autonomous-agent-patterns — quality + safety report

In the Skillier index (antigravity__autonomous-agent-patterns) · scanned 2026-06-03 · engine: builtin+triage

A
Quality
92/100
Safety

5 heuristic flags to review

Heuristic flags from the builtin scanner, which is known to over-flag (it trips on legitimate env-reading integrations, security skills, and library .eval calls). This is NOT an authoritative malicious verdict — re-scan with SkillSpector for the authoritative result. Run the authoritative scan →

Skillproof quality grade A

📇 This skill is in the Skillier index (curated · deduped · quality-filtered). Install Skillier to route & load it into your AI client.

Quality notes

Skill is large (~5620 tokens)
medium · quality · body
→ Tighten to the essential procedure; move long reference material to linked files.

About this skill

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

📄 Read the SKILL.md
---
name: autonomous-agent-patterns
description: "Design patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex)."
risk: critical
source: community
date_added: "2026-02-27"
---

# 🕹️ 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

### 1.1 Agent Loop

```
┌─────────────────────────────────────────────────────────────┐
│                     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:
                lines = f.readlines()

            if start_line and end_line:
                lines = lines[start_line-1:end_line]

            return ToolResult(
                success=True,
                output="".join(lines)
            )
        except FileNotFoundError:
            return ToolResult(
                success=False,
                error=f"File not found: {path}"
            )
```

### 2.2 Essential Agent Tools

```python
CODING_AGENT_TOOLS = {
    # File operations
    "read_file": "Read file contents",
    "write_file": "Create or overwrite a file",
    "edit_file": "Make targeted edits to a file",
    "list_directory": "List files and folders",
    "search_files": "Search for files by pattern",

    # Code understanding
    "search_code": "Search for code patterns (grep)",
    "get_definition": "Find function/class definition",
    "get_references": "Find all references to a symbol",

    # Terminal
    "run_command": "Execute a shell command",
    "read_output": "Read command output",
    "send_input": "Send input to running command",

    # Browser (optional)
    "open_browser": "Open URL in browser",
    "click_element": "Click on page element",
    "type_text": "Type text into input",
    "screenshot": "Capture screenshot",

    # Context
    "ask_user": "Ask the user a question",
    "search_web": "Search the web for information"
}
```

### 2.3 Edit Tool Design

```python
class EditFileTool(Tool):
    """
    Precise file editing with conflict detection.
    Uses search/replace pattern for reliable edits.
    """

    name = "edit_file"
    description = "Edit a file by replacing specific content"

    def execute(
        self,
        path: str,
        search: str,
        replace: str,
        expected_occurrences: int = 1
    ) -> ToolResult:
        """
        Args:
            path: File to edit
            search: Exact text to find (must match exactly, including whitespace)
            replace: Text to replace with
            expected_occurrences: How many times search should appear (validation)
        """
        with open(path, 'r') as f:
            content = f.read()

        # Validate
        actual_occurrences = content.count(search)
        if actual_occurrences != expected_occurrences:
            return ToolResult(
                success=False,
                error=f"Expected {expected_occurrences} occurrences, found {actual_occurrences}"
            )

        if actual_occurrences == 0:
            return ToolResult(
                success=False,
                error="Search text not found in file"
            )

        # Apply edit
        new_content = content.replace(search, replace)

        with open(path, 'w') as f:
            f.write(new_content)

        return ToolResult(
            success=True,
            output=f"Replaced {actual_occurrences} occurrence(s)"
        )
```

---

## 3. Permission & Safety Patterns

### 3.1 Permission Levels

```python
class PermissionLevel(Enum):
    # Fully automatic - no user approval needed
    AUTO = "auto"

    # Ask once per session
    ASK_ONCE = "ask_once"

    # Ask every time
    ASK_EACH = "ask_each"

    # Never allow
    NEVER = "never"

PERMISSION_CONFIG = {
    # Low risk - can auto-approve
    "read_file": PermissionLevel.AUTO,
    "list_directory": PermissionLevel.AUTO,
    "search_code": PermissionLevel.AUTO,

    # Medium risk - ask once
    "write_file": PermissionLevel.ASK_ONCE,
    "edit_file": PermissionLevel.ASK_ONCE,

    # High risk - ask each time
    "run_command": PermissionLevel.ASK_EACH,
    "delete_file": PermissionLevel.ASK_EACH,

    # Dangerous - never auto-approve
    "sudo_command": PermissionLevel.NEVER,
    "format_disk": PermissionLevel.NEVER
}
```

### 3.2 Approval UI Pattern

```python
class ApprovalManager:
    def __init__(self, ui, config):
        self.ui = ui
        self.config = config
        self.session_approvals = {}

    def request_approval(self, tool_name: str, args: dict) -> bool:
        level = self.config.get(tool_name, PermissionLevel.ASK_EACH)

        if level == PermissionLevel.AUTO:
            return True

        if level == PermissionLevel.NEVER:
            self.ui.show_error(f"Tool '{tool_name}' is not allowed")
            return False

        if level == PermissionLevel.ASK_ONCE:
            if tool_name in self.session_approvals:
                return self.session_approvals[tool_name]

        # Show approval dialog
        approved = self.ui.show_approval_dialog(
            tool=tool_name,
            args=args,
            risk_level=self._assess_risk(tool_name, args)
        )

        if level == PermissionLevel.ASK_ONCE:
            self.session_approvals[tool_name] = approved

        return approved

    def _assess_risk(self, tool_name: str, args: dict) -> str:
        """Analyze specific call for risk level"""
        if tool_name == "run_command":
            cmd = args.get("command", "")
            if any(danger in cmd for danger in ["rm -rf", "sudo", "chmod"]):
                return "HIGH"
        return "MEDIUM"
```

### 3.3 Sandboxing

```python
class SandboxedExecution:
    """
    Execute code/commands in isolated environment
    """

    def __init__(self, workspace_dir: str):
        self.workspace = workspace_dir
        self.allowed_commands = ["npm", "python", "node", "git", "ls", "cat"]
        self.blocked_paths = ["/etc", "/usr", "/bin", os.path.expanduser("~")]

    def validate_path(self, path: str) -> bool:
        """Ensure path is within workspace"""
        real_path = os.path.realpath(path)
        workspace_real = os.path.realpath(self.workspace)
        return real_path.startswith(workspace_real)

    def validate_command(self, command: str) -> bool:
        """Check if command is allowed"""
        cmd_parts = shlex.split(command)
        if not cmd_parts:
            return False

        base_cmd = cmd_parts[0]
        return base_cmd in self.allowed_commands

    def execute_sandboxed(self, command: str) -> ToolResult:
        if not self.validate_command(command):
            return ToolResult(
                success=False,
                error=f"Command not allowed: {command}"
            )

        # Execute in isolated environment
        result = subprocess.run(
            command,
            shell=True,
            cwd=self.workspace,
            capture_output=True,
            timeout=30,
            env={
                **os.environ,
                "HOME": self.workspace,  # Isolate home directory
            }
        )

        return ToolResult(
            success=result.returncode == 0,
            output=result.stdout.decode(),
            error=result.stderr.d

… (truncated)
Scan or optimize your own skill →

Want a live grade + an embeddable README badge? Run your skill through the free scanner.

Graded independently by Skillproof — nothing to sell the author. Quality is mechanical + corpus-grounded; safety flags are heuristic (builtin+triage), not a malicious verdict.