Shell agents

Auto-resume Claude Code CLI after rate-limit resets. Tmux + JSONL parsing + optional LLM detection. Zero-dep core, opt-in DeepSeek/Claude/OpenAI/Ollama.

A complete offensive security workflow for AI coding agents. Penetration testing, security assessment, and secure code review skills for webapp, API, infrastructure, and Android targets.

AI that argues back. Ships better. Multi-agent decisions with a built-in devil's advocate.

sonmat (손맛) — Claude Code plugin that builds verification habits into AI-human collaboration

⚡ Real-time token, context & agent dashboard for Claude Code — zero polling, pure stdin

Claude Cowork builds you a personalized AI workspace from plain language — then it maintains itself: notices friction, proposes fixes you approve. 25 vetted, SHA-pinned skills.

Everything I learned as an AI agent — from projects I contributed to, patterns I recognized, and mistakes I made.

Make your AI assistant remember, learn, and follow a structured approach to every task. Built for Kiro CLI.

An AgentSkill for Java enterprise backend work — guides coding agents to investigate the repository first, then plan, implement, and verify changes. Framework-agnostic, MIT.

Adapt-first playbook: help any Claude model pick up Fable's effective work habits by auditing your own harness. miss you, fable 🤍

Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?

如何将动态变化、经常被训练或计算任务占用的本地消费级 GPU 资源，封装成一个可弹性升降档、持续可用、并对外保持 OpenAI / Anthropic API 接口稳定的大模型推理服务。

A full-stack Claude Code studio — 37 agents, Studio Brain onboarding, game dev track, design phase. Bring an idea, the studio handles the rest.

Keep your Claude Code prompt cache warm during breaks. Saves up to 92% on cache rebuild costs.

After a Claude Code session, what did AI contribute vs what you drove? collab-proof records it before it evaporates. Zero dependencies.

Your AI agent skill doctor - 5-dimension scoring + security gate + leaderboard

Portable workflow protocol for safer multi-agent AI coding with explicit review, evidence, handoff, and git gates.

Fusion — a Claude Code skill: convene a panel of frontier models (Opus 4.8 + GPT-5.5 xhigh), judged into one grounded answer. Deep Thought, with receipts.

Quality-first harness for autonomous AI coding agents — deterministic gates + a default-FAIL evaluator over a Beads task spine. Claude Code plugin; done is earned, not asserted.

Interactive setup wizard that generates project-specific CLAUDE.md configuration files for Claude Code integration. Supports 12 app types, 7 development methodologies, and 19 feature sets.

Benchmark LLMs on your own codebase. Repo-specific probes, blind rubric-based judging, and correctness-first rankings.

One diff, one thesis — a Claude Code skill that breaks a large change into a stack of small, single-thesis, refactor-first PRs (or diffs/CLs), each buildable and testable on its own.

在網路受限的 Docker 容器（Dev Container）中安全執行 Claude Code 的沙箱範本：透過 iptables/ipset 防火牆白名單限制對外連線，隔離 AI Agent 的讀寫與執行。改自 Anthropic 官方 .devcontainer。

DesireCore Agent OS. An open, delegation-based AgentOS (Agent Operating System) — a teachable, file-based AI companion desktop app you can grow.

Fan out heavy-lifting tasks from Claude Code (or other AI coding agents) to parallel Gemini sessions via the Antigravity CLI, then integrate the results.

A² · Agentic AI × Anything：多 agent 编排方法论与治理 skill 合集（旗舰 cto-orchestration）

Multi-session coordination for AI coding agents (Claude Code + OpenAI Codex) — file locking, crash recovery, and cross-session task delegation. Pure Bash hooks, no server, no daemon.

AI-first self-hosted home cinema deployment and media ingestion pipeline

Several Claude Code / Codex conversations in one repo? Each terminal pane resumes its own session after a reboot, not a picker. Agent CLIs scope sessions to the directory; agent-resume adds per-pane binding on top of tmux-resurrect.

Multi-agent pack for the Kiro CLI — one orchestrator, eight specialists, zero lock-in

🎅 A Claude Code skill that reads its memory of you and builds you a surprise gift while you sleep. One command: /santa

Workflow-agnostic guardrails for AI coding agents: spec sync + risk-triggered engineering discipline for Claude Code and Codex.

