---
version: 4.1.0-fractal
name: autonomous-agent-patterns
description: "Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants."
---

# 🕹️ Autonomous Agent Patterns

> Design patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).

## When to Use This Skill

Use this skill when:

- Building autonomous AI agents
- Designing tool/function calling APIs
- Implementing permission and approval systems
- Creating browser automation for agents
- Designing human-in-the-loop workflows

---

## 1. Core Agent Architecture

## 🧠 Knowledge Modules (Fractal Skills)

### 1. [1.1 Agent Loop](./sub-skills/11-agent-loop.md)
### 2. [1.2 Multi-Model Architecture](./sub-skills/12-multi-model-architecture.md)
### 3. [2.1 Tool Schema](./sub-skills/21-tool-schema.md)
### 4. [2.2 Essential Agent Tools](./sub-skills/22-essential-agent-tools.md)
### 5. [2.3 Edit Tool Design](./sub-skills/23-edit-tool-design.md)
### 6. [3.1 Permission Levels](./sub-skills/31-permission-levels.md)
### 7. [3.2 Approval UI Pattern](./sub-skills/32-approval-ui-pattern.md)
### 8. [3.3 Sandboxing](./sub-skills/33-sandboxing.md)
### 9. [4.1 Browser Tool Pattern](./sub-skills/41-browser-tool-pattern.md)
### 10. [4.2 Visual Agent Pattern](./sub-skills/42-visual-agent-pattern.md)
### 11. [5.1 Context Injection Patterns](./sub-skills/51-context-injection-patterns.md)
### 12. [5.2 Checkpoint/Resume](./sub-skills/52-checkpointresume.md)
### 13. [6.1 MCP Server Pattern](./sub-skills/61-mcp-server-pattern.md)
### 14. [Agent Design](./sub-skills/agent-design.md)
### 15. [Safety](./sub-skills/safety.md)
### 16. [UX](./sub-skills/ux.md)