Shell agents

Attentively Embracing Noise for Robust Latent Representation in BERT (COLING 2020)

🧠 Claude Code plugin marketplace featuring Second Brain - an agentic workflow system with persistent memory and tribal knowledge. Transform Claude from goldfish to elephant with cross-session learning.

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.

AI bot for Telegram. Free, self-hosted, 5 min setup.

Ready-to-use AI agent templates with complete workflows that make Claude smarter at specific development tasks.

crosswire (xw) — Cross-machine communication protocol for AI coding agents. File-based, SSH-bridged, agent-agnostic. Zero dependencies beyond Bash.

DevOps-AI

Development workflow enforcement plugin for Claude Code

Reference implementation of a Databricks-native document intelligence agent with cited answers.

Privacy focused Open-source AI, Platforms, and Automation driven business-in-a-box. Designed for small business and startups.

A collection of specialized agent configurations for Claude Code.

AI context toolkit for Claude Code — commands, decisions, skills, and feature planning for your codebase

An operating system for your Claude Code skills, agents & MCPs — organize everything into auto-routing orchestras.

Beginner-safe Linux VPS hardening skill for Claude Code. SSH lockdown deferred until key login is verified — first-time lockout structurally impossible. macOS/Linux/Windows laptops, Debian/Ubuntu servers.

Build complete AI agents — 150+ personalities + 7 skills + messaging + identity. The skill builder for AI Maestro.

Reusable agents, commands, and permission templates for Claude Code

Run parallel Claude Code agents in tmux with automatic permission approval. Auto-approves Bash, WebFetch, and other tool prompts so agents run unattended. One-liner install for macOS, Linux, WSL and Termux.

Configuration governance for Claude Code. Bootstrap, audit, sync, and evolve .claude/ across projects.

Force any OpenAI-compatible or Anthropic API-compatible tool (Claude Code, Qwen Code, Aider, Fabric, Interpreter) to use Gemini, Groq, Cerebras, or Ollama. Pure Bash. Zero dependencies.

Portable Bash-only framework for building stdio Model Context Protocol (MCP) servers with zero dependencies.

Agent Skill for GitHub repository setup and platform-specific features | Claude Code compatible

Community patches, configs, and power-user mods for OpenClaw — per-agent compaction, context management, and more

Agentic workflow plugins for tasks you'd rather not do yourself. Someone has to secure your secrets, sort your inbox, and tell you when you're wrong. It's not going to be you.

418 AI agent skills across 31 domains & 54 roles. Role-based installer with export for Claude, ChatGPT, Gemini, Cursor, Copilot, Windsurf & any LLM API. Open source skill library that gives AI agents professional-grade methodology.

Docker image to run a self-hosted text embeddings and reranking server powered by Hugging Face TEI, with an OpenAI-compatible API. Supports BGE, Nomic, MiniLM and other models. Features optional reranking via cross-encoder models, API key auth, model management, offline/air-gapped mode, and persistent model cache.

Local-first governance layer for Claude Code, built entirely on its native primitives — hooks, subagents, skills, MCP. Turns every session into a queryable, local SQLite record, then reads it back to predict your next dispatch, recall past incidents, attribute cost, and gate commits. The record is the product.

A GitHub Action to run Rovo Dev (Atlassian's developer AI agent) in your CI/CD workflows.

Automated AUR packaging for OpenAI Codex Desktop on Arch Linux.

Claude Code autopilot with self-healing memory: one command → build → test → localhost. Trajectory tracking, learned routing, and stop-hook enforcement across runs.

Agent skills for working with Zapier, maintained by Zapier teams. Indexed by skills.sh.

Agent-native browser with fingerprint control and proxy support.

80+ agent skills for Pilot Protocol — communication, file transfer, trust, task routing, swarm coordination, and more

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.

Codebuddy IDE CN（国内版）的非官方 Linux 自动化打包与安装构建脚本工具

A peer-review protocol for AI models. Claude, Codex, Gemini and others review each other's code via CLI handoffs. Bidirectional, symmetric, opensource.

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

AI-powered Fortune 500 business operating system for Claude Code — 15 executive agents, governed initiative lifecycle, Decision Authority Matrix, and 17 slash-command workflows.

免电脑 | 一条命令在安卓手机运行Claude Code AI Agent | 接入微信 | DeepSeek平替

The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.

一个 AI 会话干所有活?上下文越聊越烂、任务无法并发、信息同步靠复制粘贴。Solobaton:一个人指挥多个并行 AI 会话(产品/全栈/测试)像小团队一样交付中大型项目——信息走文件不走人嘴、完成必须带证据、关键决策人拍板。方法论 + 拷贝即用脚手架,一句「给我的项目搭协作骨架」起步。

Autonomous session orchestrator for Claude Code — run sessions back-to-back with creative/refine improvement modes

Hire a 42-employee AI company in one command: 7 departments, 42 skills, 1 CEO. For Claude Code & any AI CLI.

Shift-handover workflow for AI coding agents — capture ideas into an inbox, dispatch tasks to the cheapest capable executor (any CLI agent or subagent), and hand work down between sessions, agents, and tools. Composes with superpowers and OpenSpec.

Whisper speech-to-text server installer for Ubuntu, Debian, AlmaLinux, Rocky Linux, CentOS, RHEL and Fedora. OpenAI-compatible transcription and translation APIs powered by faster-whisper. Supports all Whisper models, word-level timestamps, JSON/SRT/VTT output, SSE streaming and offline mode.

中国+海外双市场 Flutter+NestJS 多平台 App 开发 Agent Skills：三 flavor 发布/第三方登录/测试/CI-CD/可观测性，适配 Claude Code、Codex 等

A meta-framework for long-running AI-assisted development: continuity across hundreds of agent sessions, governed by evidence, gates and falsifiable mechanisms.

Adversarial startup idea interrogation pipeline → BUILD / KILL / PIVOT verdict. Works with Claude Code, Codex, Cursor, Windsurf, Kiro, and OpenCode.

Parzival Oversight Agent - Technical PM & Quality Gatekeeper for Claude Code multi-agent projects. Oversight templates, session management, and verification workflows.

AI agent swarm orchestration toolkit — spawn, monitor, and manage coding agents (Codex, Claude Code, Gemini) with automated PR review and CI fix handling

Practical AI agent swarm: 6–15+ parallel coding agents in Docker with isolated git branches. 500–800 commits/day, massive test coverage gains. Clean, safe, no worktrees. Battle-tested on 100k+ LOC codebases.

Comprehensive toolkit extending Claude Code with 70+ slash commands, specialized AI agents, and automation workflows. Features hybrid parallel-scanning architecture, intelligent problem routing, and automated code quality improvements. One-command pipelines for security audits, performance optimization, and refactoring.

Claude Code plugins for spec-driven development workflows: SPECLAN integration, BMAD-METHOD interop, and SDD automation skills.

10 AI agents with persistent memory, professional knowledge, and file-based coordination. Built for Claude Code.

MINTORAIN 바이브코딩 - Claude Code 팀 에이전트 tmux 5분할 자동화 키트

AI-powered code review framework for Claude Code - Detects 40+ issue types across 10 categories

TAS: Tracking, Automation, and Skills - An operational harness for Claude Code. Session tracking, token budgeting, slash-command skills, and maintenance cadence.

Local-first agentic NetOps framework that connects LLMs to real network devices with unified intents, adapters, and full observability.

north-starr is your AI development partner

Workflow continuity system for TRAE IDE with multi-session support. Save context with SAVEAGG, restore with LOADAGG. Plug-and-play package with bilingual docs (EN/IT).

A ready-to-run Docker image for OpenClaw, a personal AI assistant that connects to WhatsApp, Telegram, Discord, Slack and more

Enhanced status line for Claude Code - model, git, context window, session cost, and live usage limits in one bash script

Claude Code plugin — automates the full dev cycle (spec → plan → implement → review → clean) with adaptive skill orchestration, critic loops, 12 agents, and intent-based evaluation. Zero dependencies.

This project demonstrates a real-time AI "Meeting Coach" showcasing the use of Confluent Cloud for Apache Flink AI Inference functions to build a real-time Retrieval-Augmented Generation (RAG) pipeline. The demo uses both a static knowledge base of sales documents and real-time simulated meeting data.

Structured marketing knowledge base optimized for AI, LLMs, agents, and prompt workflows. Modular, reusable, and high-density content for sales, marketing, and copywriting.

Agent Skill for creating and maintaining TYPO3 extension documentation | Claude Code compatible

Tracking the systems that automate scientific research — from literature scrapers to full paper-writing pipelines

Ready-to-use Kiro IDE configurations for enterprise SDLC — Phase-Based (14 roles, 5 phases) and Sprint-Based DevSecOps (Scrum + security shift-left). Steering, Hooks, Skills, Subagents, MCP/Powers.

