Agent skill

Shogun Bloom Config

by yohey-w in 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.

MITAuto-check passedAI & LLM Engineering

Install Shogun Bloom Config

skills CLI

$ npx skills add yohey-w/multi-agent-shogun --skill shogun-bloom-config -a claude-code

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

GitHub CLI

$ gh skill install yohey-w/multi-agent-shogun shogun-bloom-config --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-bloom-config .claude/skills/shogun-bloom-config && 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/

Paste into Claude Code

Install the "shogun-bloom-config" agent skill from https://github.com/yohey-w/multi-agent-shogun/tree/main/skills/shogun-bloom-config into .claude/skills/shogun-bloom-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shogun-bloom-config", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/yohey-w/multi-agent-shogun/tree/main/skills/shogun-bloom-config

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add yohey-w/multi-agent-shogun --skill shogun-bloom-config -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install yohey-w/multi-agent-shogun shogun-bloom-config --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yohey-w/multi-agent-shogun.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/shogun-bloom-config .agents/skills/shogun-bloom-config && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "shogun-bloom-config" agent skill from https://github.com/yohey-w/multi-agent-shogun/tree/main/skills/shogun-bloom-config into .agents/skills/shogun-bloom-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shogun-bloom-config", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add yohey-w/multi-agent-shogun --skill shogun-bloom-config -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install yohey-w/multi-agent-shogun shogun-bloom-config --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yohey-w/multi-agent-shogun.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/shogun-bloom-config .cursor/skills/shogun-bloom-config && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "shogun-bloom-config" agent skill from https://github.com/yohey-w/multi-agent-shogun/tree/main/skills/shogun-bloom-config into .cursor/skills/shogun-bloom-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shogun-bloom-config", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/yohey-w/multi-agent-shogun.git --path skills/shogun-bloom-config

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add yohey-w/multi-agent-shogun --skill shogun-bloom-config -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install yohey-w/multi-agent-shogun shogun-bloom-config --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yohey-w/multi-agent-shogun.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/shogun-bloom-config .gemini/skills/shogun-bloom-config && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "shogun-bloom-config" agent skill from https://github.com/yohey-w/multi-agent-shogun/tree/main/skills/shogun-bloom-config into .gemini/skills/shogun-bloom-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shogun-bloom-config", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install yohey-w/multi-agent-shogun shogun-bloom-config

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add yohey-w/multi-agent-shogun --skill shogun-bloom-config -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/yohey-w/multi-agent-shogun.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/shogun-bloom-config .github/skills/shogun-bloom-config && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "shogun-bloom-config" agent skill from https://github.com/yohey-w/multi-agent-shogun/tree/main/skills/shogun-bloom-config into .github/skills/shogun-bloom-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shogun-bloom-config", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add yohey-w/multi-agent-shogun --skill shogun-bloom-config -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install yohey-w/multi-agent-shogun shogun-bloom-config --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yohey-w/multi-agent-shogun.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/shogun-bloom-config .opencode/skills/shogun-bloom-config && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "shogun-bloom-config" agent skill from https://github.com/yohey-w/multi-agent-shogun/tree/main/skills/shogun-bloom-config into .opencode/skills/shogun-bloom-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shogun-bloom-config", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: shogun-bloom-config
GitHub stars: 1.4k
Token cost: ~3.1k tokens
SKILL.md length: 502 words
Files: 1
Skills in repo: 8
Repo updated: Aug 6, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

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

Works in 5 steps: Q1 — Claude plan (AskUserQuestion) → Q2 — ChatGPT plan (AskUserQuestion) → 5: Q3 — Rate limit preference (両方契約の場合のみ) → …
Tasks that involve Model routing and gateways
SKILL.md covers Overview, When to Use, Instructions and Pattern A-Free — Claude Free のみ, plus 5 more sections
Calls claude

What it does

Shogun Bloom Config is an agent skill from 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. Trigger: "capabilitytiers", "bloom config", "routing setup", "set up model routing", "ルーティング設定", "capabilitytiers設定", "モデル設定", "サブスク設定", "model routing"

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Model routing and gateways and Quizzes and assessments. It works with OpenAI. 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 Model routing and gateways
Tasks that involve Quizzes and assessments

Example prompts

“capabilitytiers”
“bloom config”
“routing setup”
“/shogun-bloom-config”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Q1 — Claude plan (AskUserQuestion)
Q2 — ChatGPT plan (AskUserQuestion)
5: Q3 — Rate limit preference (両方契約の場合のみ)
Map answers to pattern
Output the matching pattern below

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 nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- claude
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 Bloom Config loads about 3.1k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 502 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~87
When it runs · the whole SKILL.md, loaded when a task matches: ~3.1k

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). 502 words, ~3,118 tokens.

