Code agents

Ready-to-install skills and plugins for Codex, Claude Code, and AI coding agents: practical workflows for app delivery, architecture, research, design, and agent tooling.

Infrastructure access broker for AI agents — SSH & Kubernetes. Per-operation ephemeral credentials minted by a separate signer; the model never touches one. MCP stdio / HTTP+OIDC.

Chinese template for designing Multica multi-agent + skill workflows around task type, budget, models, and verification gates.

Organize cloud infrastructure context, orchestrate AI agents, and serve structured cloud data through MCP.

Local-first flight recorder for AI coding agents. Hash-chained audit trail, MITRE-mapped sequence detection, DLP. Forwards to the SIEM you already run.

Local agent orchestration for solo developers running long tasks without babysitting: fresh worker and critic cycles, files as memory, multi-task plans with git checkpoints, a live dashboard, and ChatGPT control via MCP. Runs Codex or Claude Code.

Eyes for AI coding agents 👁️ — render → perceive → report → fix → re-render. A machine-graded visual feedback loop (DOM/contrast/OCR-grounded + optional vision LLM) agents consume to self-correct before claiming done.

Product discovery workflows for Claude Code: test decision-changing assumptions and turn the evidence into independently reviewed PRDs.

Drop-in instructions, prompts, and workflows to reduce token usage across Codex, Claude Code, GitHub Copilot, Cursor, and other AI coding agents

Agent skill: make AI-written analysis/report docs easy for humans to read and share (fights AI verbosity/slop).

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.

Persistent cross-session memory for AI coding assistants. Works with Claude Code, Cursor, Windsurf, Cline, OpenClaude, and MCP-compatible editors.

A taste system for AI agents. 288 skills, 80 agents, 12 rules, and 8 hooks that turn generic AI output into work with genuine design quality. Anti-slop detection, typography craft, color systems, brand voice, product strategy, and 50+ specialized reviewers across UI, industry, platform, and content domains.

Local-first Python SDK for AI agents: Shadow DOM flatten, Action Map, SchemaSnap, form fill, security scan, MCP (64–97% token reduction)

A Next.js starter showing how to run Claude Code / Codex in safe, verified loops — plan → build → report cycles with lock files, budgets, denylists, and a human merge gate baked in.

Control Spotify from your AI Agent, easily and securely

Agent skills for Realsee Argus panorama reconstruction and editable Blender spaces. Works with Claude Code, Codex, and other agents.

Your AI agent develops firmware on its own: build, flash, stimulate real hardware, observe, fix - policy-gated MCP tools + pytest plugin.

Open-source agentic pipeline that transforms a single high-level requirement into deep discovery, EARS-compliant requirements, HLD, LLD, and a scored guardrail review — enforced by 36 enterprise rule files.

Living Docs — a AI agent skill that runs your project's documentation as a living system: constitution, ADRs, BDRs, PRDs, issues, research notes & Mermaid architecture diagrams under five no-drift governance invariants. OKF-formatted, stack-agnostic. Works with Claude Code, Cursor, Copilot, OpenCode & Pi.

MCP C++ project indexer for fast symbol, module, and source-range navigation in large C++20 codebases.

The McKinsey 7-step problem solving framework (from Conn & McLean's Bulletproof Problem Solving) as a portable Claude Code skill. Drop-in analytical rigor for AI agents.

A practical roadmap for engineers adopting advanced agentic coding workflows and dev tools.

Pocket workbench for Hermes Agent — limited FOA desk, dual decode, skills+MEMORY fabric, neural FOA. Not J-space. Not a second runtime.

Practice real coding work in the AI agent era: task challenges and AI PR review drills.

“What’s the thing?” You’d answer: “Skills that teach you how to maintain skills & repos”. Engineering Stewardship for any repository (app, library, tool), a structural governance and quality layer for agent-operated engineering repos.

Safety and contract checks for AI-generated n8n workflows

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.

Task-scoped AI coding workflow: 1 planned task → 1 GitHub issue → 1 branch → 1 PR → human review. Built on original GSD.

MCP server, CLI, and web dashboard for Ren'Py visual-novel development — inspect, drive and debug a running game from an AI agent or the browser

Personal finance tracker with AI-assisted categorization. Self-hostable Next.js + PostgreSQL + OpenAI.

Open-source AI-powered B2B outreach system — lead scoring, personalized cold emails, reply tracking & auto follow-up. Built with N8N, OpenAI, GLM-4, and Google Places API.