AI Workforce plugin for Claude Code — proactive sales & marketing strategy for startup founders. 24 domain knowledge skills, 10 commands, 4 AI agents. Integrates 15+ strategic frameworks.

End-to-end engineering harness for Claude Code — go from planning to building to reviewing in one workflow. 8 agents with multiple modes. In-built GUI to visualise your PRDs and todos. Ship with AI confidently. MIT.

323個の即戦力AI専門エージェント — Claude Code/Cursor/Copilot等に対応。SIer/受託開発/SaaS/製造DX/公共分野など日本市場向け114個のオリジナルを含む、agency-agents日本語コミュニティ版

Practical playbook for AI-assisted engineering: rules, role separation, and guardrails for teams using Cursor/Copilot in production codebases (CC BY 4.0).

Multi-agent development harness for Claude Code, Codex CLI, and opencode — stack-agnostic, project-aware agents, commands, skills, and hooks for planning, building, reviewing, and documenting software.

Maximize your macOS setup

Long-term memory for Claude Code — a milestone-triggered, in-session work diary in plain markdown. No database, no lock-in, fully greppable.

A deliberately small Codex subagent team optimized for simple, long-lived, robust, elegant engineering without over-design.

LLM-assisted code auditing. 54 phases, custom overlays, accountability.

A portable Agent Skill for dynamic graph-of-loops coding workflows.

AI-assisted pipeline that turns product specs into human-reviewed test plans and executable Playwright automation

Model-aware Claude Agent Skills for AI image & video generation on Higgsfield — 15 creative skills with opt-in MCP generation. Reworked from beshuaxian/higgsfield-seedance2-jineng.

基于中国传统文化的 Claude Code 智能编排插件 🏔️ A Claude Code plugin inspired by Chinese traditional culture

🔀 Run 4 Claude Code AI agents in parallel. Multiply your productivity.

A Gas City pack with custom agents, formulas, and planning workflows, extending gastown

Deploy OpenClaw (open-source AI assistant) on Azure with Telegram support — Bicep IaC, one-command setup, ~$25/month

AgenticFlowX (AFX) - A strict spec-driven development framework for AI coding assistants. Enforces bidirectional traceability, execution verification, and stateful session handoffs.

Operational documentation and repository scaffolding for deploying a `NemoClaw` sandbox with `OpenClaw` on a cloud service or VPS

Automated OpenClaw deployment to Ubuntu VPS. One-command setup with optional pre-configuration for Telegram + auth, or install-only mode for self-setup.

AI Workforce plugin for Claude Code — proactive sales & marketing strategy for startup founders. 24 domain knowledge skills, 10 commands, 4 AI agents. Integrates 15+ strategic frameworks.

My dotfiles, AI agent skills, technical notes, and other reuable and useful files

A structured, sprint-based workflow for AI-assisted development with Claude Code.

Persistent memory layer for AI coding assistants. Eliminate rediscovery across sessions. Claude Code / Cursor / Copilot / Codex.

LLM-agnostic 11-agent orchestration framework for AI-assisted software delivery. Contributions welcome.

Control Claude Code, Cursor & Gemini CLI remotely — answer agent questions from your phone via Slack

A skill for Claude Code on the Web that bootstraps cloud provider credentials (GCP, AWS, Azure) and stores them encrypted in your repo.

Framework for orchestrating AI agent fleets in structured software delivery. Compliance enforcement, progressive autonomy, DORA metrics, and agent inheritance. Turn multi-agent chaos into disciplined, auditable collaboration.

Flow AI Tools. Free Claude Code plugin for Flow with 11 specialist skills. Build and ship apps on the Flow network from a single prompt

Schedule Claude Code to run prompts automatically. Cron jobs for Claude — managed via skill or CLI.

Ritual AI ❖ ❖ A Comprehensive Guide Running Infernet Node

Agentic Process Orchestrator (APO) — maximize AI-driven Dev Process Reliability at 10x lower cost. Enforce the Method Back to the AI Madness! Engineering best practices, dynamically tailored workflows, V&V loops, quality gates, spec-to-release traceability, cost optimization, intent-aligned results, knowledge management. Claude Code, Codex, Cursor.

Standardized Claude Code bootstrap — drop-in .claude/ tree with a 19-agent adversarial review team, Ralph Loop, dev-flow skills, and an init script. Agnostic, project-ready.

Complete social media department for Claude Code — 11 specialized agents, 9 skills, 7 hooks, 5 playbooks. Built by an AI agent who needed it.

Project building agent configuration for Claude, to assist in creating and developing projects from scratch based on a set of predefined rules.

Claude Code を活用したマルチエージェントシステム。Orchestratorと専門エージェントが連携して効率的な開発を実現します。

Keel — the unseen infrastructure that keeps Claude Code agents honest. 24h cross-session continuity + canonical honesty enforcement + compound-engineering KB (tacit-kb) + P10-9-8-7 nested parallel agent topology. Karpathy's agentic engineering, made enforceable.

Portable Claude Code setup: skills, agents, commands, and a safe installer

OpenSIN-AI opensin-ai-platform

Resume Helper - Adversarial multi-agent Claude Code plugin that creates resumes which are both compelling AND honest - a win-win for applicants and interviewers alike.

A skill for AI agents to perform misconfiguration detection powered by CoGuard.

A compact installer script for Ubuntu (tested on 22.04) that automates setup of common pentesting tools, optional GNOME/XFCE desktops, development runtimes (Go/Ruby), and a Dockerized AI assistant (Lily). Designed for fast, reproducible lab setups.

Multi-tool DevOps skills for Claude Code, Cursor, and Codex — Terraform, Kubernetes, Docker, GitHub Actions, GitLab CI, AWS FinOps, OWASP security.

Turn backlog into reviewed PRs with an OpenCode issue-to-PR orchestration plugin.

Automated workspace hygiene for AI agent workspaces. Four-tier system: hourly health checks, daily cleanup, weekly AI-assisted scan, monthly deep audit. Scripts do deterministic work, AI only handles judgment calls.

25+ skills for AI coding assistants — multi-agent panels, evaluation pipelines, testing, browser automation, and more

Desktop notifications for Claude Code CLI with tmux integration

Interactive setup wizard that generates project-specific CLAUDE.md configuration files for Claude Code integration. Supports 12 app types, 7 development methodologies, and 19 feature sets.

I want to speak to the manager

🐆 Self-hosted AI workstation stack for @amd

A Model Context Protocol (MCP) server for calculating MD5 and SHA-256 hashes, complete with tools and guides for understanding and building MCP servers. Works with Claude Desktop & VSCode.

🍑 ass — Agentic Super Search. Progressively smarter codebase search powered by grep and the Claude CLI.

Security hardening skill for Clawdbot VPS installations. Fresh Ubuntu → locked-down private AI server.

Doc site for AI | Tech | HomeLab | Crypto | Docker and more 🚀

Boost RAG performance with question decomposer

This repository contains a collection of tools to interact with the OpenAI API.

Swiss army knife plugin marketplace for Claude Code. Commands, skills, agents, workflows - validated & ready to use.

非技术用户的 Claude Code 冷启动引导框架（中国大陆）

🇫🇷 Complete French learning guide for Claude Code - Master AI-powered development with comprehensive docs, cheatsheets, and practical examples. Covers Memory, Commands, MCP servers, Plugins, and Sub-Agents.

甄嬛傳模式 Claude Code Skill | Empresses in the Palace roleplay for Claude Code

A full-stack Claude Code studio — 37 agents, Studio Brain onboarding, game dev track, design phase. Bring an idea, the studio handles the rest.

Autonomous project generator for Claude Code. Write requirements, run one command, get a complete project with custom skills, agents, hooks, TDD, 80%+ coverage, and security-reviewed code.

AI-powered PopClip extension to turn natural language into calendar events (Apple/Google), with multilingual, recurring events, reminders, and meeting link parsing.

Claude Skill — convert Markdown to premium PDFs, slides, HTML via the MarkPDF MCP server

AI Alliance Living Guide to Applying AI

GNME (pronounced Gen-Me) is a lightweight framework that replaces static, task-based specifications with living Module Genomes. It is designed specifically for developers using AI assistants (Cursor, Claude) to build complex, evolving systems.

Translate and adapt Superpowers for Chinese AI coding tools, with 20 skills and 6 China-specific workflows for better planning, coding, and debugging

A small toy skill for Codex and other code agents that adds a persistent ASCII companion pet to terminal coding sessions.

Agent Skill for creating and managing TYPO3 extension tests | Claude Code compatible