Shell agents

Autonomous AI chief-of-staff agent built on Claude Code. Multi-tenant template — blank Ubuntu VPS to a Telegram-reachable agent in under an hour. Memory, sub-agent swarms, observability, voice.

Enable accurate academic citation by searching, evaluating, and generating BibTeX entries with quality metrics using Semantic Scholar data.

Professional .cursorrules configs for 8 popular stacks. Works with Cursor, Cline, Claude Code.

Easiest way to use OpenClaw on Android

Blueprint repo to build Copilot instruction prompts and custom agents using GitHub Copilot itself.

Run Claude Code with --dangerously-skip-permissions safely. Per-project Docker sandbox with capability-drop, docker-socket proxy whitelist, git-RCE hardening, and shared OAuth token across projects.

Six Claude Code skills that keep AI-generated code tight. Audit, refactor, commit, PR, curate context.

A curated list of frameworks, patterns, and research for orchestrating multi-agent systems built on Claude, including subagent collections and primary sources from Anthropic.

Local-first governance framework for AI agents. Tamper-evident audit logs, pre-execution gatekeeping, kill switches. No tokens.

TAD Method — Triangle Agent Development (Two-Agent Quality Framework): Design (Alex) + Execute (Blake) + 4-Gate quality system + 25 capability packs.

Multi-agent Claude Code pipeline: spec → plan → parallel impl in worktrees → integration tests → two-tier review → smoke → PR. 13 sub-agents, 7 slash commands, calibrated on 222 completed tasks.

DAG-scheduled multi-session epics with parallel-worktree execution. Works with Claude Code and OpenCode.

Ten composable AI skills covering the full arc from idea to launch. Discovery hub for prd-ready, architecture-ready, roadmap-ready, stack-ready, repo-ready, production-ready, deploy-ready, observe-ready, launch-ready, harden-ready. Plug into Claude Code, Codex, Cursor, Windsurf.

One person. Any project. Production-ready output.

Self-evolving AI personas built on Claude Code

Claude Code documentation plugin - auto-synced reference for features, configuration, skills, agents, hooks, and MCP servers.

A Claude Code skill that turns the agent into a relentless Kaggle Grandmaster — battle constitution + technique arsenal.

Relentless Project Manager — Claude Code plugin that prevents drift and keeps you on task across LLM-assisted development sessions

Language-agnostic coordination protocol for parallel AI agents. Defines invariants, execution rules, and message formats that any Polywave implementation must satisfy.

Scan multi-language projects using AI to detect and fix technical debt, security issues, and documentation gaps without external dependencies.

全新结构+多agents辩论+统筹裁决框架的决策skill，开启一场众神之会。

AI ready linux distribution for agentic development. Optinionated defaults that help me (and possibly you too) get stuff done faster. Installable, Live-Bootable, Customizeable. Built by Finn Glas

Project-scoped shared memory for Claude Code and Codex AI coding agents.

道法符籙 ── 以道教科儀之法為 Claude Code 生成 agent prompt | Daoist Talismans: Generate structured agent prompts for Claude Code using Daoist ritual metaphors

A Claude Code skill for orchestrating Opus/Sonnet/Haiku subagents plus a cross-vendor Codex peer

Lean, adaptive multi-agent engineering setup for Codex CLI with focused specialists, reusable skills, safe defaults, and bounded delegation.

Coordination toolkit for parallel Claude Code sessions sharing one repo — issue-pickup claim protocol, worktree isolation pitfalls, parallel-PR conflict recovery, subagent integrity, and squash/merge mechanics. 61 skills, Pattern B multi-skill plugin.

Coding agents that ship to a real repository on their own: one agent writes, a different agent reviews the exact diff, and the tests actually run.

One isolated, disposable environment per git worktree — own port, own Chrome/CDP, own database. A Claude Code plugin (and portable skill) for running N parallel agent coding sessions without collisions.

Hermes-EchoNet is a cybersecurity-focused customization layer for Hermes Agent that replaces the default soft personality with a more technical, pentest-oriented workflow assistant using custom SOUL.md and config.yaml configurations optimized for ethical hacking labs, CTFs, and security research.

A beautiful Claude Code statusline with live progress bars for context, rate limits, and cost, plus model-aware accents, rich git, PR status, and a session reminder. Single Bash script, Linux, no Nerd Font required.

