---

Overview

%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8b5cf6', 'primaryTextColor': '#fff', 'primaryBorderColor': '#7c3aed', 'lineColor': '#a78bfa', 'secondaryColor': '#ec4899', 'tertiaryColor': '#6366f1', 'noteTextColor': '#fff', 'noteBkgColor': '#8b5cf6', 'textColor': '#fff' }}}%%
mindmap
  root((🐔 Agentic Systems))
    🦄 Foundations
      Augmented LLM
      What Changed 2026
    ⚙️ Workflows
      🏎️ Baseline
      ⛓️ Chaining
      🚦 Routing
      🛤️ Parallel
      🦑 Orchestrator
      🩻 Evaluator
    🐔 Autonomous Agent
      The Alternative
      Multi-Window
    🛠️ Implementation
      🐦 Subagent
      🦴 Command
      📚 Skill
      🪝 Hook
    📜 Patterns as Code
      Check before
      Trace after

---

[!TIP] New in the 2026 edition — 🗞️ What Changed 2025-2026 (the dated map: context engineering, the multi-agent debate, the AGENTS.md · SKILL.md · MCP stack, harness engineering) and 📜 Patterns as Code (every pattern as a runnable file — checked in CI on every push, no API key needed).

_{⬆️ real capture: a repeated prompt graduates into a checked, runnable file — every pattern in this repo works this way · and three of them run a real campaign daily 🛰️}

🗺️ Navigation

🦄 Foundations The building block for everything 🦄 Augmented LLM LLM + Retrieval + Tools + Memory 🗞️ What Changed 2025-2026 Context engineering · skills/MCP stack · harness era ⚙️ Workflows Predefined orchestration — code controls the flow # Workflow Use When 0 🏎️ Baseline Simple, 1-step task 1 ⛓️ Prompt Chaining Sequential steps 2 🚦 Routing Classify & dispatch 3 🛤️ Parallelization Independent tasks 4 🦑 Orchestrator Expert delegation 5 🩻 Evaluator Quality iteration

🐔 Autonomous Agent Dynamic autonomy — LLM controls the flow Pattern Use When 🐔 Autonomous Agent Open-ended problems 🖥️ Multi-Window Cross-session state (variant) 🛠️ Implementation Claude Code components & architecture Component Location 🐦 Subagent .claude/agents/*.md 🦴 Command .claude/commands/*.md 📚 Skill .claude/skills/*/SKILL.md 🪝 Hook .claude/settings.json 🗺️ Guides & 📖 Reference Resource Description Selection Guide Choose the right pattern 📜 Patterns as Code Every pattern as a runnable, checkable file Use Cases 6 validated examples Glossary A-Z definitions Visual Standards Colors & emojis

---

Quick Decision

%%{init: {'theme': 'base', 'themeVariables': {'lineColor': '#64748b'}}}%%
flowchart LR
    START((🎯 Task)) --> DEST{Destructive?}
    DEST -->|Yes| WIZ[🧙 Wizard]
    DEST -->|No| COMP{Complex?}
    COMP -->|No| BASE[🏎️ Baseline]
    COMP -->|Yes| PRED{Predictable<br/>steps?}
    PRED -->|Yes| WORK{Need<br/>specialists?}
    PRED -->|No| AGENT[🐔 Autonomous]
    WORK -->|No| CHAIN[⛓️ Chain]
    WORK -->|Yes| ORCH[🦑 Orchestrator]

    classDef default fill:#f8fafc,stroke:#64748b,stroke-width:1px,color:#1e293b
    classDef decision fill:#fef3c7,stroke:#f59e0b,stroke-width:2px,color:#92400e
    classDef baseline fill:#64748b,stroke:#475569,stroke-width:2px,color:#ffffff
    classDef wizard fill:#14b8a6,stroke:#0d9488,stroke-width:2px,color:#ffffff
    classDef workflow fill:#8b5cf6,stroke:#7c3aed,stroke-width:2px,color:#ffffff
    classDef agent fill:#ec4899,stroke:#db2777,stroke-width:2px,color:#ffffff

    START:::decision
    DEST:::decision
    COMP:::decision
    PRED:::decision
    WORK:::decision
    BASE:::baseline
    WIZ:::wizard
    CHAIN:::workflow
    ORCH:::workflow
    AGENT:::agent

Situation	→ Use
Simple task (1 step)	🏎️ Baseline
Sequential (2-4 steps)	⛓️ Prompt Chaining
Categorize inputs	🚦 Routing
Independent subtasks	🛤️ Parallelization
Multiple specialists	🦑 Orchestrator-Workers
Quality iteration	🩻 Evaluator-Optimizer
Open-ended / unknown steps	🐔 Autonomous Agent
Destructive operations	🧙 Wizard
Long-running (>10 min)	🖥️ Multi-Window Context

---

Anthropic Taxonomy

%%{init: {'theme': 'base', 'themeVariables': {'lineColor': '#64748b'}}}%%
flowchart LR
    subgraph WORKFLOWS["⚙️ WORKFLOWS"]
        direction TB
        W1[🏎️ Baseline]
        W2[⛓️ Prompt Chaining]
        W3[🚦 Routing]
        W4[🛤️ Parallelization]
        W5[🦑 Orchestrator]
        W6[🩻 Evaluator]
    end

    subgraph AGENTS["🐔 AUTONOMOUS AGENT"]
        direction TB
        A1[🐔 The Alternative]
        A2[🖥️ Multi-Window variant]
    end

    CODE[📝 Code controls] --> WORKFLOWS
    WORKFLOWS --> LLM[🧠 LLM controls]
    LLM --> AGENTS

    classDef workflowBox fill:#ede9fe,stroke:#8b5cf6,stroke-width:2px,color:#5b21b6
    classDef agentBox fill:#fce7f3,stroke:#ec4899,stroke-width:2px,color:#9d174d
    classDef control fill:#f1f5f9,stroke:#64748b,stroke-width:1px,color:#475569

    WORKFLOWS:::workflowBox
    AGENTS:::agentBox
    CODE:::control
    LLM:::control

Key distinction: Workflows have predefined paths (code controls). Agents decide their own path (LLM controls).

---

Critical Rule

%%{init: {'theme': 'base', 'themeVariables': {'lineColor': '#64748b'}}}%%
flowchart LR
    U1[🙋‍♀️ User] -->|request| MA[🐔 Main Agent]
    MA -->|🪺 spawn| SA1[🐦 Subagent]
    MA -->|🪺 spawn| SA2[🐦 Subagent]
    SA1 -->|result| MA
    SA2 -->|result| MA
    MA -->|response| U2[💁‍♀️ User]

    SA1 x--x|"❌ CANNOT spawn"| SA3[🐦]

    classDef user fill:#6366f1,stroke:#4f46e5,stroke-width:2px,color:#ffffff
    classDef main fill:#f59e0b,stroke:#d97706,stroke-width:2px,color:#ffffff
    classDef sub fill:#ec4899,stroke:#db2777,stroke-width:2px,color:#ffffff
    classDef blocked fill:#ef4444,stroke:#dc2626,stroke-width:2px,color:#ffffff,stroke-dasharray: 5 5

    U1:::user
    U2:::user
    MA:::main
    SA1:::sub
    SA2:::sub
    SA3:::blocked

🐦 Subagents cannot spawn other 🐦 subagents. All delegation flows through 🐔 Main Agent.

---

Repository Structure

.
├── README.md                      # 🏠 You are here
│
├── foundations/                   # 🦄 Core concepts
│   └── augmented-llm.md
│
├── workflows/                     # ⚙️ Predefined orchestration
│   ├── 00-baseline.md
│   ├── 01-prompt-chaining.md
│   ├── 02-routing.md
│   ├── 03-parallelization.md
│   ├── 04-orchestrator-workers.md
│   └── 05-evaluator-optimizer.md
│
├── agents/                        # 🐔 Autonomous Agent (the alternative)
│   ├── autonomous.md              # The pattern
│   └── multi-window.md            # Variant
│
├── implementation/                # 🛠️ Claude Code specifics
│   ├── components/                # 🐦🦴📚🪝
│   └── architecture/              # 5-layer system
│
├── guides/                        # 🗺️ Selection & use cases
│   └── use-cases/                 # 6 validated examples
│
└── reference/                     # 📖 Glossary, standards

---

References

Resource	Link
Building Effective Agents	anthropic.com/engineering
Claude Code Docs	docs.anthropic.com
Agent SDK	docs.anthropic.com/agent-sdk
Anthropic Cookbook	github.com/anthropics
Agent Skills spec	agentskills.io
Agentic AI Foundation (MCP · AGENTS.md · goose)	aaif.io
Patterns as runnable files (this repo)	patterns-as-code/

---

Contributing

Contributions welcome! See CONTRIBUTING.md.

Requirements: Official sources • Code examples • Mermaid diagrams • Established format

---