Download SKILL.mdSave it as .claude/skills/shogun-bloom-config/SKILL.md (or your agent's skills folder).

name: shogun-bloom-config
description: Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capability_tiers YAML + fixed agent model assignments. Trigger: "capability_tiers", "bloom config", "routing setup", "set up model routing", "ルーティング設定", "capability_tiers設定", "モデル設定", "サブスク設定", "model routing"

/shogun-bloom-config — Bloom Routing Wizard

Overview

選択肢誘導型インタビューで2問に答えるだけで、最適な capability_tiers 設定を ready-to-paste 形式で生成する。

Output:

capability_tiers YAML → config/settings.yaml にそのまま貼り付け可
available_cost_groups 宣言
固定エージェント推奨モデル（Karo / Gunshi）
カバレッジギャップ警告（Bloom L6が対応不可の場合など）

When to Use

config/settings.yaml の初期セットアップ
サブスク追加・変更後の再設定
"capability_tiersってどう設定すればいい？"
/shogun-model-list でモデル一覧を確認した後

Instructions

IMPORTANT: Do NOT output the pattern tables directly. Always ask questions first using AskUserQuestion.

Step 1: Q1 — Claude plan (AskUserQuestion)

Call AskUserQuestion with the following:

question: "Claudeのプランを教えてください。"
header: "Claude Plan"
options:
  - label: "Max 20x ($200/月)"
    description: "Opus・Sonnet・Haiku全モデル利用可。20倍使用量。Spark Dual運用ならコレ (Recommended)"
  - label: "Max 5x ($100/月)"
    description: "同上、5倍使用量。コスト重視で十分な量なら。"
  - label: "Pro ($20/月)"
    description: "Opus・Sonnet・Haiku利用可。使用量は標準。個人利用に十分。"
  - label: "Free / なし"
    description: "SonnetとHaikuのみ（Opus不可）。L6タスクはギャップが発生する。"

Step 2: Q2 — ChatGPT plan (AskUserQuestion)

Call AskUserQuestion with the following:

question: "ChatGPT（OpenAI）のプランを教えてください。"
header: "ChatGPT Plan"
options:
  - label: "なし（Claude onlyで運用）"
    description: "Claude枠のみ。シンプル構成。足軽はHaiku4.5が主力。"
  - label: "Plus ($20/月)"
    description: "gpt-5.3-codex利用可（Spark不可）。L4まで補完できる。"
  - label: "Pro ($200/月)"
    description: "Spark(1000 tok/s, Terminal-Bench 58.4%) + gpt-5.3(77.3%)利用可。足軽7体の最強構成 (Recommended)"

Step 2.5: Q3 — Rate limit preference (両方契約の場合のみ)

Q1=Pro/Max かつ Q2=Plus または Pro の場合のみ聞く。 両方のサブスクが使える場合、同じBloomレベルをどちらのクォータで処理するか確認する。

Q3a: L3タスク（量産コード生成・テンプレート適用）の優先クォータ

Call AskUserQuestion with:

question: "L1-L3タスク（量産・テンプレート・簡単な実装）はどちらのクォータを優先しますか？"
header: "L3クォータ優先"
options:
  - label: "ChatGPT Pro (Spark / gpt-5.3) 優先 (Recommended)"
    description: "Spark 1000 tok/s で爆速処理。Claude Max枠を温存してL5-L6に集中。"
  - label: "Claude Max (Haiku 4.5) 優先"
    description: "Claude枠を均等利用。ChatGPT Pro枠を節約してL4に余裕を持たせる。"