Claude Code plugin providing AI-powered agents for code auditing, research, and multi-model consultation (OpenAI Codex, Google Gemini)

Autonomous spec-driven development plugin for Claude Code. Describe a feature, get merged, tested, reviewed code. Full pipeline from PRD to PR with dependency-aware task tracking, AI code review, and zero dependencies beyond bash + jq.

Rode o Claude Code enquanto você dorme. Spec-driven development com modo autopilot: planeja, constrói, valida (segurança, qualidade, testes) e comita fase por fase sozinho — pausa ao bater o limite do plano e retoma no reset. Acorde com a feature pronta. Agnóstica de stack. PT-BR.

Claude Code status line with Catppuccin Frappe theme

nv:context > Context engineering for engineers who ship. Auto-detects, analyzes, generates configs, hooks, session management, and token budgets. 200+ research sources.

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

agent-skill for p2claw - peer to peer app delivery

97 reasoning patterns from history's greatest minds — as Claude Code agents. Curie to Toulmin. Engineering to humanities. Every claim cites its source. Every commit is checked. The only agent system where "I don't know" is a feature.

Open source Claude Code plugin — 52 invisible engineering skills turn vibe coding into production-ready software. Auto specs, TDD, security hooks, quality gates, self-improving retrospective. 97% vs 41% on blind benchmark.

Multi-agent Kiro CLI config — master orchestrator, 12 specialist subagents, 16 steering docs, 24 skills, AWS Agent Toolkit MCP stack, self-evolving personal rules

A Claude Code plugin that transforms Claude into a multi-agent orchestrated system with specialized agents (Riko, Senku, Loid, Lawliet, Alphonse), verification gates, and cost-aware model selection.

The best blockchain harness for agentic AI - on-chain execution with runtime, skills, and component library.

Comprehensive guides for AI coding assistants: Claude Code, GitHub Copilot, Gemini CLI. Includes MCP servers, multi-agent orchestration, and production templates.

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

Multi-model AI deliberation system querying 12 AI consultants (Gemini, Codex, Claude, Mistral, Ollama, etc.) in parallel. Features unique personas, confidence scoring, multi-agent debate, weighted synthesis, presets, and self-exclusion. Claude Code skill compatible with agentskills.io

Universal full-stack dev Skills for Kiro IDE, based on superpowers methodology

Scribo Claude/Codex skill — generate EN 16931-compliant e-invoices (ZUGFeRD, XRechnung, US plain PDF; Factur-X, Facturae, Peppol BIS UBL coming soon) via the public Scribo HTTP API

Claude Code plugin that intercepts tool calls with hooks and routes work across Gemini, Codex, and Grok — then A/B tests whether delegation actually saves tokens.

Claude Code plugin that delegates boring, low-risk tasks (bulk i18n, trivial style tweaks) to the Gemini CLI — a transparent Claude ⇄ Gemini pipeline.

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

🦞 Effortlessly manage your Claude subscriptions — route Claude Code across multiple accounts so your plans last longer.

Let Claude Code talk to your other coding agents

Autonomous agentic coding environment — an OpenCode-driven 12-agent crew that ships hands-off. AGPL-3.0 · use at your own risk.

A practical, opinionated Claude Code workflow: a task-rubric loop that makes AI-written code trustworthy, a lean CLAUDE.md pattern, and a lab for versioning your own setup

whoami: a Claude Code skill that scans your machine + interviews you to build a portable profile, giving any AI coding agent (Claude, Cursor, Codex) instant context about who you are.

Forge your Claude Code projects — pass them through, they come out faster.

Stop trusting 'done'. Make AI coding agents prove their work — frozen specs, tamper-detected tests, an independent blind verifier, hard-blocking gates. Fails loudly instead of pretending. For Claude Code, Codex, OpenCode & any Agent Skills runtime. No unverified work passes.

ai-berkshireの日本株版（fork ではなく独立実装）— EDINET DB MCP（有報一次データ）接地の Claude Code スキルパック / Japanese-equity edition of ai-berkshire, grounded in primary-source EDINET filings

Reusable UI/UX design skills for AI coding agents — Codex, Claude Code, ZCode, and more.

Spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework lock-in.

Guardrails para desenvolver com agentes de IA: gate de CI bloqueante, hooks determinísticos, supply chain travada e fluxo de task com evidência. De 0 a funcionando sem orçamento

Portable /goal-writer agent skill for Claude Code and OpenAI Codex — drafts goal+rider document pairs (≤4,000-char goal + phased rider) per goal-engineering best practices