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.
npx skills add sean-sunagaku/claude-code-plugin --skill skill-creator-teamgit clone --depth 1 https://github.com/sean-sunagaku/claude-code-pluginWrote 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/skills/sean-sunagaku/claude-code-plugin/skill-creator-team)<a href="https://agentmods.dev/skills/sean-sunagaku/claude-code-plugin/skill-creator-team"><img src="https://agentmods.dev/badge/skills/sean-sunagaku/claude-code-plugin/skill-creator-team.svg" alt="Measured on agentmods" 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 | $0.00240 | $0.01462 |
| Opus 5 | $0.00120 | $0.00731 |
| Sonnet 5 | $0.00048 | $0.00292 |
| Haiku 4.5 | $0.00024 | $0.00146 |
Grade A, and why
skill-creator-team 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 7d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator Team
4つの専門エージェントがチームで議論し、高品質なスキルを作成する。
外部リファレンス(直接読み込み)
以下のファイルはコピーではなく、実ファイルを直接 Read して参照する。
skill-creator ベストプラクティス
SKILL_CREATOR_BASE=/Users/babashunsuke/.claude/plugins/cache/anthropic-agent-skills/example-skills/1ed29a03dc85/skills/skill-creator
- ワークフローパターン:
${SKILL_CREATOR_BASE}/references/workflows.md - 出力パターン:
${SKILL_CREATOR_BASE}/references/output-patterns.md - 初期化スクリプト:
${SKILL_CREATOR_BASE}/scripts/init_skill.py - バリデーション:
${SKILL_CREATOR_BASE}/scripts/quick_validate.py - パッケージング:
${SKILL_CREATOR_BASE}/scripts/package_skill.py
既存スキル(パターン参照用)
LOCAL_SKILLS=~/.claude/skills/
PLUGIN_SKILLS=~/.claude/plugins/marketplaces/sunagaku-marketplace/
エージェントはこれらのパスから既存スキルの構造やエージェント定義を Read して参考にする。
ワークフロー
- ユーザーからスキル要件をヒアリング
- Agent Team を作成し、4エージェントを並列起動
- 2〜3ラウンドの設計・議論・フィードバック
- スキルファイル一式を
~/.claude/skills/{skill-name}/に出力 - バリデーション実行
Step 1: ヒアリング
以下を確認する(不明ならユーザーに質問):
- スキルの目的: 何を自動化・支援するスキルか
- トリガー: どんな言葉でスキルが起動すべきか
- Agent Team 構成: チームエージェント型か、単体スキルか
- 参考にすべき既存スキル: 似たパターンの既存スキルがあるか
- 出力物: レポート、コード、設定ファイル等
Step 2: チーム作成とエージェント起動
TeamCreate で skill-creator-team チームを作成。以下4エージェントを 1つのメッセージで並列に Task ツールで起動する。
| name | 役割 | 主な手段 |
|---|---|---|
skill-architect |
構造設計・要件分析・既存パターン分析 | Read, Glob |
domain-researcher |
対象ドメインのベストプラクティス調査 | WebSearch |
skill-writer |
SKILL.md・エージェント定義・リファレンス作成 | Read, Write |
quality-reviewer |
品質レビュー・ベストプラクティス準拠チェック | Read, Glob |
各エージェントは agents/ ディレクトリにサブエージェントとして定義済み。
タスク作成
TaskCreate で5つのタスクを作成:
- skill-architect: 構造設計(既存スキル分析含む)
- domain-researcher: 対象ドメインの調査
- skill-writer: スキルファイル一式の作成(タスク1,2完了後)
- quality-reviewer: 品質レビュー(タスク3完了後)
- 最終出力: バリデーション + パッケージング(タスク4完了後)
依存関係:
- タスク3:
addBlockedBy: ["1","2"] - タスク4:
addBlockedBy: ["3"] - タスク5:
addBlockedBy: ["4"]
起動設定
subagent_type: "skill-architect"
team_name: "skill-creator-team"
mode: "bypassPermissions"
run_in_background: true
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.
- 7d ago First seen · 116 lines · 240 tokens per session scan A 1e0dff66be09
skill-creator-team is a skill published in the GitHub repository sean-sunagaku/claude-code-plugin (36 stars, last pushed 1mo ago), licensed MIT. It adds 240 tokens to every session and 1,462 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…