doit-mcp-server: Instructions file for Codex

AGENTS.md

doit-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from doitintl/doit-mcp-server. It costs 2,673 tokens per session, scanned A, original, MIT.

Repository instructions for a Model Context Protocol (MCP) server that gives language models access to the DoiT API, a cloud-cost management service. They explain the Node.js setup, package structure, and public-repository restrictions.

In plain words
What is it for?
Use them when changing the MCP server, its shared core package, setup commands, workflows, or public documentation.
Why use it?
They help agents understand which code belongs to the local server and which belongs to a separate private service, while avoiding confidential details in public changes.

Instructions file for CodexOpenCode

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

This is doitintl/doit-mcp-server's own configuration. It tells Codex and OpenCode how to work on doit-mcp-server 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 doit-mcp-server configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { zodToMcpInputSchema } from "../utils/schemaHelpers.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to doitintl/doit-mcp-server. 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/doitintl/doit-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/doitintl/doit-mcp-server

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 doit-mcp-server AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/doitintl/doit-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/doitintl/doit-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,673 This file is loaded in full into every session.
When invoked 2,673 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 $0.02673 $0.02673
Opus 5.5 $0.01069 $0.01069
Sonnet 5.5 $0.00535 $0.00535
Haiku 4.5 $0.00267 $0.00267

Measured 6d ago against content hash 0ea45af5e2fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doit-mcp-server 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 6d 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 · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Public Repo

This repo is public. Do not commit or write into PR titles/descriptions: internal Jira issue keys (e.g. CMP-1234), names of private/internal repos, or other internal-only details. Keep references generic (e.g. "a separate private repo") instead.

Environment Setup

Requires Node.js >=20 (the MCP SDK v2 packages set that floor). Install dependencies before running any commands:

yarn install

Yarn 4.18.1 via Corepack. Enable Corepack before using Yarn. The root project and test/integration are separate projects with their own modern yarn.lock files and packageManager pins. Both use the node-modules linker. CI installs with yarn install --immutable; migrate both projects and their workflows together.

Never run npm install. npm lockfiles are gitignored, rejected by the no-npm-lockfiles pre-commit hook, and fail the Enforce yarn step in test.yml. npm is still used deliberately for publishing only — release.yml's publish-npm job needs the npm CLI for Trusted Publishing (OIDC + provenance), which yarn cannot do. That is registry publication, not dependency management. There is deliberately no local publish script: publishing happens only from that CI job.

Project Overview

DoiT MCP Server is a Model Context Protocol (MCP) server that provides LLMs with access to the DoiT API.

This repo is the stdio MCP server plus a transport-independent core package:

  1. stdio server (src/) - Core MCP server implementation using stdio transport

    • Published as @doitintl/doit-mcp-server on npm
    • Runs locally via npx or stdio connection
    • Entry point: src/index.ts
  2. Core export (src/core.ts) - Transport-independent tools, prompts, and utilities

    • Published as the @doitintl/doit-mcp-server/core subpath
    • Consumed by a remote Cloudflare Worker that lives in a separate private repo

Project Structure

Main Package (src/)

src/
├── index.ts              # Entry point (stdio transport)
├── stdio.ts              # serveDoitStdio: serves 2025-era and 2026-07-28 clients (see docs/protocol-compatibility.md)
├── server.ts             # MCP server setup and request handlers (createServer is the per-connection factory)
├── tools/                # MCP tool implementations
│   └── __tests__/        # Tool tests
├── types/                # Tools and general type definitions
├── utils/                # Shared utilities
│   ├── util.ts           # General utilities (debugLog, etc.)
│   ├── prompts.ts        # MCP prompt definitions
│   ├── consts.ts         # Constants
│   ├── toolsHandler.ts   # Tool request handler
│   └── __tests__/        # Utility tests
└── __tests__/            # Server-level tests

Read the full file on GitHub · 189 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. 6d ago Changed · +20 tokens per session 0ea45af5e2fe
  2. 9d ago Changed · +7 tokens per session 1ba970cd9756
  3. 11d ago Changed · -3 lines · -89 tokens per session cc7cd591987b
  4. 19d ago Changed · +19 lines · +599 tokens per session 28885b5e9467
  5. 24d ago Changed · +5 lines · +69 tokens per session a10935282846
  6. 1mo ago Changed · -5 lines · +56 tokens per session 61ad5e587013
  7. 1mo ago Changed · +1 lines · +46 tokens per session 1db2f03b60b6
  8. 1mo ago Changed · +1 lines · +9 tokens per session 3e3a62504da9
  9. 1mo ago Changed · +6 lines · +117 tokens per session 07af0281b971
  10. 2mo ago First seen · 165 lines · 1,839 tokens per session scan A 752367a3bec0

Subscribe to this mod's changes

doit-mcp-server AGENTS.md is an instructions file published in the GitHub repository doitintl/doit-mcp-server (14 stars, last pushed yesterday), licensed MIT. It adds 2,673 tokens to every session, about $0.0107 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 2026-08-30.

Related

doit-mcp-server AGENTS.md compared with instructions from other repositories

doit-mcp-server AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
doit-mcp-server AGENTS.mddoitintl/doit-mcp-serverInstructions file14yesterdayMITA2,673Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot