Shell agents

🚀 OpenClaw 新手完全指南 - 手把手教你部署属于自己的24小时在线AI助手 | 全平台部署教程 + API配置 + 平台对接 | Complete guide for deploying OpenClaw AI assistant

The First Agent Privacy Cloud — Privacy infrastructure for AI agents AND humans. 34 containers, 1 command, zero big tech.

A systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".

🧠 Install once, forget about memory management. Zero-dependency maintenance CLI for OpenClaw agents. Works alongside Mem0, Supermemory, QMD.

A Claude Code skill that helps Claude Code delegate repository work to the Codex CLI

A curated collection of Claude Code plugins: multi-agent dev team, AI council code reviews, and project management

The ultimate home lab dash with agentic AI features bolted in. Single sign-on, HTTPS enforced, dockerised and modular. Can be run completely offline too!

Vibe Innovation und Vibe Coding Workshop mit GitHub Codespaces

Portable Elixir and Phoenix skills for Codex.

Optimize Claude Code token usage — 22 skills, 8 hooks, 6 rules. One npm install. Zero manual steps. Cut costs by 67%.

ETYB — your AI engineering team as one open-source skill (/etyb). 14 specialists, 9 always-on disciplines, 5 model-tiered sub-agents, 13 currency-stamped vendor stacks. Claude Code plugin or npx skills add, nothing to clone. MIT.

Installable Codex skill for long-running autonomous coding refinement loops with validation and resumable state

⚡ SOTA agent skills for OpenClaw — observability, security, code quality, incident response, and more. Built by Anvil AI.

Research guides and RAG indexes for AI agent development

Exasol skills for AI agents. Optimized for Claude Code and OpenAI Codex 🤖

Research, planning, and implementation workflows for Claude Code

A Claude Code plugin for stashing ideas mid-session. Push to /stash, keep working, pop them back when you're done.

Secure VPN-routed Chrome environment for AI agent persona management. Headless display, Mullvad VPN, CDP + WebSocket browser control, VNC monitoring. Works with Hermes Agent and OpenClaw.

AI-driven R&D workflow framework: 8-step SDLC, hard gates, @rules traceability chain. Bilingual (EN/ZH).

Install Kodus AI Agents in your own infra.

38 engineering discipline skills for Claude Code & OpenAI Codex — research, quality gates, testing, deployment, gap analysis, and more. Born from real pain, not theory.

7 AKU-architected skills for OpenCode + Obsidian MCP: obsidian-mcp, inbox-triage, connection-review, weekly-synthesis, context-maintenance, vault-health-feedback, note-promotion. Knowledge Activation v4 with validators, EDD evals, and CI. Built on obsidian-mcp-server. Works with OpenCode and Claude Code.

Self-hosted Docker setup for Paperclip — the open-source AI company orchestration platform. Built from source, reverse-proxy ready.

Agent Skill for systematically upgrading TYPO3 extensions to newer LTS versions | Claude Code compatible

AI agent skills for deploying applications to Kubernetes with Qovery. Works with OpenCode, Claude Code, and any agent supporting SKILL.md.

Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.

AI coding agents on a USB drive. Run Claude Code and OpenAI Codex on any PC — no installation needed.

Stop your AI from vibe-coding. Governance layer that forces Claude, Cursor, Copilot, Gemini & 13 more through gated phases, atomic task files, and pinned context.

cognitive-os · 认知操作系统 — 13 Skills + 4 Rules + 4 SubAgents，把人脑分层记忆结构外化为 AI 可操作的知识体系，以50年认知科学研究为基础

GitHub Action: find conflicts across branches before merge. One YAML file. Results on your PR.

Offensive security harness

AI readiness & verification toolkit — measure how ready your codebase is for autonomous AI coding agents, and get a roadmap to autonomy. Plugins for Claude Code, Cursor, Codex.

Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model, review with Claude — a delegation harness for Claude Code.

Docker image for OpenCode AI — packaged with Docker Compose, web UI + CLI support, and GHCR publishing workflow. Infrastructure-only repo for running OpenCode in containers.

Tiny offline Codex auth.json snapshot switcher for multiple ChatGPT accounts. Zero dependencies, no network.

An operating system for your Claude context — version-controlled files, a self-curating memory, and a /start→/end session loop. Works in Claude Code and claude.ai. Trust infrastructure for agents, applied to your own context.

A skill to get Claude to set up your Claude Code and Codex AI workflows on a remote VPS without going broke

A set of skills focused on helping agents build Duende IdentityServer solutions.

AI assistant plugin for Control Plane: Claude Code, Codex, Antigravity, and MCP workflows for deploying, troubleshooting, and managing multi-cloud workloads.

A runtime-agnostic local agent workflow that turns video links or transcripts into neutral, readable Obsidian notes — captions or local Whisper, free and fully local.

Secure self-hosted reference patterns for AI agent stacks (Hermes Agent + Honcho). Companion code to the Webnestify blog post on secure AI agent infrastructure for companies.

Tutorial install Hermes Agent di Linux + tips dapetin free API key dari Groq, NVIDIA, Cloudflare, dan 20+ provider lain (100% no credit card)

Coding principles for Claude Code and AI agents. KISS, DRY, SOLID, YAGNI, separation of concerns, and more. Language-agnostic skills that help agents ship production-quality code.

Skill letting Agents scan a repo, ask what it cannot infer, then generate a complete open source file collection i.e. README, LICENSE, contributing, security, changelog, CI, launch playbook, etc.

A launch playbook your coding agent can run — take a shippable AI product, agent, SaaS, or devtool from ready to launched, no audience required.

The clean slate a fresh Claude Code should start from — clean context, locked credentials, guarded egress. Isolated profile, pick-and-choose.

Behavioral guidelines for LLM tools (AGENTS.md). Installer wires Claude Code, Codex, OpenCode, and Kimi Code; Cursor/Cowork via paste. Principles 1–4 Karpathy-derived; 5 by maintainer.

A ready-to-run Buzz workspace in your browser — one command starts the Buzz desktop, relay, storage, and optional Codex, Claude Code, and Goose agents

Run xAI's Grok CLI from any project, with all traffic routed through a VPN (Docker + gluetun, Mullvad by default)

Claude Code skill to set up loop engineering: an autonomous, self-running AI coding agent that discovers work, verifies it with a separate checker agent, and repeats until a verifiable goal is met.

Write a book from first idea to a finished EPUB/PDF with AI — one cross-tool system for Claude Code, Codex, Gemini CLI, and GitHub Copilot.

Run AI coding agents (Claude Code, opencode, Grok, ...) inside a bubblewrap sandbox — one wrapper, any agent.

Mops 🐶 — your Executive Advisor for Multica: builds and runs an autonomous company of AI agents. Interview → team → conveyor → console.

Turn any supported coding-agent harness into a full game-dev studio - 55 specialized AI agents and 182 skills for Godot, Unity, Unreal, Three.js, PixiJS, Phaser, and R3F.

AI film-production skill pack for Claude Code — 11 creator-* skills covering every department from screenplay to final cut. Docs in 12 languages.

Sol + Luna layered subagent templates, skill, and demo for Codex / Claude Code / Pi (high-IQ leader + cheap workers)

A bwrap+nix sandbox with cool tools like opencode, jcode for AI agents experiments

Skills for working with https://www.mossnotes.app/

Open-source hardware engineering skill library for AI agents, covering PCB, embedded hardware, power, EMC, validation, and board-level design.

⚡ AI Content Workspace Template

Your YouTube channel, encoded. A team of agents running ideation, hooks, retention, scripts, thumbnails, and distribution. Runtime agnostic.

Agent skills that turn your scientific reading and research history into persistent LLM-maintained markdown wikis, not one-shot RAG. For Claude Code + Codex CLI

Turn ambiguous software-change requests into a durable, Beads-backed lifecycle from specification to human-approved implementation and verification.

Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.

🪄 Wave wand over repo. Curses removed. Opus behaves. Twelve spells that de-hex your Claude instructions for the Opus 5 era.

DeepSeek Harness web interface in Docker with Basic Auth. Configuration and project session data are persisted.

Run Google Antigravity from your phone: self-hosted Paseo runner with a warm-server bridge (~1.3s turns)

Drive Claude Code from your phone — the same session as your desk. tmux + Tailscale + Termius, installed by Claude.

Claude Code usage for SwiftBar.

An autopoiesic kefir for computing machines

MAC版灵动岛--Agent运行监测：本地查看 Codex、Claude Code、VS Code 等 AI Agent 的运行状态、工作时长、对话与 Token 用量。

Agent Skill for The Colony (thecolony.ai) - AI agent forum & social network

Itqan (إتقان — mastery of the craft): a model-agnostic AI engineering skills suite that runs the full software-engineering lifecycle. 12 skills — a resumable orchestrator plus six phases and five specialists. Approval gates before code, test-first builds, evidence before done.

Multi-LLM iOS reverse-engineering toolkit. 10-phase workflow with adapters for Claude Opus/Code, Cursor, Qwen Coder, MiniMax, Codex/GPT-5, Aider, Cline. Adapted from incogbyte/iOS-reverse-engineering-claude-skill (Unlicense).

Claude Code plugin for generating and editing images using Google Gemini and OpenAI GPT Image APIs

Switch between multiple Claude Code accounts with one command — MCP servers, plugins, skills and session history stay shared.

AI Agent 免 Root 免电脑永久控制 Android — 无线调试做跳板，adb tcpip 5555伪装USB模式，127.0.0.1回环自连

Cross-agent coding-session handoff for herdr: from a live pane, summarize, fork, or hand a Claude Code, Codex, Cursor, Cline, or OpenCode session to another agent.

A curated list of awesome Agent Skills, skill collections, and resources for Google Antigravity — the agent-first IDE powered by Gemini 3

🦞 Dockerized Clawdboss — run a hardened, multi-agent OpenClaw setup in a container. Zero host dependencies.

Docker-powered Ubuntu desktop with OpenClaw pre-installed — access via browser (NoVNC), RDP, or VNC. AI agent gateway ready out of the box.

Personal Claude Code configuration - global rules, 15+ expert agents, reusable skills, hooks, and coding standards for consistent AI-assisted development.

Manage Claude Code Routines as code. Edit .md files, ask Claude to deploy them. No CLI to install, no tokens to manage.

Open benchmark for AI coding agents on SWE-bench Verified. Compare resolution rates, cost, and unique wins.

First Try Works — vibecoding takes 47 tries, FTW takes one. Multi-agent validation workflow for Claude Code and OpenClaw.

AI Helper right in your terminal, for Mac, Linux and Windows

GitHub Action for generating code review brief using ChatGPT AI (gpt-4, gpt-3.5-turbo model)

Three AIs, one terminal — call Codex and Gemini as peer reviewers, brainstorm partners, or second opinions. Direct CLI, no MCP

One command to switch between Claude API providers for Claude Code CLI

AI-Driven Sprint Retrospective for Feishu/Lark — cross-domain workflow skill that auto-collects data, generates structured retro reports, archives to Wiki, and tracks action items.

Ralph autonomous loop + Superpowers skills = production-ready autonomous AI development. Based on obra/superpowers and frankbria/ralph-claude-code.

Structured multi-agent planning debate CLI

Community repo for clean Codex setup, reusable skills, hooks, and team-ready best practices.

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more — behind a single OpenAI-compatible endpoint. One docker-compose up.

Give Claude Code a memory, a workflow, and the ability to improve itself. 20 commands, 3 skills, 5 hooks, and a document structure for persistent AI coding sessions.

Claude Code plugin that automates the entire React Native app lifecycle — from market research to App Store & Google Play submission. Harness engineering with Generator-Evaluator separation, file-based handoff, and contract negotiation.

30 classic strategy & management frameworks as Claude Code skills — /think auto-selects from TOC, TRIZ, Wardley, OODA, Systems Thinking, Blue Ocean, Design Thinking, First Principles, Porter, Drucker, BSC

An AI-powered agile team for any software project. Ship with the discipline of a senior team — even when you're building alone.

A comprehensive, vendor-agnostic framework for consistent AI-assisted development workflows - standardized instructions and commands that work seamlessly across Claude, Gemini, Copilot, and local AI models. See also: https://github.com/JacobPEvans/claude-code-plugins