xserver-mcp: Skill for Claude Code

.claude/skills/tdd-test-scaffold/SKILL.md

tdd-test-scaffold is a skill for Claude Code from Mink16/xserver-mcp. It costs 331 tokens per session (4,746 once invoked), scanned A, original, MIT.

A test-scaffolding workflow for adding new MCP tools with TDD, or test-driven development: writing failing tests before writing the implementation. It creates a test file with three cases, request fixtures, IDN assertions, and destructive-action checks, but does not write source code.

In plain words
What is it for?
Use it when adding a new MCP tool or new tool cases, including argument, error, internationalized-domain, or destructive-action coverage.
Why use it?
It removes the repetitive setup needed to begin the failing-test phase and keeps implementation separate from test design.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is Mink16/xserver-mcp's own configuration. It tells Claude Code how to work on xserver-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 xserver-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { <toolName>Tool } from "../../../src/tools/<domain>/<toolName>.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to Mink16/xserver-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/Mink16/xserver-mcp/main/.claude/skills/tdd-test-scaffold/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Mink16/xserver-mcp

Made for: Claude Code.

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 tdd-test-scaffold

README.md
[![agentmods](https://agentmods.dev/badge/skills/mink16/xserver-mcp/tdd-test-scaffold/github.svg)](https://agentmods.dev/skills/mink16/xserver-mcp/tdd-test-scaffold)
Your own site
<a href="https://agentmods.dev/skills/mink16/xserver-mcp/tdd-test-scaffold"><img src="https://agentmods.dev/badge/skills/mink16/xserver-mcp/tdd-test-scaffold/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 tdd-test-scaffold

Your own site · 80×15
<a href="https://agentmods.dev/skills/mink16/xserver-mcp/tdd-test-scaffold"><img src="https://agentmods.dev/badge/skills/mink16/xserver-mcp/tdd-test-scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 331 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,746 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00331 $0.04746
Opus 5 $0.00166 $0.02373
Sonnet 5 $0.00066 $0.00949
Haiku 4.5 $0.00033 $0.00475

Measured 9d ago against content hash dcf55e10578e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tdd-test-scaffold 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.

.claude/skills/tdd-test-scaffold/SKILL.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tdd-test-scaffold

xserver-mcp で新しい MCP tool を TDD で追加するとき、RED フェーズの定型作業 ——「テストファイルを作って 3 ケース書いて MSW fixture 組んで IDN アサート入れて destructive ガード確認して」—— を 1 回のやり取りで済ませるスキル。出力は tests/tools/<domain>/<toolName>.test.ts のみ。実装 (src/) は絶対に書かない。

When to use

次のいずれかに当てはまる場面で必ず起動する:

  • 新しい MCP tool を追加する (src/tools/<domain>/<tool>.ts を新設する、または tests/tools/... の新規テストファイルを書く)
  • 既存ツールにケース追加 (新しい引数・エラーケース・IDN 対応・破壊的ガード追加など)
  • ユーザーが「RED」「テスト雛形」「TDD スキャフォルド」「failing test 書いて」と言った
  • test-writer または tdd-developer サブエージェントとして RED を書き始めた

When NOT to use

  • 既存テストの refactor だけ (ファイル読み込んで直接 Edit で十分)
  • src/client/ 層の変更 (transport/retry は integration テストの責務)
  • docs/ / .claude/rules/ のみの変更

Pre-scaffold interview

スキャフォルド生成前に、以下を明確化する。ユーザーが既に与えていたら省略。複数不明なときは 1 回のメッセージにまとめて聞く。

  1. tool 名 (camelCase) — 例: createDnsRecord, deleteMailAccountBulk, updateDnsRecord
    • ファイル名 (src/tools/<domain>/<name>.ts, tests/tools/<domain>/<name>.test.ts) はこの camelCase
    • MCP 登録名 (create_dns_record など snake_case) は tool.name プロパティで指定され、describe() のラベルもこちら
  2. domain — 既存の mail / dns / server / domainVerification、または新規
  3. HTTP method + endpoint path — 例: POST /v1/server/{servername}/dns, DELETE /v1/server/{servername}/mail/{mail_account}
  4. ツール種別read (GET) / write (POST/PUT/PATCH) / destructive (DELETE) / composite (複数 primitive を内部呼び出しする高レベルツール)
  5. IDN 入力を受けるか — input に domain または mail_address を持つか

不明点は endpoint を docs/xserver-openapi.json で lookup して推測できる。

Common skeleton (全パターン共通)

installFetchMock は global fetchvi.fn() ベースのスタブに差し替える単純なモック (MSW ではない)。makeContextapiKey: "test-key", servername: "sv.example", retry.maxAttempts: 1ToolContext を返す。

import { afterEach, describe, expect, it } from "vitest";
import { <toolName>Tool } from "../../../src/tools/<domain>/<toolName>.js";
import { installFetchMock } from "../../helpers/mockFetch.js";
import { makeContext } from "../../helpers/toolContext.js";

describe("<mcp_tool_name>", () => {  // snake_case — MCP 登録名と一致
  let restore: (() => void) | undefined;
  afterEach(() => restore?.());

  // 以下に 3+ ケースを書く
});

Read the full file on GitHub · 361 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 · 361 lines · 0 tokens per session scan A dcf55e10578e

Subscribe to this mod's changes

tdd-test-scaffold is a skill published in the GitHub repository Mink16/xserver-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 331 tokens to every session and 4,746 once invoked, about $0.0017 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 skills, from other repositories

implement

Implement a specification using a TDD-oriented workflow. Extracts requirements, generates tests first, then implements to pass the tests. Includes spiral detection and acceptance gates.

Kastalien-Research/thoughtbox · 34 tokens

dev-pipeline

Issue → Explore → Plan → TDD (Red→Green→Refactor) → Benchmark → PR → Review.

kimimgo/viznoir · 68 tokens

prespec

Write the behaviour specification for a feature BEFORE implementing it, as test cases. Use whenever you are about to build a new endpoint, screen, flow, or behaviour — especially anything touching auth, sessions, tokens, lists, or pagination. Also use when asked "how should I test this", "what should this actually…

emretheus/prespec · 91 tokens

Test Driven Development

Strict Red-Green-Refactor implementation methodology for high quality, regression-free software.

ankur-gaurav161418/omniforge · 21 tokens

testing

Comprehensive software testing skill covering unit tests, integration tests, TDD/BDD, mocking strategies, and test automation across multiple languages. Use this skill when writing test cases, designing test strategies, implementing test automation, or need guidance on testing frameworks and best practices. Ideal for…

ProjAnvil/MindForge · 65 tokens

tdd

Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first, red-green-refactor, tracer bullets, integration tests, or public-interface behavior tests. Skip for docs-only, path-only rename, formatting-only, or purely mechanical chores unless explicitly…

youdotcom-oss/dx-toolkit · 63 tokens