Codex skill that disables Responses Lite model mapping to restore hosted Web Search through OpenAI-compatible gateways.

Persian-first, machine-readable directory of free LLM APIs with quotas, OpenAI compatibility, official sources, and Iran-access evidence.

LLMForge is probably the most modern AI vulnerability lab for OWASP VulnerableApp — real-LLM-backed labs for prompt injection, LLM-orchestrated BOLA, and RAG attacks.

A proactive, local-first cognitive agent with approval-gated tools, memory, and collectors - runs on your own model API key.

本地优先的 Personal AI Learning Companion，把目标、个人知识、真实实践与可验证证据连接成一条可恢复的 Agent 执行链。

任务结束后生成老板视角的 AI 小票：费用、工作路径、SOP 与协作复盘。

AI agent that runs your manual test cases in a real browser

Robinhood CLI (MCP + API) — unofficial Robinhood API map + CLI + MCP for a real account (reads live, writes gated). The API map is the product.

Vault-native MCP server for Obsidian: let Codex, Claude Code, Hermes, and other agents read, search, and safely manage your notes.

Senior-level knowledge base: 60 cross-linked guides for designing beautiful, usable, accessible, high-converting websites — built for humans and AI agents.

Desktop app to test, inspect, and debug ACP (Agent Client Protocol) agents — a JSON-RPC protocol inspector, like MCP Inspector for ACP.

Instagram CLI for AI agents. Meta Graph API + instagrapi private API. JSON output, policy routing.

Open-source, AI-native HR & payroll OS for growing field-based companies. Multi-tenant, mobile-first, biometric attendance, multi-country payroll and OpenAPI integrations.

Bring your Diagrams to Life

Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.

Your coding agent, wired to 4,000 developers' real-world knowledge. Ask via /rombot-cli — grounded, cited answers, not web-search fluff. Claude Code, Codex, Cursor, Pi.

Skill library for Space Engineers plugin, mod and in-game script development. Usable with any "skills" compatible agentic coding harness.

Trust and verification for the skills your AI agent installs.

macOS 悬浮仪表盘：监控 OpenAI Codex 与 Claude Code 的订阅额度余额、Token 消耗与多设备趋势，支持 Touch Bar 常驻显示

Emacs integration for OpenAI Codex CLI

Native macOS notch activity for ChatGPT Codex tasks and weekly quota

BlackFlare - A native macOS menu bar app for Claude Code and Codex. Keep your Mac awake during long runs, get pinged when a session finishes or needs you, switch your defaults from the menu, and watch plan usage — all on-device.

AI-powered trading system for Polymarket prediction markets. Built on 40+ years of research using mean reversion, GPT-4o analysis, and multi-model paper trading. Live at polymarket-trading-dashboard.vercel.app

A compact macOS menu bar companion for Codex: live status icons, elapsed timers, active and unread sessions, usage indicators, and approval/input alerts.

Codex skill for whole-page imagegen PDF translation to Simplified Chinese

Path of Exile MCP Suite

Async web crawler powered by Playwright headless Chromium — JavaScript rendering, AI-powered extraction (OpenAI / Anthropic / Google), CSS rule engine with visual preview, and a full PySide6 desktop GUI. SQLite WAL crash recovery, proxy circuit breaker, RFC 9309 robots.txt, ReDoS-immune regex, 3,822 tests. pip install astrocrawl[full,gui,fast].

Lightweight, agent-friendly AI security toolkit for Node.js & TypeScript. Stop prompt injection, audio hallucinations, and RAG data scraping. Zero dependencies. MIT

ChatCut口播 · 马甲实战版｜v1.6.0 一句话稳剪与可恢复主流程

AI Agent skill for TI MSPM0 (G3507/G3519/L1306): SysConfig validation, board-aware pin safety for LCKFB Tianmengxing/Dimengxing/Dizhengxing, CCS/Keil/CMake workflows, UART debugging.

Introducing Bimo 5 (Autonomous Multi-Modal AI Agent with real-time voice, vision processing, document analysis, image generation, and web search).

Gordon is the frontier trading agent. The world's first agent harness for financial markets.

