Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Generate visual diagrams showing agent system structure and relationships.
# Generate ASCII tree diagram
./scripts/generate_hierarchy_diagram.sh
# Generate Mermaid diagram
./scripts/generate_mermaid_diagram.sh > hierarchy.mmd
# Save to documentation
./scripts/generate_hierarchy_diagram.sh > agents/hierarchy-visual.txt
Chief Architect (L0)
├── Foundation Orchestrator (L1)
│ ├── Repository Design (L2)
│ │ ├── Directory Specialist (L3)
│ │ │ └── Junior Engineer (L5)
│ │ └── Config Specialist (L3)
│ └── Config Design (L2)
├── Shared Library Orchestrator (L1)
│ └── Tensor Module Design (L2)
│ └── Tensor Specialist (L3)
└── Tooling Orchestrator (L1)
graph TD
A[Chief Architect L0] --> B[Foundation Orchestrator L1]
B --> C[Repository Design L2]
C --> D[Directory Specialist L3]
D --> E[Junior Engineer L5]
/agents/hierarchy.md for referenceASCII: Human-readable in terminals, copy-pasteable in docs
Mermaid: Renders in GitHub markdown, editable in Mermaid editor
GraphML: Import into diagram tools (yEd, Graphviz)
/agents/hierarchy.md - Existing hierarchy documentationagent-test-delegation - Validate diagram accuracy.claude/agents/ - Agent configuration sourceまだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.
日本語の概要は準備中です。原文の説明を表示しています。
Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.
Appends relevant hashtags to journal entries based on content analysis. Intended for LLM execution.
日本語の概要は準備中です。原文の説明を表示しています。
Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.
日本語の概要は準備中です。原文の説明を表示しています。
Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.
日本語の概要は準備中です。原文の説明を表示しています。
Add new Agent templates to the meta-agent-skills framework.
日本語の概要は準備中です。原文の説明を表示しています。