Q3b: L4タスク（分析・コードレビュー・デバッグ）の優先クォータ — Q2=Pro の場合のみ

Call AskUserQuestion with:

question: "L4タスク（分析・デバッグ・コードレビュー）はどちらのクォータを優先しますか？"
header: "L4クォータ優先"
options:
  - label: "ChatGPT Pro (gpt-5.3-codex) 優先 (Recommended)"
    description: "Terminal-Bench 77.3%。Codex Pro枠を活用してClaude枠を温存。"
  - label: "Claude Max (Sonnet 4.6) 優先"
    description: "SWE-bench 79.6%。Claude品質でL4も処理。ChatGPT Pro枠をSparkに集中。"

これらの回答に応じて capability_tiers の max_bloom 値を調整する（下記パターンのカスタム節を参照）。

Step 3: Map answers to pattern

Claude	ChatGPT	Pattern
なし/Free	なし	A-Free
Pro/Max	なし	A
なし/Free	Plus	B
なし/Free	Pro	C
Pro/Max	Plus	D
Pro/Max	Pro	E (Full Power)

Step 4: Output the matching pattern below

Output ONLY the matching pattern. Show:

簡単な説明（なぜこの設定か）
capability_tiers YAML（コピー可能なコードブロック）
available_cost_groups
固定エージェント推奨
ギャップ警告（あれば）
次のステップ

Pattern A-Free — Claude Free のみ

Sonnet 4.6 と Haiku 4.5 が使えるが Opus 4.6 は不可。L6 タスクはL5品質で処理される。

固定エージェント

エージェント	推奨モデル	備考
Karo (家老)	`claude-sonnet-4-6`	Opusは使えないのでSonnet
Gunshi (軍師)	`claude-sonnet-4-6`	同上

`config/settings.yaml` snippet

yaml

available_cost_groups:
  - claude_max

capability_tiers:
  claude-haiku-4-5-20251001:
    max_bloom: 3       # L1-L3: $1/$5/M, SWE-bench 73.3%
    cost_group: claude_max
  claude-sonnet-4-6:
    max_bloom: 5       # L4-L5: $3/$15/M, SWE-bench 79.6%, 1M context
    cost_group: claude_max

カバレッジ

Bloom	モデル	備考
L1–L3	Haiku 4.5	速い・安い
L4–L5	Sonnet 4.6	分析・設計評価
L6	⚠️ GAP	Opus 4.6 不可。L5品質で代替処理される。

Pattern A — Claude Pro/Max のみ ($20–$200/月)

Claude Opusまで全モデル利用可。足軽はHaiku(L1-L3)→Sonnet(L4-L5)→Opus(L6)で自動ルーティング。

固定エージェント

エージェント	推奨モデル	備考
Karo (家老)	`claude-sonnet-4-6`	L4-L5オーケストレーション。Opusは過剰。
Gunshi (軍師)	`claude-opus-4-6`	L5-L6の深いQC・アーキテクチャ評価

`config/settings.yaml` snippet

yaml

available_cost_groups:
  - claude_max

capability_tiers:
  claude-haiku-4-5-20251001:
    max_bloom: 3       # L1-L3: $1/$5/M, SWE-bench 73.3% — 量産タスク主力
    cost_group: claude_max
  claude-sonnet-4-6:
    max_bloom: 5       # L4-L5: $3/$15/M, SWE-bench 79.6%, 1M context
    cost_group: claude_max
  claude-opus-4-6:
    max_bloom: 6       # L6: $5/$25/M, SWE-bench 80.8% — 真の創造タスクのみ
    cost_group: claude_max

カバレッジ

Bloom	モデル	備考
L1–L3	Haiku 4.5	SWE-bench 73.3%、Sonnet 4.5比▲4pp、コスト1/3
L4–L5	Sonnet 4.6	SWE-bench 79.6%、数学+27pt (vs Sonnet 4.5)
L6	Opus 4.6	SWE-bench 80.8%。Sonnetと1.2pp差。真のL6のみ推奨

Pattern B — ChatGPT Plus のみ ($20/月)

Spark は使えない。gpt-5.3-codex が主力。L6 ギャップあり。Claude なし構成はコスパが低い。

固定エージェント

Claude サブスクなし → Karo/Gunshi も Codex モデル使用。L6 ギャップに注意。

エージェント	推奨モデル
Karo (家老)	`gpt-5.3-codex`
Gunshi (軍師)	`gpt-5.1-codex-max`

`config/settings.yaml` snippet

yaml

available_cost_groups:
  - chatgpt_plus

capability_tiers:
  gpt-5-codex-mini:
    max_bloom: 2       # L1-L2: 軽量タスク専用
    cost_group: chatgpt_plus
  gpt-5.3-codex:
    max_bloom: 4       # L3-L4: Terminal-Bench 77.3%
    cost_group: chatgpt_plus
  gpt-5.1-codex-max:
    max_bloom: 5       # L5: 最高Codexモデル
    cost_group: chatgpt_plus

カバレッジ

Bloom	モデル	備考
L1–L2	codex-mini	最小クォータ消費
L3–L4	gpt-5.3-codex
L5	codex-max
L6	⚠️ GAP	Codex は新規創造設計タスクに不適。Claude Opus 推奨。

Pattern C — ChatGPT Pro のみ ($200/月)

Spark (1000 tok/s) 使用可。L6 ギャップは残る。Claude も加えると完全構成に。

Show full SKILL.md (196 more words)Show less

固定エージェント

エージェント	推奨モデル
Karo (家老)	`gpt-5.3-codex`
Gunshi (軍師)	`gpt-5.1-codex-max`

`config/settings.yaml` snippet

yaml

available_cost_groups:
  - chatgpt_pro

capability_tiers:
  gpt-5.3-codex-spark:
    max_bloom: 3       # L1-L3: 1000+ tok/s — 足軽7体でも余裕のスループット
    cost_group: chatgpt_pro
  gpt-5.3-codex:
    max_bloom: 4       # L4: Terminal-Bench 77.3%, 400K+ context
    cost_group: chatgpt_pro
  gpt-5.1-codex-max:
    max_bloom: 5       # L5: 最高Codex capability
    cost_group: chatgpt_pro

カバレッジ

Bloom	モデル	備考
L1–L3	Spark	Cerebras製。Codex枠と独立クォータ。
L4	gpt-5.3-codex
L5	codex-max
L6	⚠️ GAP	L6 は Claude Opus 4.6 必須。

Pattern D — Claude Pro/Max + ChatGPT Plus ($40–$220/月)

Claude が高品質担当 (L4+)。Codex Plus がL1-L4の量産をカバー。Spark 不可。

固定エージェント

エージェント	推奨モデル
Karo (家老)	`claude-sonnet-4-6`
Gunshi (軍師)	`claude-opus-4-6`

`config/settings.yaml` snippet

yaml

available_cost_groups:
  - claude_max
  - chatgpt_plus

capability_tiers:
  gpt-5-codex-mini:
    max_bloom: 2       # L1-L2: Claude枠節約。Codex Plusクォータを消費。
    cost_group: chatgpt_plus
  gpt-5.3-codex:
    max_bloom: 4       # L3-L4: Terminal-Bench 77.3%
    cost_group: chatgpt_plus
  claude-sonnet-4-6:
    max_bloom: 5       # L5: Claude品質のアーキテクチャ評価
    cost_group: claude_max
  claude-opus-4-6:
    max_bloom: 6       # L6: 創造・戦略タスク
    cost_group: claude_max

カバレッジ

Bloom	モデル	備考
L1–L2	codex-mini	Codex Plus枠を消費してClaude Max節約
L3–L4	gpt-5.3-codex
L5	Sonnet 4.6	Claude品質に切り替わる
L6	Opus 4.6

Pattern E — Claude Pro/Max + ChatGPT Pro ($220–$400/月) ⭐ Full Power

最強構成。Spark で L1-L3 を爆速処理、Claude で L4-L6 を高品質処理。月 $400（Claude Max 20x + ChatGPT Pro）で全 Bloom をフルカバー。

固定エージェント

エージェント	推奨モデル	理由
Karo (家老)	`claude-sonnet-4-6`	L4-L5オーケストレーション。SWE-bench 79.6%
Gunshi (軍師)	`claude-opus-4-6`	L5-L6深いQC。SWE-bench 80.8%

Q3a×Q3b の回答別 config

E-1: Spark優先 (L3) × Codex優先 (L4) ← デフォルト推奨

Claude Max枠をL5-L6に集中。ChatGPT Pro枠でL1-L4を高速処理。

yaml

available_cost_groups:
  - claude_max
  - chatgpt_pro

capability_tiers:
  gpt-5.3-codex-spark:
    max_bloom: 3       # L1-L3: 1000+ tok/s — ChatGPT Pro枠でL1-L3を高速処理
    cost_group: chatgpt_pro
  claude-haiku-4-5-20251001:
    max_bloom: 3       # L1-L3: Claude枠フォールバック（Spark枠切れ時に自動切替）
    cost_group: claude_max
  gpt-5.3-codex:
    max_bloom: 4       # L4: Terminal-Bench 77.3% — Codex Pro枠をL4にも活用
    cost_group: chatgpt_pro
  claude-sonnet-4-6:
    max_bloom: 5       # L5: SWE-bench 79.6%, 1M context
    cost_group: claude_max
  claude-opus-4-6:
    max_bloom: 6       # L6: SWE-bench 80.8%
    cost_group: claude_max

E-2: Spark優先 (L3) × Sonnet優先 (L4)

L4もClaude品質で処理。ChatGPT Pro枠をSparkに集中させる。

yaml

available_cost_groups:
  - claude_max
  - chatgpt_pro

capability_tiers:
  gpt-5.3-codex-spark:
    max_bloom: 3       # L1-L3: 1000+ tok/s — ChatGPT Pro枠をSparkに集中
    cost_group: chatgpt_pro
  claude-haiku-4-5-20251001:
    max_bloom: 3       # L1-L3: Claude枠フォールバック
    cost_group: claude_max
  claude-sonnet-4-6:
    max_bloom: 5       # L4-L5: SWE-bench 79.6% — L4もClaude品質
    cost_group: claude_max
  claude-opus-4-6:
    max_bloom: 6       # L6: SWE-bench 80.8%
    cost_group: claude_max

E-3: Haiku優先 (L3) × Codex優先 (L4)

L3はClaude枠で処理してChatGPT Pro枠をL4のgpt-5.3に温存する。

yaml

available_cost_groups:
  - claude_max
  - chatgpt_pro

capability_tiers:
  claude-haiku-4-5-20251001:
    max_bloom: 3       # L1-L3: SWE-bench 73.3% — Claude枠でL3を処理
    cost_group: claude_max
  gpt-5.3-codex-spark:
    max_bloom: 2       # L1-L2のみ: Sparkは補助的に使用（L3はHaikuへ）
    cost_group: chatgpt_pro
  gpt-5.3-codex:
    max_bloom: 4       # L4: Terminal-Bench 77.3% — ChatGPT Pro枠をL4に集中
    cost_group: chatgpt_pro
  claude-sonnet-4-6:
    max_bloom: 5       # L5
    cost_group: claude_max
  claude-opus-4-6:
    max_bloom: 6       # L6
    cost_group: claude_max

E-4: Haiku優先 (L3) × Sonnet優先 (L4)

L1-L5を全てClaude枠で処理。ChatGPT Pro枠は節約（Spark補助的使用のみ）。

yaml

available_cost_groups:
  - claude_max
  - chatgpt_pro

capability_tiers:
  gpt-5.3-codex-spark:
    max_bloom: 2       # L1-L2補助: Sparkで超軽量タスクのみ処理
    cost_group: chatgpt_pro
  claude-haiku-4-5-20251001:
    max_bloom: 3       # L1-L3: Claude枠で統一処理
    cost_group: claude_max
  claude-sonnet-4-6:
    max_bloom: 5       # L4-L5: Claude品質でL4も処理
    cost_group: claude_max
  claude-opus-4-6:
    max_bloom: 6       # L6
    cost_group: claude_max