Context Layering & Engineering for Agentic Resources — Persistent memory, intelligent context, and structured project management for Claude Code

An assistant that never makes things up. Runs on your machine, remembers in plain markdown you can open in Obsidian, cites the file it read, and says 'I do not have that' when it does not.

把開發規範寫成機器可讀的約束，讓 Claude 自動遵守 TDD、ADR、commit 閘門與發布檢查

Deliver and enforce engineering discipline with 38 proven skills and a CLI designed for real-world multi-agent CI/CD workflows.

A safe-by-default, batteries-included Claude Code harness starter pack — guardrails, a wiki-grounded quality loop, and a memory lifecycle.

Structured code-level review of open-source AI agent projects

Agent driven shared TTY via zellij

track your agents, skills, and tools usage - Analytics dashboard for Claude Code, Gemini CLI, Codex CLI, and OpenCode

Multi-Agent AI 短视频/短剧自动化流水线，模块化可扩展影视生成工作流

An engineering process for Claude Code projects: plan, review, record. The commit gate is a git hook, so it isn't optional.

Ralph Wiggum loop starter kit for Claude Code: a fresh-context autonomous build loop with stop conditions, guardrails, and spec/plan scaffolding.

🥧 Apple Pie — AI coding agent harness for native Android & iOS apps: drives Claude Code to take a Jira or markdown ticket through plan → implement → verify and out as a reviewed pull request. Android ships today; iOS is under development, preview coming soon. Parallel agents, one TUI dashboard, never auto-merges.

Handoff-first protocol for coordinating Codex, Claude Code, Gemini/Antigravity CLI & Grok Build agents on shared repos. AGENT_HANDOFF.md as source of truth, with file ownership, anti-overwrite guardrails and validation scripts. For multi-agent teams and single-agent sessions across runs.

Multi-agent coordinator for herdr: a head Claude Code agent that delegates tasks to worker agents (claude, codex, gemini, ...) in their own tabs

Feynman first-principles skills for research projects. For when you're prompting agents without really understanding your own assumptions.

A self-evolving AI Agent Team — agents that rewrite their own operating manual.

Ship a tracker ticket: dispatch it into a worktree, drive it to a pull request, merge it after review, and clean up after itself.

OpenFOAM CFD automation Claude Code Skill set - simulate (of-sim), post-process (of-post), diagnose failures (of-doctor), one-command machine setup (of-setup)

Agent Skill - March 7th Role-Play Skill

Analyze OpenClaw session logs to generate weekly self-improvement suggestions for AI agents without silent modifications.

Claude Code skill: one session coordinates, spawns and reviews builder sessions across a multi-phase build

Connect a dedicated WhatsApp number to an OpenClaw agent — without going through Meta's Business API.

Robots will learn about who you are and then tell you what they find.

Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment

📈 Generate AI-driven investment reports using multi-agent orchestration and real-time data for informed equity research and decision-making.

Orchestrate parallel AI teammates in Claude Code — 2-skill pipeline (execute, audit) with per-task adversarial review (Executor → Reviewer → Challenger ephemeral), hook enforcement, and workspace tracking

Expert orchestration framework for OpenClaw that turns agency-agents into installable multi-agent workflows for code review, security review, and AI automation.

A Claude Code skill for managing parallel story development using Git worktrees, enabling multiple isolated Claude Code sessions to implement stories simultaneously without merge conflicts. Part of the BMAD (Breakthrough Method for Agile Development) framework with an 8-phase workflow and automated worktree management.

Orchestrate multiple agents to execute Claude Code workflows with cross-model verification for reliable AI code automation.

v4.1 Opus 4.7 native prompt meta-compiler — skill-level meta-refinement, automatic ROSETTA via 5 hooks, Jarvis v3.0 overhaul (3-obs threshold, awareness cards), micro-task methodology. dual-layer memory, Buffer-of-Thoughts + Meta-Reasoner bandit, 125+ scientific papers. Claude Code plugin.

A workflow skill that turns OpenSpec and superpowers into a structured end-to-end software delivery flow

AI-First Multi-Agent Operating System with Zenith Coder, Agent Zero, and MCP Integration

두레클로 — 분산 디바이스 AI 에이전트 협력 오케스트레이션 | Distributed AI agent crew orchestration

🔪 Surgical AI for your codebase. Diagnose. Assemble. Operate. Zero side effects.

Portable multi-chat sprint orchestration skill for Claude Code. Validated in 17+ production sprints.

