claude-code-conductor: Skill for Claude Code

.claude/skills/mcp-config/SKILL.md

mcp-config is a skill for Claude Code from satoh-y-0323/claude-code-conductor. It costs 28 tokens per session (2,665 once invoked), scanned A, original, MIT.

A project-scoped configuration helper for adding, listing, and removing MCP servers in `.claude/settings.json`. MCP servers are external tools or services that an AI coding agent can connect to.

In plain words
What is it for?
Use it to interactively register an MCP server, inspect the configured list, or remove a server from the project settings.
Why use it?
It keeps these server settings in one project file instead of leaving configuration spread across different locations.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

This is satoh-y-0323/claude-code-conductor's own configuration. It tells Claude Code how to work on claude-code-conductor 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 claude-code-conductor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to satoh-y-0323/claude-code-conductor. 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/satoh-y-0323/claude-code-conductor/main/.claude/skills/mcp-config/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/satoh-y-0323/claude-code-conductor

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 mcp-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/mcp-config/github.svg)](https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/mcp-config)
Your own site
<a href="https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/mcp-config"><img src="https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/mcp-config/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 mcp-config

Your own site · 80×15
<a href="https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/mcp-config"><img src="https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/mcp-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,665 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 $0.00028 $0.02665
Opus 5 $0.00014 $0.01333
Sonnet 5 $0.00006 $0.00533
Haiku 4.5 $0.00003 $0.00266

Measured 5d ago against content hash 84680d465a30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-config 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 5d 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/mcp-config/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-config

MCP サーバーの追加・一覧・削除を対話形式で行う。 全ての設定は .claude/settings.json のプロジェクトスコープに書き込む。

注意: Claude Code にはネイティブの /mcp コマンドが別途存在するが、それとは別物。 ネイティブ /mcp addsettings.json 以外のファイル(~/.claude/mcp.json 等)に書き込む可能性があるが、 正確な書き込み先は Claude Code のバージョン依存であり未確認(要確認)。 C3 プロジェクトでは必ずこの /mcp-config スキルを使うこと(設定の分散を防ぐため)。


Step 1: 操作を選択する

AskUserQuestion ツール:

{
  "questions": [{
    "question": "MCP サーバーに対して何をしますか?",
    "header": "操作選択",
    "options": [
      { "label": "追加する", "description": "新しい MCP サーバーを登録する" },
      { "label": "一覧を見る", "description": "登録済みの MCP サーバーを確認する" },
      { "label": "削除する", "description": "登録済みの MCP サーバーを削除する" }
    ]
  }]
}

Step 2(一覧表示)

.claude/settings.json を Read して mcpServers の内容を整形して表示する。

  • mcpServers が存在しない・空の場合: 「登録済みの MCP サーバーはありません」と表示して終了する。
  • 存在する場合: サーバー名・接続方法・URL/コマンドを一覧形式で表示して終了する。

Step 2(削除)

.claude/settings.json を Read して mcpServers の一覧を表示する。

登録がない場合: 「登録済みの MCP サーバーはありません」と表示して終了する。

AskUserQuestion ツール:

{
  "questions": [{
    "question": "削除するサーバー名を入力してください"
  }]
}

入力されたサーバー名のエントリを settings.json から Edit ツールで削除する。 削除後: 「{name} を削除しました」と表示して終了する。


Step 2(追加): 公開 or 社内を選ぶ

AskUserQuestion ツール:

{
  "questions": [{
    "question": "追加する MCP サーバーの種別を選んでください",
    "header": "サーバー種別",
    "options": [
      { "label": "公開サーバー", "description": "npm / GitHub 等で公開されているもの(例: @modelcontextprotocol/server-slack)" },
      { "label": "社内・カスタムサーバー", "description": "社内に建てられているもの・自作のもの" }
    ]
  }]
}

[公開サーバー追加フロー]

Step 3a: キーワードを入力させる

AskUserQuestion ツール:

{
  "questions": [{
    "question": "探したい MCP サーバーのキーワードや用途を入力してください(例: Slack, GitHub, Postgres)"
  }]
}

Step 4a: WebSearch で候補を調査する

WebSearch で以下のクエリで検索する:

MCP server {キーワード} model context protocol site:github.com OR site:npmjs.com OR site:mcp.so

検索結果から候補を最大 4 件抽出する。各候補につき以下を収集する:

  • サーバー名(わかりやすい表示名)
  • npm パッケージ名またはリポジトリ URL
  • 概要(1行)
  • 必要な env vars(判明している範囲で)

Read the full file on GitHub · 333 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. 5d ago First seen · 333 lines · 28 tokens per session scan A 84680d465a30

Subscribe to this mod's changes

mcp-config is a skill published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 2,665 once invoked, about $0.0001 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 2026-09-04.