Agent skill

Shogun Model Switch

by yohey-w in yohey-w/multi-agent-shogun

エージェントのCLI/モデルをライブ切替するスキル。settings.yaml更新→/exit→新CLI起動→ pane metadata更新を一発で実行。Thinking有無も制御。

MITAuto-check passed

Install Shogun Model Switch

skills CLI
$ npx skills add yohey-w/multi-agent-shogun --skill shogun-model-switch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yohey-w/multi-agent-shogun shogun-model-switch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yohey-w/multi-agent-shogun.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/shogun-model-switch .claude/skills/shogun-model-switch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
shogun-model-switch
GitHub stars
1.4k
Token cost
~1.1k tokens
SKILL.md length
175 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

エージェントのCLI/モデルをライブ切替するスキル。settings.yaml更新→/exit→新CLI起動→ pane metadata更新を一発で実行。Thinking有無も制御。

  • Works in 3 steps: config/settings.yaml の対象エージェントの… → bash scripts/switch_cli.sh で再起動 → pane border に +T の有無が反映される
  • Tasks that involve Email management
  • SKILL.md covers Overview, When to Use, Architecture and Display Name Mapping, plus 4 more sections
  • Calls bash and codex

What it does

Shogun Model Switch is an agent skill from yohey-w/multi-agent-shogun. エージェントのCLI/モデルをライブ切替するスキル。settings.yaml更新→/exit→新CLI起動→ pane metadata更新を一発で実行。Thinking有無も制御。 「モデル切替」「Sonnetにして」「Opusに変えて」「足軽全員切替」「Thinking切って」で起動。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with tmux. The repository describes itself as: Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy. The licence is MIT.

When your agent uses it

  • Tasks that involve Email management

Example prompts

  • “/shogun-model-switch”

Requirements

  • Pre-approved tools (allowed-tools): Bash(bash scripts/switch_cli.sh *), Read, Edit

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. config/settings.yaml の対象エージェントの thinking: を true / false に変更
  2. bash scripts/switch_cli.sh で再起動
  3. pane border に +T の有無が反映される

What it can do on your machine

Read from SKILL.md and the folder at commit aff8dc8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(bash scripts/switch_cli.sh *)
    • Read
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bash
    • codex

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Shogun Model Switch loads about 1.1k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 175 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yohey-w/multi-agent-shogun at commit aff8dc8, republished under its MIT licence (© yohey-w). 175 words, ~1,060 tokens.

Download SKILL.mdSave it as .claude/skills/shogun-model-switch/SKILL.md (or your agent's skills folder).
name
shogun-model-switch
description
エージェントのCLI/モデルをライブ切替するスキル。settings.yaml更新→/exit→新CLI起動→ pane metadata更新を一発で実行。Thinking有無も制御。 「モデル切替」「Sonnetにして」「Opusに変えて」「足軽全員切替」「Thinking切って」で起動。
allowed-tools
Bash(bash scripts/switch_cli.sh *), Read, Edit
argument-hint
[agent-name target-model e.g. ashigaru1 sonnet]

/model-switch - Agent CLI Live Switcher

Overview

稼働中のエージェントのCLI種別・モデル・Thinking設定をライブで切り替える。 settings.yaml → build_cli_command() → /exit → 新CLI起動 → pane metadata更新 を一貫実行。

When to Use

  • 「ashigaru3をOpusにして」「足軽全員Sonnetに切替」
  • 「モデル切替」「モデル変えて」「CLI変えて」
  • 「Thinking切って」「Thinking有効にして」
  • 「CodexからClaudeに戻して」「Sparkにして」
  • タスクの性質に応じてモデルを切り替えたいとき

Architecture

settings.yaml (source of truth)
    │
    ├─ cli.agents.{id}.type      → claude | codex | copilot | kimi
    ├─ cli.agents.{id}.model     → claude-sonnet-4-6 | claude-opus-4-6 | ...
    └─ cli.agents.{id}.thinking  → true | false
         │
         ├── build_cli_command()
         │   └─ thinking: false → "MAX_THINKING_TOKENS=0 claude --model ..."
         │   └─ thinking: true  → "claude --model ..."
         │
         └── get_model_display_name()
             └─ thinking: true  → "Sonnet+T" / "Opus+T"
             └─ thinking: false → "Sonnet" / "Opus"

Display Name Mapping

model (settings.yaml)表示名+Thinking
claude-sonnet-4-6SonnetSonnet+T
claude-opus-4-6OpusOpus+T
claude-haiku-4-5-20251001HaikuHaiku+T
gpt-5.3-codexCodex—
gpt-5.3-codex-sparkSpark—

Instructions

単体切替
bash
# settings.yaml の現在値で再起動(CLIリセットしたいだけのとき)
bash scripts/switch_cli.sh ashigaru3

# モデル変更(settings.yaml も自動更新)
bash scripts/switch_cli.sh ashigaru3 --model claude-opus-4-6

# CLI種別ごと変更(Codex → Claude)
bash scripts/switch_cli.sh ashigaru3 --type claude --model claude-sonnet-4-6

# Claude → Codex Spark
bash scripts/switch_cli.sh ashigaru5 --type codex --model gpt-5.3-codex-spark
一括切替
bash
# 全足軽をSonnetに
for i in $(seq 1 7); do
    bash scripts/switch_cli.sh ashigaru$i --type claude --model claude-sonnet-4-6
done

# 全足軽をSparkに
for i in $(seq 1 7); do
    bash scripts/switch_cli.sh ashigaru$i --type codex --model gpt-5.3-codex-spark
done

# 全エージェント(家老・軍師含む)を再起動
for agent in karo ashigaru1 ashigaru2 ashigaru3 ashigaru4 ashigaru5 ashigaru6 ashigaru7 gunshi; do
    bash scripts/switch_cli.sh "$agent"
done
Thinking 制御

settings.yaml の thinking フィールドを編集してから switch_cli.sh を実行:

yaml
# config/settings.yaml
cli:
  agents:
    ashigaru3:
      type: claude
      model: claude-opus-4-6
      thinking: false  # ← MAX_THINKING_TOKENS=0 で起動
bash
# settings.yaml 編集後に再起動
bash scripts/switch_cli.sh ashigaru3

Thinking ON/OFF の切替手順:

  1. config/settings.yaml の対象エージェントの thinking: を true / false に変更
  2. bash scripts/switch_cli.sh <agent_id> で再起動
  3. pane border に +T の有無が反映される
inbox 経由(家老からの切替)
bash
# 家老が足軽のCLIを切り替える場合
bash scripts/inbox_write.sh ashigaru3 "--type claude --model claude-opus-4-6" cli_restart karo

inbox_watcher が cli_restart type を検知し、switch_cli.sh を自動実行する。

What switch_cli.sh Does (internal)

  1. settings.yaml 更新(--type/--model 指定時のみ)
  2. 現在のCLI種別を検出(tmux pane metadata @agent_cli)
  3. CLI別の exit コマンドを送信
    • Claude: /exit + Enter
    • Codex: Escape → Ctrl-C → /exit + Enter
    • Copilot/Kimi: Ctrl-C → /exit + Enter
  4. シェルプロンプト復帰を待機(最大15秒、1秒ごとにキャプチャ)
  5. build_cli_command() で新コマンド構築
    • thinking: false → MAX_THINKING_TOKENS=0 prefix 付与
  6. tmux send-keys で新CLI起動(テキストとEnterを分離送信)
  7. pane metadata 更新: @agent_cli, @model_name

Files

ファイル役割
scripts/switch_cli.shメインスクリプト
lib/cli_adapter.shbuild_cli_command(), get_model_display_name()
config/settings.yamlエージェント設定(type, model, thinking)
scripts/inbox_watcher.shcli_restart type ハンドリング
logs/switch_cli.log実行ログ

Constraints

  • 将軍(shogun)ペインには送信しない: switch_cli.sh は multiagent セッションのペインのみ対象
  • 実行中のエージェントに注意: タスク実行中に切り替えるとデータ消失の可能性あり。idle確認してから実行
  • Codex → Claude 切替時: Codex の /exit が不安定な場合がある。Escape + Ctrl-C で確実に終了させる
  • inbox_watcher との連携: cli_restart 後、inbox_watcher の CLI_TYPE 変数も自動更新される

© yohey-w, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/shogun-model-switch of yohey-w/multi-agent-shogun.

Open the folder on GitHubat commit aff8dc8

Compare with similar skills

Shogun Model Switch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Shogun Model Switch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Shogun Model Switch this skillyohey-w/multi-agent-shogun1.4k—~1.1kAutomated safety check: PassMIT
TuiosGaurav-Gosain/tuios5k—~3.7kAutomated safety check: PassMIT
Clawteamwin4r/ClawTeam-OpenClaw1.5k—~3.1kAutomated safety check: PassMIT
Workeryangyuan-zhen/PolyWeather3151 repos~1.4kAutomated safety check: PassAGPL-3.0
Process Inboxtelegramdesktop/tdesktop33k2 repos~4.5kAutomated safety check: PassGPL-3.0
Codex Plugin QAcode-yeongyu/oh-my-openagent70k1 repos~1.9kAutomated safety check: PassCustom licence

Similar skills

  • Tuios

    Gaurav-Gosain/tuios

    Drive tuios from inside one of its panes. An agent skill from Gaurav-Gosain/tuios.

    5k GitHub stars~3.7k tokensUpdated yesterday
    MobileAuto-check passed
  • Clawteam

    win4r/ClawTeam-OpenClaw

    Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.

    1.5k GitHub stars~3.1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Worker

    yangyuan-zhen/PolyWeather

    [OMX] Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams

    315 GitHub starsUsed in 1 repo~1.4k tokens
    Productivity & AutomationAuto-check passed
  • Process Inbox

    telegramdesktop/tdesktop

    Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.

    33k GitHub starsUsed in 2 repos~4.5k tokens
    Productivity & AutomationAuto-check passed
  • Codex Plugin QA

    code-yeongyu/oh-my-openagent

    Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.

    70k GitHub starsUsed in 1 repo~1.9k tokens
    Testing & QAAuto-check passed
  • Tmux

    openclaw/openclaw

    Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.

    392k GitHub starsUsed in 2 repos~640 tokens
    Auto-check passed

More from yohey-w/multi-agent-shogun

All 8 skills in this repo
  • Shogun Screenshot

    yohey-w/multi-agent-shogun

    スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。

    1.4k GitHub stars~901 tokensUpdated 2 mo ago
    Auto-check: notes
  • Shogun Bloom Config

    yohey-w/multi-agent-shogun

    Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capabilitytiers YAML + fixed agent model assignments.

    1.4k GitHub stars~3.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Shogun Model List

    yohey-w/multi-agent-shogun

    All AI CLI tools × available models × required subscriptions × Bloom max capability.

    1.4k GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Skill Creator

    yohey-w/multi-agent-shogun

    Claude Codeスキル(SKILL.md)の設計・作成・バリデーション・レビュー. An agent skill from yohey-w/multi-agent-shogun.

    1.4k GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Shogun Readme Sync

    yohey-w/multi-agent-shogun

    README.md(英語)とREADMEja.md(日本語)の同期を確認・実行するスキル。README変更時に両言語版を必ず同時更新するために使用。「README更新」「README同期」「readme sync」で起動。

    1.4k GitHub stars~528 tokensUpdated 2 mo ago
    Auto-check passed
  • Inbox Write

    yohey-w/multi-agent-shogun

    別エージェントのinboxにメッセージを送信する。agent-to-agent通信の唯一の手段. An agent skill from yohey-w/multi-agent-shogun.

    1.4k GitHub stars~186 tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about Shogun Model Switch

What does Shogun Model Switch do?

エージェントのCLI/モデルをライブ切替するスキル。settings.yaml更新→/exit→新CLI起動→ pane metadata更新を一発で実行。Thinking有無も制御。. Shogun Model Switch is an agent skill from yohey-w/multi-agent-shogun.

When should I use Shogun Model Switch?

Shogun Model Switch fits situations like: tasks that involve Email management.

How do I install Shogun Model Switch in Claude Code?

Run `npx skills add yohey-w/multi-agent-shogun --skill shogun-model-switch -a claude-code`. Or copy the skill folder (skills/shogun-model-switch in yohey-w/multi-agent-shogun) into .claude/skills/shogun-model-switch in your project. Claude Code loads it when a task matches its description.

How do I install Shogun Model Switch in Codex?

Run `npx skills add yohey-w/multi-agent-shogun --skill shogun-model-switch -a codex`. Or copy the skill folder (skills/shogun-model-switch in yohey-w/multi-agent-shogun) into .agents/skills/shogun-model-switch in your project. Codex loads it when a task matches its description.

Can I use Shogun Model Switch in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yohey-w/multi-agent-shogun --skill shogun-model-switch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shogun-model-switch, .gemini/skills/shogun-model-switch, .github/skills/shogun-model-switch and .opencode/skills/shogun-model-switch in your project.

What does Shogun Model Switch need to run?

Going by SKILL.md and its folder, Shogun Model Switch needs the command-line tools its instructions call (bash and codex). Its frontmatter pre-approves these tools: Bash(bash scripts/switch_cli.sh *), Read, Edit.

Does Shogun Model Switch access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Shogun Model Switch safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Shogun Model Switch use?

Shogun Model Switch is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Shogun Model Switch use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Shogun Model Switch?

Skills that share tags, products or a category with Shogun Model Switch: Tuios (Gaurav-Gosain/tuios, 5k stars), Clawteam (win4r/ClawTeam-OpenClaw, 1.5k stars), Worker (yangyuan-zhen/PolyWeather, 315 stars) and Process Inbox (telegramdesktop/tdesktop, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Shogun Model Switch?

yohey-w (a GitHub user) maintains it in yohey-w/multi-agent-shogun, which has 1,423 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 6, 2026.

Source: yohey-w/multi-agent-shogun on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.