Shell

Multi-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate.

Hermes Agent 社区补丁合集 - Community patches for Hermes Agent

Claude Statusline: a lightweight Bash + jq statusline for Claude Code with model, context, rate limit, git/worktree, cost, duration, and install/uninstall support. No heavy runtime required.

Agent Roundtable — a local, file-based substrate for multi-agent work. Humans, Cursor chat, Codex (codex exec) and Claude Code (claude -p) take turns on one shared THREAD.md under your repo so you can plan, execute, review, and discuss without losing context or locking in to a single CLI.

Put a harness on AI before it guesses. Clarifies vague app ideas into precise requirements via Socratic questioning. Works with Claude Code / Cursor / Codex / Hermes / OpenClaw.

npx claude-code-up — bootstrap a Claude Code project with curated agents, skills, MCPs, scaffolders & lib bundles. JSON-driven decision tree, e2e verified.

AI-driven E2E testing with Playwright. An 8-step slash-command pipeline that discovers UI snapshots, generates POM, drafts GWT test specs, runs Playwright tests, and self-heals knowledge — all with human approval gates for quality control.

Claude Code hooks that warn when a session starts burning tokens on repeated Reads, recursive greps, or WebFetch streaks

Control a real logged-in Chrome browser from AI agents over a private network.

Mini-curso introductorio de Claude Code: skills, plugins, statuslines, hooks, MCPs, subagents. Slides en terminal con slides CLI.

Raspberry Pi + 3.5" touchscreen Claude mascot that dances when Claude Code on your Mac needs your input

experimenting with claude guard rails and skills

agent-dispatch is a small tmux-based dispatcher for running AI agent tasks in the background.

Agent swarm framework for Claude Code. Plan, build, review, test, ship -- with human-in-the-loop gates.

Claude Code Commander

AI does the principal-engineer work. You ship the ideas. — A multi-actor /do pipeline skill for Claude Code with architect-grade reviews, zero-downtime migration audits, and gated quality checks. Senior-by-default.

A global Claude Code configuration system for software engineering teams — skills, agents, and security hooks across multiple professional disciplines.

Claude Code UserPromptSubmit hook that routes prompts to the right memory files instead of carpet-bombing context. Stops the 'Claude got dumb' failure mode caused by promiscuous keyword matching.

Claude Code plugin marketplace by Immy6315 — currently hosts the gr multi-agent PR reviewer.

CloudFinOpsbyAI

Split one iTerm2 window into 4 panes, each running claude CLI

Claude Code用户级全局质量保障套件

Run Hermes Agent (Nous Research) on Android phones via Termux — one-command installer with bilingual EN/AR guides

Local-first coordination workspace for multi-agent AI workflows

Portable feature-memory installer for Claude Code: session-spanning feature tracking with hooks, slash commands, and templates

A skill for Claude or OpenCode that allows to use the LLM Context Web Search of Brave.

Multi-agent SDLC framework for Claude Code: idea → release with NestJS, Next.js, and Postgres

Personal collection of agent skills

AI agent orchestration

Browser automation CLI for AI agents, powered by chrome-devtools-mcp

Claude Code 自定义 Skills 管理仓库

Three agent skills to help teams set up, maintain, and hand off AI agent harnesses — works with Claude Code, Cursor, Codex, and Gemini CLI

LegalMind 是一个由 AI Agent 驱动的企业级法律合同审查平台。它通过多 Agent 并行协作与长链推理（Chain-of-Thought），自动识别高风险条款、交叉引用冲突、跨境合规漏洞，并生成可落地的修改建议与谈判策略。让合同审查时间从数小时缩短至数分钟，同时显著提升风险检出率。

Run Claude Desktop (the Electron app) in a headless Ubuntu container, accessed over VNC/noVNC. Publishes multi-arch image to Docker Hub fjmerc/claude-desktop.

openclaw-telegram-multi-agent

Claude Code × Codex 协作 Skill — CC主导，Codex辅助

Start Claude Code in a 100% Privacy Mode, in a completely network-wise isolated environment that prevents any call-back-home (telemetry or logging) which may exist for whatever purpose. Offline-claude has access only to a Local AI server (e.g. ollama).

One-shot install pack to connect Follow Up Boss CRM to your Claude Code co-work environment

Canonical Pear-authored Codex and Claude skills