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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yohey-w/multi-agent-shogunnpx agentmods add skills/yohey-w/multi-agent-shogun/shogun-model-switchWrote 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/shogun-model-switch)<a href="https://agentmods.dev/skills/yohey-w/multi-agent-shogun/shogun-model-switch"><img src="https://agentmods.dev/badge/skills/yohey-w/multi-agent-shogun/shogun-model-switch.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
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 →
- high Excessive Agency · line 63 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 66 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 69 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 77 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 82 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00083 | $0.01707 |
| Opus 5 | $0.00042 | $0.00853 |
| Sonnet 5 | $0.00017 | $0.00341 |
| Haiku 4.5 | $0.00008 | $0.00171 |
Grade A, and why
shogun-model-switch 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 8d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/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-4-6 | Sonnet | Sonnet+T |
| claude-opus-4-6 | Opus | Opus+T |
| claude-haiku-4-5-20251001 | Haiku | Haiku+T |
| gpt-5.3-codex | Codex | — |
| gpt-5.3-codex-spark | Spark | — |
Instructions
単体切替
# 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
# 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
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.
- 8d ago First seen · 154 lines · 83 tokens per session scan A 9a67b81b5297
shogun-model-switch is a skill published in the GitHub repository yohey-w/multi-agent-shogun (1,420 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,707 once invoked, about $0.0004 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
devops-expert
Expert-level DevOps practices, culture, automation, and continuous delivery. Use when the user mentions CI/CD, automation, infrastructure, or culture, or when the task involves DevOps Culture or Culture & Process.
email-intel
Daily email intelligence processor. Scans incoming + outgoing 31C Exchange emails (via exchangelib/EWS), groups by conversation thread, categorizes for CRM actions, tasks, pipeline updates, knowledge capture, and relationship signals. Presents digest for approval before executing. Integrates with /prime for morning…
prime
Initialize a working session. Loads full workspace context (personal info, business, strategy, current data, pipeline, key contacts, datastore index), runs CRM and sync health checks, surfaces what needs attention, and lists available skills with recommendations for the day. Use at the start of every working session.…
viraid
Viraid virtual assistant -- reads new messages from M's VIRAID Telegram channel, analyzes and categorizes each message (CRM action, calendar, task, research, note), enriches with workspace context (CRM contacts, calendar policy, pipeline), proposes actions for approval, then executes (write tasks, log CRM…
radar
Manual-actions + silent-health detector. Runs scripts/ops-radar.py, which surfaces which high-consequence MANUAL actions are objectively overdue (backup, publish-to-fleet, weekly-review, cold-sweep, Odin collect/reflect) and which machine-domain states have degraded (ollama down, memory-index stale), self-healing the…
telegram
Use this skill to communicate via Telegram as Misha's personal account. Handles all Telegram messaging: send messages to contacts or groups, read conversations, check unread, search message history, forward messages between chats, reply to specific messages, send files/photos, download media, list chats/groups, view…