カバレッジ（E-1基準）

Bloom	モデル	速度/品質
L1–L3	Spark → Haiku(フォールバック)	1000 tok/s。枠切れ時に自動切替
L4	gpt-5.3-codex	Codex Pro枠フル活用
L5	Sonnet 4.6	Claude品質。Opusとの差1.2ptで1/5価格
L6	Opus 4.6	真の創造タスクのみ投入

コスト最適化のポイント: Spark と gpt-5.3 は独立クォータ。両方を同時最大利用可能。 L5 は Opus でなく Sonnet 4.6 で十分（SWE-bench差1.2%、価格差約1.7倍: $3/$15 vs $5/$25/M）。

Step 5: 設定の適用手順

出力したYAMLの後に、以下の適用手順を必ず案内する:

1. config/settings.yaml を開く

yaml

# available_cost_groups と capability_tiers を貼り付け
available_cost_groups:
  - ...   ← ここに貼り付け

capability_tiers:
  ...:    ← ここに貼り付け

2. 固定エージェントのモデルを更新

yaml

cli:
  agents:
    karo:
      type: claude
      model: claude-sonnet-4-6     # ← Karo推奨モデルに変更
    gunshi:
      type: claude
      model: opus                  # ← Gunshi推奨モデルに変更
    ashigaru1:                     # ← 足軽はcapability_tiersに従って自動ルーティング
      type: codex                  #    CLIの種類はサブスクに合わせて設定
      model: gpt-5.3-codex-spark

3. bloom_routing の有効化（オプション）

yaml

bloom_routing: "manual"   # "off"(無効) → "manual"(手動) → "auto"(全自動)

4. 設定の検証（ターミナルで）

bash

# subscription coverage チェック（カバーできないBloomレベルを検出）
source lib/cli_adapter.sh && validate_subscription_coverage

Quick Decision Tree

Claude Pro以上を契約している?
  Yes → 固定エージェント(Shogun/Karo/Gunshi)にClaudeが使える ✓
  No  → Codexのみ。L6ギャップに注意 ⚠️

ChatGPT Pro ($200) を契約している?
  Yes → Spark (L1-L3, 1000 tok/s) + gpt-5.3 (L4) が使える ✓
  Plus ($20) → gpt-5.3 (L3-L4) のみ。Spark不可。
  なし → Claude Haikuが足軽のL1-L3を担当

Files

Just SKILL.md in skills/shogun-bloom-config of yohey-w/multi-agent-shogun.

Open the folder on GitHubat commit aff8dc8

Compare with similar skills

Shogun Bloom Config 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 Bloom Config compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Shogun Bloom Config this skillyohey-w/multi-agent-shogun	1.4k	—	~3.1k	Automated safety check: Pass	MIT	2 mo ago
Codex Model Routing Teamzjp1997720/codex-model-routing-team	158	—	~736	Automated safety check: Pass	MIT	2 mo ago
Darwinian EvolverLuciole-Studio/Misaka-Agent	171	2 repos	~2.1k	Automated safety check: Warn	MIT	3 days ago
Olore Tensorzero Latestolorehq/olore	104	—	~1.6k	Automated safety check: Pass	MIT	yesterday
LLM Routercuriositech/some_claude_skills	244	—	~1.7k	Automated safety check: Pass	MIT	1 mo ago
9Router AI Gateway Setupdecolua/9router	31k	—	~744	Automated safety check: Pass	MIT	2 days ago

Similar skills

Codex Model Routing Team
zjp1997720/codex-model-routing-team
在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team…
158 GitHub stars~736 tokensUpdated 2 mo ago
AI & LLM EngineeringAuto-check passed
Darwinian Evolver
Luciole-Studio/Misaka-Agent
Evolve prompts/regex/SQL/code with Imbue's evolution loop. An agent skill from Luciole-Studio/Misaka-Agent.
171 GitHub starsUsed in 2 repos~2.1k tokens
AI & LLM EngineeringAuto-check: warnings
Olore Tensorzero Latest
olorehq/olore
Local TensorZero documentation reference (latest). An agent skill from olorehq/olore.
104 GitHub stars~1.6k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
LLM Router
curiositech/some_claude_skills
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements.
244 GitHub stars~1.7k tokensUpdated 1 mo ago
AI & LLM EngineeringAuto-check passed
9Router AI Gateway Setup
decolua/9router
Sets up access to the 9Router AI gateway, an OpenAI-compatible REST endpoint for chat, images, speech, embeddings, web search and web fetch, and indexes its capability skills.
31k GitHub stars~744 tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
9Router Chat Completions
decolua/9router
Sends chat and code-generation requests through a 9Router gateway using OpenAI or Anthropic message formats, with streaming and auto-fallback combos.
31k GitHub stars~635 tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed

Questions about Shogun Bloom Config

What does Shogun Bloom Config do?

Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capabilitytiers YAML + fixed agent model assignments. Shogun Bloom Config is an agent skill from 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.

When should I use Shogun Bloom Config?

Shogun Bloom Config fits situations like: tasks that involve Model routing and gateways; tasks that involve Quizzes and assessments.

How do I install Shogun Bloom Config in Claude Code?

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

How do I install Shogun Bloom Config in Codex?

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

Can I use Shogun Bloom Config 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-bloom-config -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-bloom-config, .gemini/skills/shogun-bloom-config, .github/skills/shogun-bloom-config and .opencode/skills/shogun-bloom-config in your project.

What does Shogun Bloom Config need to run?

Going by SKILL.md and its folder, Shogun Bloom Config needs the command-line tools its instructions call (claude).

Does Shogun Bloom Config 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 Bloom Config 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 Bloom Config use?

Shogun Bloom Config 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 Bloom Config use?

About 3.1k tokens (SKILL.md is roughly 12k 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 Bloom Config?

Skills that share tags, products or a category with Shogun Bloom Config: Codex Model Routing Team (zjp1997720/codex-model-routing-team, 158 stars), Darwinian Evolver (Luciole-Studio/Misaka-Agent, 171 stars), Olore Tensorzero Latest (olorehq/olore, 104 stars) and LLM Router (curiositech/some_claude_skills, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Shogun Bloom Config?

yohey-w (a GitHub user) maintains it in yohey-w/multi-agent-shogun, which has 1,425 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.

Install Shogun Bloom Config

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

/shogun-bloom-config — Bloom Routing Wizard

Overview

When to Use

Instructions

Step 1: Q1 — Claude plan (AskUserQuestion)

Step 2: Q2 — ChatGPT plan (AskUserQuestion)

Step 2.5: Q3 — Rate limit preference (両方契約の場合のみ)

Q3a: L3タスク（量産コード生成・テンプレート適用）の優先クォータ

Q3b: L4タスク（分析・コードレビュー・デバッグ）の優先クォータ — Q2=Pro の場合のみ

Step 3: Map answers to pattern

Step 4: Output the matching pattern below

Pattern A-Free — Claude Free のみ

固定エージェント

config/settings.yaml snippet

カバレッジ

Pattern A — Claude Pro/Max のみ ($20–$200/月)

固定エージェント

config/settings.yaml snippet

カバレッジ

Pattern B — ChatGPT Plus のみ ($20/月)

固定エージェント

config/settings.yaml snippet

カバレッジ

Pattern C — ChatGPT Pro のみ ($200/月)

固定エージェント

config/settings.yaml snippet

カバレッジ

Pattern D — Claude Pro/Max + ChatGPT Plus ($40–$220/月)

固定エージェント

config/settings.yaml snippet

カバレッジ

Pattern E — Claude Pro/Max + ChatGPT Pro ($220–$400/月) ⭐ Full Power

固定エージェント

Q3a×Q3b の回答別 config

E-1: Spark優先 (L3) × Codex優先 (L4) ← デフォルト推奨

E-2: Spark優先 (L3) × Sonnet優先 (L4)

E-3: Haiku優先 (L3) × Codex優先 (L4)

E-4: Haiku優先 (L3) × Sonnet優先 (L4)

カバレッジ（E-1基準）

Step 5: 設定の適用手順

Quick Decision Tree

Files

Compare with similar skills

Similar skills

More from yohey-w/multi-agent-shogun

Related

Questions about Shogun Bloom Config

`config/settings.yaml` snippet

`config/settings.yaml` snippet

`config/settings.yaml` snippet

`config/settings.yaml` snippet

`config/settings.yaml` snippet