Autonomous Agent Patterns Skill for Codex

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.

6k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

505

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill autonomous-agent-patterns

What comes with it

22 204 bytes besides the instruction

sub-skills/11-agent-loop.md

sub-skills/12-multi-model-architecture.md

sub-skills/21-tool-schema.md

sub-skills/22-essential-agent-tools.md

sub-skills/23-edit-tool-design.md

sub-skills/31-permission-levels.md

sub-skills/32-approval-ui-pattern.md

sub-skills/33-sandboxing.md

sub-skills/41-browser-tool-pattern.md

sub-skills/42-visual-agent-pattern.md

sub-skills/51-context-injection-patterns.md

sub-skills/52-checkpointresume.md

sub-skills/61-mcp-server-pattern.md

sub-skills/agent-design.md

sub-skills/safety.md

sub-skills/ux.md

What it tells the agent to use

found in the instruction text

Edit edits files in place

The instruction itself

20 sections, as written by the author

🕹️ 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

🧠 Knowledge Modules (Fractal Skills)

1. 1.1 Agent Loop

2. 1.2 Multi-Model Architecture

3. 2.1 Tool Schema

4. 2.2 Essential Agent Tools

5. 2.3 Edit Tool Design

6. 3.1 Permission Levels

7. 3.2 Approval UI Pattern

8. 3.3 Sandboxing

9. 4.1 Browser Tool Pattern

10. 4.2 Visual Agent Pattern

11. 5.1 Context Injection Patterns

12. 5.2 Checkpoint/Resume

13. 6.1 MCP Server Pattern

14. Agent Design

15. Safety

16. UX

Other skills for the same job

different authors, same section of the catalogue

Autonomous Agent Patterns

Use when the user says "use the DevTools skill" or when they need help debugging a web app with Chrome DevTools MCP (UI bugs, incorrect behavior, console errors, network/API failures, or performance/lag), especially if the user seems inexperienced and needs guided, step-by-step diagnosis.

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under `src/vs/platform/browserView` and `src/vs/workbench/contrib/browserView`.

3k tokens

Cua Driver

by ThinkInAIXYZ

Drive a native macOS app via the cua-driver MCP server or CLI — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to /Applications in Finder", "click the Save button in Numbers").

EAS service (paid). Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any `eas simulator:*` commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas simulator to run/install/screenshot my app', 'I'm on Linux/Cursor and need an iOS device', 'no sim on this box / headless CI', 'let an agent click through my app and screenshot it', 'test my dev build on a remote sim with live reload', 'stream a sim to my browser' - even when they don't say 'EAS Simulator' or 'cloud'. On a host WITHOUT a local simulator (Linux, CI, cloud sandbox) it's the default; on macOS, do NOT auto-trigger for a plain 'run on the simulator' - use it only for a cloud/remote/shareable sim, an iOS version they lack, or an agent-driven session. NOT for local sims (expo run:ios, Xcode, Android Studio), EAS Build/Update, web preview, or physical devices.

12k tokens

Scrapling Skill

by daymade

Install, troubleshoot, and use Scrapling CLI to extract HTML, Markdown, or text from webpages. Use this skill whenever the user mentions Scrapling, `uv tool install scrapling`, `scrapling extract`, WeChat/mp.weixin articles, browser-backed page fetching, or needs help deciding between static and dynamic extraction.

4k tokens scripts

Goose Graphics

by gooseworks-ai

Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex). Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright.

23k tokens scripts

How to use it

Copy the folder

Take dokhacgiakhoa/autonomous-agent-patterns from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.