QBO-Multicompany-MCP: Instructions file for Codex

AGENTS.md

QBO-Multicompany-MCP AGENTS.md is an instructions file for Codex, OpenCode from LatinumLabs/QBO-Multicompany-MCP. It costs 672 tokens per session, scanned A, original, MIT.

A project instruction file for AI coding agents working on a TypeScript MCP server that connects an assistant to several QuickBooks Online company files.

In plain words
What is it for?
Use it to guide work on the server’s OAuth login, QuickBooks connections, storage, MCP tools, Azure deployment, tests, linting, and formatting.
Why use it?
It records the project layout, commands, deployment details, and rules that should be checked before changing the code.

Instructions file for CodexOpenCode

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

This is LatinumLabs/QBO-Multicompany-MCP's own configuration. It tells Codex and OpenCode how to work on QBO-Multicompany-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 QBO-Multicompany-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LatinumLabs/QBO-Multicompany-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/LatinumLabs/QBO-Multicompany-MCP/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/LatinumLabs/QBO-Multicompany-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 QBO-Multicompany-MCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/latinumlabs/qbo-multicompany-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/latinumlabs/qbo-multicompany-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/latinumlabs/qbo-multicompany-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/latinumlabs/qbo-multicompany-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 QBO-Multicompany-MCP AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/latinumlabs/qbo-multicompany-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/latinumlabs/qbo-multicompany-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 672 This file is loaded in full into every session.
When invoked 672 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 $0.00672 $0.00672
Opus 5 $0.00336 $0.00336
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured 9d ago against content hash 5d70486f650d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

QBO-Multicompany-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 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository guide for coding agents

A self-hosted remote MCP server giving an AI assistant access to several QuickBooks Online company files through one connection. Single npm package, TypeScript, deployed as a container to Azure Container Apps.

Commands

npm install
npm run build         # tsc -b
npm run lint          # eslint
npm run format:check  # prettier --check
npm test              # vitest run

All four run in CI on every push and pull request. The test suite is fully offline — in-memory store, local encryption key, scripted Intuit — so there is no reason to skip it.

Layout

  • src/config.ts — every environment variable, parsed and validated. Start here to understand what the service can be told to do.
  • src/oauth/ — the connector's own OAuth 2.1 authorization server (for the assistant).
  • src/qbo/ — Intuit OAuth client, token lifecycle, company registry, REST client.
  • src/store/ — Table Storage and in-memory stores, envelope encryption.
  • src/mcp/ — MCP server and tool definitions.
  • src/routes/ — OAuth routes and the published app pages.
  • infra/ — Azure Bicep and the deploy script.
  • docs/architecture.md — read before any structural change.

Conventions

  • TypeScript, strict mode. ESM with .js import specifiers (NodeNext resolution) — importing ./foo.ts will not compile.
  • Comments explain why. Match the surrounding density rather than adding narration.
  • Errors reaching the model come back as tool results with isError, not protocol failures, so the model can read and correct them.

Invariants worth knowing before you change things

  • Never log tokens, authorization codes, or sealed values. Realm ids and hashed user ids are the safe correlation keys.
  • Operator identity is configuration, not source. Every deployment is run by someone different. Nothing about a particular operator, practice, or contact address belongs in the code — it comes from OPERATOR_* env vars.
  • Test fixtures use example.com and obviously fake secrets. Keep it that way; never commit real credentials, realm ids, or company names.
  • The privacy page is a factual claim. If a stored record gains a field, disclose it in src/routes/appRoutes.ts. appRoutes.test.ts has assertions that exist as a reminder.
  • Several subtle things are load-bearing and documented in docs/architecture.md: the hashed user id (how one person holds many companies), conditional company writes (how concurrent refreshes do not clobber each other), the shared in-flight refresh, and single-use records consumed with ETag-conditional deletes.
  • New environment variables go in three places: src/config.ts, docs/configuration.md, and .env.example — plus infra/main.bicep and infra/deploy.sh if they need to reach a deployment.

Read the full file on GitHub · 64 lines

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. 9d ago First seen · 64 lines · 672 tokens per session scan A 5d70486f650d

Subscribe to this mod's changes

QBO-Multicompany-MCP AGENTS.md is an instructions file published in the GitHub repository LatinumLabs/QBO-Multicompany-MCP (1 stars, last pushed 1mo ago), licensed MIT. It adds 672 tokens to every session, about $0.0034 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens