Agent skill · software engineering · davila7
autonomous-agent-patterns
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.
Why this skill is useful
Provides executable design patterns and code snippets for building autonomous coding agents, enhancing the AI's ability to create complex agent architectures.
What it needs
About 7k tokens when loaded. Last updated 2026-08-06. 30,138 stars on the source repository.
What this skill does
🕹️ 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 1.2 Multi-Model Architecture --- 2. Tool Design Patterns 2.1 Tool Schema 2.2 Essential Agent Tools 2.3 Edit Tool Design --- 3. Permission & Safety Patterns 3.1 Permission Levels 3.2 Approval UI Pattern 3.3 Sandboxing --- 4. Browser Automation 4.1 Browser Tool Pattern 4.2 Visual Agent Pattern --- 5. Context Management 5.1 Context Injection Patterns \n{item['content']}\n 5.2 Checkpoint/Resume python class CheckpointManager: """ Save and restore agent state for long-running tasks. """ def init(self, storagedir: str): self.storagedir = storagedir os.makedirs(storagedir, existok=True) def savecheckpoint(self, sessionid: str, state: dict) -> str: """Save current agent state""" checkpoint = { "timestamp": datetime.now().isoformat(), "sessionid": sessionid, "history": state["history"], "context": state["context"], "workspacestate": self.captureworkspace(state["workspace"]), "metadata": state.get("metadata", {}) } path = os.path.join(self.storagedir, f"{sessionid}.json") with open(path, 'w') as f: json.dump(checkpoint, f, indent=2) return path def restorecheckpoint(self, checkpointpath: str) -> dict: """Restore agent state from checkpoint""" with open(checkpointpath, 'r') as f: checkpoint = json.load(f) return { "history": checkpoint["history"], "context": checkpoint["context"], "workspace": self.restoreworkspace(checkpoint["workspacestate"]), "metadata": checkpoint["metadata"] } def captureworkspace(self, workspace: str) -> dict: """Capture relevant workspace state""" # Git sta
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills davila7/autonomous-agent-patterns