moneys3-mcpInstructions file219d agoMITA424Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode