Borrowing it
Nothing to install: this file belongs to co-native-ab/graphdo-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/co-native-ab/graphdo-ts/main/.github/agents/tdd-green.agent.mdgit clone --depth 1 https://github.com/co-native-ab/graphdo-tsWrote 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.
[](https://agentmods.dev/agents/co-native-ab/graphdo-ts/tdd-green)<a href="https://agentmods.dev/agents/co-native-ab/graphdo-ts/tdd-green"><img src="https://agentmods.dev/badge/agents/co-native-ab/graphdo-ts/tdd-green/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.
<a href="https://agentmods.dev/agents/co-native-ab/graphdo-ts/tdd-green"><img src="https://agentmods.dev/badge/agents/co-native-ab/graphdo-ts/tdd-green.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.01228 |
| Opus 5.5 | $0.00014 | $0.00491 |
| Sonnet 5.5 | $0.00007 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
TDD Green Phase - Make Tests Pass Quickly 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD Green Phase - Make Tests Pass Quickly (graphdo-ts)
Write the minimal code necessary to make failing vitest tests pass. Resist the urge to write more than required.
Always read AGENTS.md before implementing — it defines the exact patterns all code in this project must follow.
Core Principles
- Just enough code — implement only what's needed to make the test pass
- Follow existing patterns — look at
src/graph/mail.tsorsrc/graph/todo.tsas models for Graph operations; look atsrc/tools/mail.tsorsrc/tools/todo.tsfor tool registration patterns - Minimal implementation — start simple, generalise only when forced by additional tests
- Don't modify tests — the test defines the contract; the implementation must conform to it
The graphdo-ts Implementation Patterns
Adding a Graph Operation (src/graph/)
Look at src/graph/mail.ts as the model:
import type { GraphClient } from "./client.js";
import type { SomeType } from "./types.js";
export async function getSomething(client: GraphClient, id: string): Promise<SomeType> {
const result = await client.request<SomeType>("GET", `/me/some/resource/${id}`);
return result;
}
export async function createSomething(
client: GraphClient,
data: { field: string },
): Promise<SomeType> {
return client.request<SomeType>("POST", "/me/some/resource", data);
}
Adding a Tool Registration (src/tools/)
Look at src/tools/mail.ts as the model:
import { z } from "zod";
import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { GraphClient } from "../graph/client.js";
import { AuthenticationRequiredError } from "../auth.js";
import { logger } from "../logger.js";
import type { ServerConfig } from "../index.js";
import { getSomething } from "../graph/some.js";
export function registerSomeTools(server: McpServer, config: ServerConfig): void {
server.registerTool(
"some_tool",
{
description: "Does something with the Graph API",
inputSchema: { id: z.string().min(1).describe("Resource ID") },
annotations: { readOnlyHint: true },
},
async ({ id }) => {
try {
const token = await config.authenticator.token();
const client = new GraphClient(config.graphBaseUrl, token);
const result = await getSomething(client, id);
return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }] };
} catch (error: unknown) {
const message = error instanceof Error ? error.message : String(error);
logger.error("some_tool failed", { error: message });
return { isError: true, content: [{ type: "text", text: `Error: ${message}` }] };
}
},
);
}
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.
- 1mo ago First seen · 146 lines · 35 tokens per session scan A 9fe16fc21576
TDD Green Phase - Make Tests Pass Quickly is an agent published in the GitHub repository co-native-ab/graphdo-ts (1 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,228 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.