graphdo-ts AGENTS.md

A project instruction document for graphdo-ts, a TypeScript MCP server that gives AI agents limited access to Microsoft Graph, currently for mail and Microsoft To Do. It describes the project's architecture, design choices, and dependency-injection setup.

In plain words
What is it for?
Use it as the source of project conventions when developing, reviewing, or extending graphdo-ts.
Why use it?
Contributors need the same rules for authentication, configuration, Graph requests, logging, and server structure. This document provides the reference they should read before changing the project.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/co-native-ab/graphdo-ts/agents-md
Clone the repo
git clone --depth 1 https://github.com/co-native-ab/graphdo-ts

Made for: Codex, OpenCode.

Per session 4,416 This file is loaded in full into every session.
When invoked 4,416 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04416 $0.04416
Opus 5 $0.02208 $0.02208
Sonnet 5 $0.00883 $0.00883
Haiku 4.5 $0.00442 $0.00442

Measured yesterday against content hash b00395d732d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graphdo-ts 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 yesterday.

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 · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

graphdo-ts - Scoped Microsoft Graph Access for AI Agents

What This Is

A TypeScript MCP server that gives AI agents scoped, low-risk access to Microsoft Graph API. Current capabilities cover mail and Microsoft To Do; more Graph surfaces will be added over time. Uses stdio transport and MSAL authentication (browser-only) - distributed as an MCPB bundle.

Repository: github.com/co-native-ab/graphdo-ts

Architecture

src/
  index.ts               Entry point, ServerConfig, createMcpServer()
  auth.ts                MSAL auth: browser-only login (Authenticator interface)
  browser.ts             Cross-platform openBrowser() utility (delegates to the `open` package; see ADR-0011)
  config.ts              Config struct, load/save (atomic via temp+rename), configDir()
  logger.ts              Structured logger with level filtering (debug/info/warn/error)
  loopback.ts            Custom MSAL loopback client - branded login landing page + success page
  picker.ts              Generic browser picker - local HTTP server with clickable options
  graph/
    client.ts            Lightweight HTTP client (native fetch, no Graph SDK), GraphRequestError
    types.ts             TypeScript interfaces for Graph API entities
    mail.ts              getMe, sendMail
    todo.ts              TodoList/TodoItem CRUD + checklist items + pagination ($top/$skip)
  templates/
    layout.ts            Shared HTML shell (doctype, head, fonts, favicon)
    tokens.ts            Design tokens (colors, fonts, spacing)
    styles.ts            CSS built from design tokens
    icons.ts             Base64-encoded icon assets
    login.ts             Login landing, success, and error page templates
    logout.ts            Logout confirmation page template
    picker.ts            Browser picker page template
  tools/
    login.ts             login and logout MCP tools (browser-only)
    mail.ts              mail_send MCP tool registration
    todo.ts              todo_list, todo_show, todo_create, todo_update, todo_complete, todo_delete + step tools
    config.ts            todo_select_list MCP tool (human-only list selection via browser picker)
    status.ts            auth_status MCP tool (authentication state + config info)
test/
  helpers.ts             createTestEnv() - standardized test setup
  mock-graph.ts          MockState class + in-memory Graph API server (node:http)
  mock-auth.ts           MockAuthenticator - controllable auth state for tests
  config.test.ts         Config persistence unit tests
  loopback.test.ts       Custom loopback client tests (landing page, redirect, auth code, success/error)
  picker.test.ts         Browser picker unit tests (HTML, selection, timeout, XSS, onSelect errors)
  integration/           Full e2e: in-process MCP server + real Client + mock Graph API
  graph/
    client.test.ts       GraphClient + GraphRequestError tests
    mail.test.ts         Mail operation tests
    todo.test.ts         Todo CRUD + checklist item + enhanced field tests
  templates/             Template unit tests (structure, tokens, XSS escaping, favicon)

Read the full file on GitHub · 272 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. yesterday First seen · 272 lines · 4,416 tokens per session scan A b00395d732d1

Subscribe to this mod's changes

graphdo-ts AGENTS.md is an instructions file published in the GitHub repository co-native-ab/graphdo-ts (1 stars, last pushed 11d ago), licensed MIT. It adds 4,416 tokens to every session, about $0.0221 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

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 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

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 · 5,182 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 · 4,345 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

next.js 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