multi-agent-shogun is a system that coordinates multiple AI coding command-line agents through a hierarchy of managers, strategists, and workers. Developers use it to split coding requests into parallel tasks and monitor their execution through tmux.
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 yohey-w/multi-agent-shogun --skill skill-creatorgit clone --depth 1 https://github.com/yohey-w/multi-agent-shogunWrote 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/yohey-w/multi-agent-shogun/skill-creator)<a href="https://agentmods.dev/skills/yohey-w/multi-agent-shogun/skill-creator"><img src="https://agentmods.dev/badge/skills/yohey-w/multi-agent-shogun/skill-creator/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/skills/yohey-w/multi-agent-shogun/skill-creator"><img src="https://agentmods.dev/badge/skills/yohey-w/multi-agent-shogun/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 227 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00128 | $0.03537 |
| Opus 5.5 | $0.00051 | $0.01415 |
| Sonnet 5.5 | $0.00026 | $0.00707 |
| Haiku 4.5 | $0.00013 | $0.00354 |
Grade B, and why
skill-creator scanned grade B 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 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
4. **既存スキルとの重複チェック**: `ls ~/.claude/skills/` で確認 How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator — Claude Code Skills Design & Generation v2.0
Anthropic公式 "The Complete Guide to Building Skills for Claude" (2026-03) に完全準拠。 Agent Skills Open Standard (agentskills.io) にも対応し、Claude Code以外のAIツールでも動作するスキルを設計する。
North Star
再利用可能で高品質なスキルを最短で設計・作成すること。 スキルの価値 = 発火精度 × 出力品質 × 保守性。
Frontmatter Reference（全フィールド）
---
# === 必須フィールド ===
name: skill-name # kebab-case, max 64 chars. 省略時はディレクトリ名
# "claude" / "anthropic" を含む名前は禁止（予約語）
description: | # 【最重要】発火判断の唯一の材料。1024文字以内
What + When を明記。トリガーワードを含める。
ネガティブトリガー（Do NOT use for...）で誤発火防止。
# === 任意フィールド ===
argument-hint: "[target]" # 補完時のヒント表示。引数ありスキル用
disable-model-invocation: false # true = 手動 /name でのみ起動（副作用あるスキル向け）
user-invocable: true # false = /メニュー非表示（背景知識スキル向け）
allowed-tools: Read, Grep, Bash # 許可ツール。指定すると制限にもなる。省略=全ツール継承
model: sonnet # スキル実行時のモデル指定（省略=親から継承）
context: fork # fork = サブエージェントで隔離実行
agent: general-purpose # fork時のエージェント種別: Explore, Plan, general-purpose
license: MIT # OSSスキル用。MIT, Apache-2.0 等
compatibility: | # 環境要件（1-500文字）
Claude Code + tmux + WSL2
metadata: # カスタムメタデータ
author: your-name
version: 1.0.0
mcp-server: server-name # MCP連携スキル用
hooks: # スキル内フック定義
PostToolUse:
- matcher: "Edit|Write"
hooks:
- type: command
command: "./scripts/lint.sh"
---
Frontmatter セキュリティ制約
- XML角括弧
< >禁止（プロンプトインジェクション防止） nameに "claude" / "anthropic" は使用禁止（予約語）- フロントマターはシステムプロンプト内に展開される → 悪意あるコンテンツは危険
Description設計（最重要 — 発火品質を決める）
descriptionはClaude Codeが「このスキルを使うか否か」を判断する唯一の材料。 本文は発火判定に使われない。1024文字以内。
構造: [What] + [When] + [Negative trigger]
# Good — 具体的、トリガーあり、ネガティブトリガーあり
description: |
Figmaデザインファイルを分析し、開発者向けハンドオフドキュメントを生成。
.figファイルアップロード時、「デザインスペック」「コンポーネント文書」
「デザインからコードへ」と言われた時に起動。
Do NOT use for: 一般的な画像処理やUI設計（interface-designスキルを使え）。
# Bad — 曖昧、トリガーなし
description: ドキュメント処理
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 · 275 lines · 128 tokens per session scan B 2d828dd74475
skill-creator is a skill published in the GitHub repository yohey-w/multi-agent-shogun (1,424 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 3,537 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orchestrator
Providerneutrales Protokoll zum Zerlegen komplexer Aufgaben, zum Beauftragen unabhängiger Worker und zur evidenzbasierten Abnahme ihrer Ergebnisse.
choose-your-orchestrator
Wählt vor komplexer Multi-Agent-Arbeit gemeinsam mit dem Nutzer eine passende, begrenzte Orchestrierung und erzeugt einen kompakten Session-Vertrag. Nutze den Skill bei /choose-your-orchestrator, bei unsicherer Kombination aus Orchestrator, Schwarm, Modellrouting oder Nutzerpräferenzmodell sowie vor Agentenprogrammen…
skill-agent-mapping
This skill should be used when looking up which agents own or consume specific skills, understanding skill-agent relationships, or routing tasks based on skill ownership.
agents-bridge
Skill "agents-bridge" from ellmos-ai/skills, covering agents-bridge — the lifeboat, auch: time capsule (deutsch), workflow & vorgehen and sicherheitsgrenzen.
exploration-strategy
This skill should be used when exploring codebases, finding patterns, searching for code, gathering context, or understanding code structure before planning or implementation.
team-decision
This skill should be used when deciding whether to use Agent Teams for parallel execution or sequential subagent orchestration, based on task analysis, independence criteria, and cost-benefit.