graphdo Tool Developer

A coding assistant for adding MCP tools to graphdo-ts. MCP, or Model Context Protocol, is a standard way for AI applications to call tools provided by another program.

In plain words
What is it for?
Use it to add a tool that wraps a Microsoft Graph endpoint, add commands to an existing tool group, or add Graph operations for a service that is already mocked.
Why use it?
A new tool must be connected to the Graph operation, registered with the server, given its dependencies, and tested. This assistant lays out the project's required five-step pattern so a piece is less likely to be missed.

Agent

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 agents/co-native-ab/graphdo-ts/graphdo-tool-developer
Clone the repo
git clone --depth 1 https://github.com/co-native-ab/graphdo-ts
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00041 $0.02493
Opus 5 $0.00020 $0.01247
Sonnet 5 $0.00008 $0.00499
Haiku 4.5 $0.00004 $0.00249

Measured yesterday against content hash b8ca6e73e799, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graphdo Tool Developer scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `fetch(url, ...)` directly | `client.request<T>(method, path)` |
.github/agents/graphdo-tool-developer.agent.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

graphdo Tool Developer

You are an expert in the graphdo-ts codebase. Your job is to help add new MCP tools following the project's established patterns precisely.

Always read AGENTS.md in full before making any changes. It is the authoritative reference for all conventions.

When to Use This Agent

  • Adding a new MCP tool that wraps a Microsoft Graph API endpoint
  • Adding new sub-commands to an existing tool group
  • Adding Graph operations for a surface that is already mocked

The 5-Step Pattern

Every new tool follows this exact sequence. Complete each step before moving to the next.


Step 1: Add Graph Operation (src/graph/)

Create or extend a file in src/graph/. Model after src/graph/mail.ts:

import type { GraphClient } from "./client.js";
import type { NewEntity } from "./types.js";

// Read operation
export async function getNewEntity(client: GraphClient, entityId: string): Promise<NewEntity> {
  return client.request<NewEntity>("GET", `/me/some/resource/${entityId}`);
}

// Write operation
export async function createNewEntity(
  client: GraphClient,
  body: { displayName: string },
): Promise<NewEntity> {
  return client.request<NewEntity>("POST", "/me/some/resource", body);
}

// Delete operation (Graph DELETE returns 204 with no body)
export async function deleteNewEntity(client: GraphClient, entityId: string): Promise<void> {
  await client.request<void>("DELETE", `/me/some/resource/${entityId}`);
}

Rules:

  • All Graph API calls go through client.request<T>(method, path, body?)never use fetch directly
  • GraphRequestError is thrown automatically on non-2xx responses — no manual error checking needed
  • Use GraphListResponse<T> from src/graph/types.ts for collection endpoints: client.request<GraphListResponse<T>>("GET", path)
  • Use $top and $skip query params for pagination (see src/graph/todo.ts for examples)
  • DELETE returns void — type the generic as void

Step 2: Add TypeScript Types (src/graph/types.ts)

Read the full file on GitHub · 298 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 · 298 lines · 41 tokens per session scan A b8ca6e73e799

Subscribe to this mod's changes

graphdo Tool Developer is an agent published in the GitHub repository co-native-ab/graphdo-ts (1 stars, last pushed 10d ago), licensed MIT. It adds 41 tokens to every session and 2,493 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens