🕹️ Autonomous Agent Patterns
Design patterns for building autonomous coding agents, inspired by Cline and 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
1.1 Agent Loop
code
┌─────────────────────────────────────────────────────────────┐ │ AGENT LOOP │ │ │ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ │ │ Think │───▶│ Decide │───▶│ Act │ │ │ │ (Reason) │ │ (Plan) │ │ (Execute)│ │ │ └──────────┘ └──────────┘ └──────────┘ │ │ ▲ │ │ │ │ ┌──────────┐ │ │ │ └─────────│ Observe │◀─────────┘ │ │ │ (Result) │ │ │ └──────────┘ │ └─────────────────────────────────────────────────────────────┘
python
class AgentLoop:
def __init__(self, llm, tools, max_iterations=50):
self.llm = llm
self.tools = {t.name: t for t in tools}
self.max_iterations = max_iterations
self.history = []
def run(self, task: str) -> str:
self.history.append({"role": "user", "content": task})
for i in range(self.max_iterations):
# Think: Get LLM response with tool options
response = self.llm.chat(
messages=self.history,
tools=self._format_tools(),
tool_choice="auto"
)
# Decide: Check if agent wants to use a tool
if response.tool_calls:
for tool_call in response.tool_calls:
# Act: Execute the tool
result = self._execute_tool(tool_call)
# Observe: Add result to history
self.history.append({
"role": "tool",
"tool_call_id": tool_call.id,
"content": str(result)
})
else:
# No more tool calls = task complete
return response.content
return "Max iterations reached"
def _execute_tool(self, tool_call) -> Any:
tool = self.tools[tool_call.name]
args = json.loads(tool_call.arguments)
return tool.execute(**args)
1.2 Multi-Model Architecture
python
class MultiModelAgent:
"""
Use different models for different purposes:
- Fast model for planning
- Powerful model for complex reasoning
- Specialized model for code generation
"""
def __init__(self):
self.models = {
"fast": "gpt-3.5-turbo", # Quick decisions
"smart": "gpt-4-turbo", # Complex reasoning
"code": "claude-3-sonnet", # Code generation
}
def select_model(self, task_type: str) -> str:
if task_type == "planning":
return self.models["fast"]
elif task_type == "analysis":
return self.models["smart"]
elif task_type == "code":
return self.models["code"]
return self.models["smart"]
2. Tool Design Patterns
2.1 Tool Schema
python
class Tool:
"""Base class for agent tools"""
@property
def schema(self) -> dict:
"""JSON Schema for the tool"""
return {
"name": self.name,
"description": self.description,
"parameters": {
"type": "object",
"properties": self._get_parameters(),
"required": self._get_required()
}
}
def execute(self, **kwargs) -> ToolResult:
"""Execute the tool and return result"""
raise NotImplementedError
class ReadFileTool(Tool):
name = "read_file"
description = "Read the contents of a file from the filesystem"
def _get_parameters(self):
return {
"path": {
"type": "string",
"description": "Absolute path to the file"
},
"start_line": {
"type": "integer",
"description": "Line to start reading from (1-indexed)"
},
"end_line": {
"type": "integer",
"description": "Line to stop reading at (inclusive)"
}
}
def _get_required(self):
return ["path"]
def execute(self, path: str, start_line: int = None, end_line: int = None) -> ToolResult:
try:
with open(path, 'r') as f