Project-agnostic Claude Code / multi-agent skills, slash commands, and CLAUDE.md template — extracted from a real Next.js + Supabase production codebase.

Autonomous Project Manager plugin for Claude Code that orchestrates parallel worker sessions via channels to fetch, implement, verify, and merge Linear tasks end-to-end.

Agent development rules for Claude Code, Cursor, and Windsurf. Build better OpenClaw agents with AI-assisted coding.

Agent orchestration kit — NOP reference implementation for multi-agent task dispatch. Runtime-agnostic at the protocol layer. Apache 2.0.

A playbook for orchestrating multiple AI coding agents on a single codebase

Portable Cursor IDE skill for running an autonomous multi-agent PR pipeline against any git/GitHub repo. Distilled from jiangtao129/unitree_sdk_jt.

Autonomous Claude agent fleet in Docker — one orchestrator, N workers, a Redis queue, a north star, and a supervisor that halts polish loops. Rides your Claude Max plan, zero API spend.

Multi-agent development system for Claude-powered projects. 15 specialized agents, 8 workflows, 11 scripts. TDD, BMAD structure, migration support.

Stop burning API tokens. 9 algorithmic engines for real-time context optimization, infinite-loop detection, and smart prompt compression.

Assign a GitHub issue, wake up to a PR. Autonomous agent in ~630 lines of bash — cron, flock, and git worktrees on a $10/month VPS.

A file-driven agent orchestration framework that enables technical startups to run their operations through Claude Code.

Agent orchestration framework for Claude Code — domain experts, security hooks, and self-improving knowledge bases.

Multi-agent specification-driven development (SDD) framework for Claude Code

Make Claude Code actually work like a senior engineer multi agents, token compression, safety hooks, UI pipeline.

One-shot host bootstrap for AI-agent-driven development. Sets up WSL2 / Linux / macOS with mise, Docker, Dev Container readiness, and AI agent CLIs (Claude Code, Codex, Copilot, Gemini) plus AI power tools (markitdown, ast-grep, yq, OCR/audio).

Blizz: a nomadic AI development toolshed

A customisable, living Lean/Kaizen-based GitHub Copilot instructions template for ANY project

Agentic bug bounty and pentest orchestrator. Claude Code plugin. Phase-aligned playbooks (recon -> scan -> manual -> chain -> report), parallel sub-agent dispatch, Kali via kali-ssh MCP.

Personalized YouTube digest pipeline — daily summaries filtered through your own lenses via Claude Code routines

🧠 基于文档的AI协作系统，让AI具备长期记忆能力，帮助开发者管理知识、任务和项目

玄武 Genbu — AI 防禦與保護模組。防止 prompt injection、記憶污染、鏈式攻擊與跨實例污染。基於 LDRIT 設計。

A versatile Docker container for the Google Gemini CLI, providing both an interactive web terminal (ttyd) and direct command-line execution.

🦞 Proxmox + OpenClaw IaC deployment. Terraform provisions VMs, Ansible deploys OpenClaw with TLS, auth, and automated config. From zero to AI coding assistant in minutes.

A hardened, isolated development environment for VS Code with GitHub Copilot.

Lightweight web UI for llama.cpp with dynamic model switching, chat history & markdown support. No GPU required. Perfect for local AI development.

A contextually-aware personal AI assistant with persistent memory, multi-platform messaging, and per-tier model routing. Designed to grow: voice integration, autonomous self-improvement via capability request loops, and edge deployment on Jetson are on the roadmap.

FastOpenClaw: openclaw省心一键安装，真正一次性配好，一次部署直接上手。

Plugin for Claude Code and Codex that turns freeform briefs into validated, cross-doc-consistent PRD packages. Explicit uncertainty labels (TBD / Proposed / Assumed), 16 quality gates, multi-stack, multi-language.

Comprehensive Claude Code agentic scaffold — workflow rules, auto-memory pipeline, FORGE feature loop, hooks, skills, and flavor packs. Extracted from a production SaaS codebase.

Control your running browser on macOS via AppleScript — for AI coding agents. No restarts, no special flags, full access to your existing sessions.

Secure-by-default software builder skill for Claude Code

A simple wrapper/runner for metagpt

Autonomous coding loop for OpenAI Codex and Google Gemini CLIs. Drop planning docs into a folder, set an iteration count, and loop-agent generates a backlog and runs plan → implement → review cycles to write your code. Independent-process reviews, atomic backlog updates, auto git rollback on failure, and safe rate-limit handling.