Autonomous Agent Patterns
This is a practical reference for building AI coding agents with the right architecture. It covers the core agent loop (think, decide, act, observe), tool design patterns for file operations and code understanding, and multi-model strategies for balancing speed versus reasoning power. The edit tool pattern using search/replace with occurrence validation is especially useful if you've dealt with agents making broken file modifications. Good for understanding how tools like Cline work under the hood, or if you're building your own autonomous coding assistant and need to handle permissions, browser automation, or human-in-the-loop workflows without reinventing patterns that already work.
- skills.sh installs
- 446
- GitHub stars
- 33.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davila7/claude-code-templates --skill autonomous-agent-patterns --agent claude-codeInstalls into .claude/skills of the current project.
Files
🕹️ 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
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/davila7/claude-code-templates
- Categories
- AI & Agent Building, Automation & Workflows, Design & UI/UX
- First seen
- Jun 3, 2026
More from davila7/claude-code-templates
All 618- D3 Viz445
- Manim444
- Marketing Psychology443
- Requirements Clarity442
- Frontend To Backend Requirements441
- Canvas Design439
- Nowait Reasoning Optimizer438
- Code Review Checklist437
- Prompt Caching437
- Commit435
- Vercel Deployment433
- C4 Architecture430
- Information Security Manager Iso27001428
- Mlflow427
- Statsmodels426
- Prompt Library423
- Chroma421
- Telegram Mini App420
- Pricing Strategy419
- Seo419
- Evaluating Llms Harness418
- Ml Paper Writing416
- Openalex Database416
- Workflow Automation416
Recommended
More AI & Agent Building
call-cursor-agentdotneet/claude-code-marketplaceCall cursor-agent to perform a task.446skills.sh installs
alibabacloud-rds-copilotaliyun/alibabacloud-aiops-skillsAlibaba Cloud RDS Copilot intelligent operations assistant skill. Used for RDS-related intelligent Q&A, SQL optimization, instance operations, and troubleshooti438skills.sh installs
eve-web-ui-testing-agent-browserincept5/eve-skillpacksWeb UI testing and browser automation. Use Vercel agent-browser for general apps, or the repo-pinned Playwright wrapper inside Eve Horizon. Use when tasks requi436skills.sh installs
code-review-ai-ai-reviewsickn33/antigravity-awesome-skillscode review ai ai review436skills.sh installs
chief-ai-officer-advisoralirezarezvani/claude-skillsChief AI Officer advisory for startups: model build-vs-buy decisions (API vs fine-tune vs in-house), AI risk classification under EU AI Act + US state patchwork432skills.sh installs
prompt-librarydavila7/claude-code-templatesCurated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use wh423skills.sh installs