Web UI for Claude Code, Codex CLI, opencode, pi, omp, qoder, Antigravity & more AI agents. | 所有Agent的Web UI，实时监控各类 AI 编码智能体。

PPT 专家团：AI 做 PPT 不是生成问题，是工作流问题。八步流程 Claude/Codex skill——从文章、口播稿到可编辑 HTML PPT / 图片版 / PPTX，六套原创风格+风格选择器+12套免费商用字体。

Hands-free, two-way voice for your coding agent (Claude Code, Codex, Antigravity, Ollama) from your phone — free for noncommercial use, source-available, no ElevenLabs. Browser Web Speech + a tiny Node bridge over Tailscale HTTPS.

AI customer support agent with semantic search — handles Gmail, WhatsApp & web via OpenAI Agents SDK + FastAPI

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code, Copilot, Cursor, Codex, Gemini, Zed, Amp, Kiro, Junie, and opencode — pinned by digest in a lockfile. Storage is any OCI registry; there is no service to run.

Turn any website into a portable, agent-ready Open Knowledge Format (OKF) bundle — no LLM required. Crawl, sync, chat offline, and serve docs to coding agents over MCP.

MCP server: gives your AI agent the real sources, public API and KDoc of any Maven/Gradle-published Kotlin or Java library

AI agent skill for Avito Business API: manage listings, messenger chats, delivery, orders, vacancies, autoload, statistics, promotion. Works with Claude Code, Cursor, Gemini CLI, Copilot and 30+ AI agents.

Self-hosted household finance agent for couples, with Telegram chat, checked accounting mutations, and PostgreSQL-backed auditability.

Multi-Agent Coding Harness with pluggable AI-SDLC: switch sessions across claude, codex, gemini, export/share coding sessions, save tokens, multi-frontend (TUI · web · Telegram).

A flow-driven AI coding agent runtime. Write agent workflows in the .at DSL — Turing-complete, inspectable, deterministic. The LLM is one node; atman orchestrates the rest.

A curated list of AI-native products: apps and tools where the LLM is the product itself, not a bolted-on feature.

AI compliance platform that uses RAG to automatically match AI systems to state regulations, generate grounded disclosure documents, and maintain a cryptographically-signed tamper-evident audit trail.

Collaborative travel planning SaaS — plan itineraries on a map, vote on stops, and split expenses fairly.

Template for building protoLabs A2A agents on LangGraph — fork me

RxyCode is a local multi-agent for real work, not just code. 本地多智能体，能干的不只是写代码。

Autonomous software delivery on your own Claude/Codex subscriptions — durable runs, human gates, sandboxed agents. Druks is the self-hosted home for durable agent apps.

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.

Run Codex and Claude Code reliably in the background on macOS—with a native dashboard, persistent tmux sessions, local checkpoints, recovery, notifications, and closed-lid support.

A local evidence system for AI work—unifying ChatGPT, Claude, Codex, Gemini, and agent histories into one searchable, auditable archive.

MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-compatible backend — without losing the Claude Code orchestrator session.

Agent Networking Specification

Open-source continuation of Daytona — secure, elastic sandbox infrastructure for AI code execution and agent workflows. Community fork of the last AGPL-3.0 release (v0.190.0).

Session viewer for coding agents — browse, search, trace, and export Claude Code, Codex, and Grok conversations

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.

Portable, self-contained sandboxes for AI coding agents - microVMs, containers, isolation harnesses.

Private Git-backed, rollback-safe sync for AI coding resources across Codex, Claude Code, Cursor, Windsurf and OpenCode. 私有、安全、可回滚的 AI Coding 资源同步工具。

Auto consolidate all your Agent Runtimes. Share memory across your agents.Auto highly structured task analyzer.

agy-mcp: Model Context Protocol (MCP) server for Google Antigravity CLI (agy) with async supervision and completion wakes.

Praison is a production-ready framework for building multi-agent AI systems that enables intelligent agents to collaborate, reason, self-reflect, and use tools to automate tasks, with support for over 100 LLMs and flexible workflows for both code and no-code usage.

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

Claude skill: turn a script + talking-head media into a polished, creator-grade vertical 9:16 short with HyperFrames — editorial look, A-roll/B-roll cutting, eased camera moves, themed motion graphics, SFX, and a render verification gate.

TypeScript core + CLI + MCP server to automate routine interactions with Chile's tax authority (SII), for Claude Code and Claude Desktop. Unofficial.

transformers gguf fine-tuned rust coding unsloth

中文 Agent Skills 合集：194 个条目、13 个本站原创；Codex 13/13 自动触发实测，Claude Code / Cursor 待测；来源仓库定期复检，运行记录公开