🔓DeepTeam is a framework to red team LLMs and AI agents.
// uncategorizedconfident-ai/⟨Python⟩★ 2,954◷ Apache-2.0[ claude ]
Most Battle-Tested
// most releases — mature and proven
// observatory (2232)
🔓
🔓Seamless integration between Claude Code AI assistant and Neovim
// pluginsgreggh/⟨Lua⟩★ 2,098◷ MIT[ claude ]
🔓ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.
// uncategorizedopenclaw/⟨TypeScript⟩★ 1,994◷ MIT[ claude ]
🔓Claude Code가 명확한 한국어를 구사하게 만드는 output-style 플러그인 | Claude Code output-style for clear, fluent Korean
// pluginssnflkd/★ 1,366◷ MIT[ claude ]
🔓🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
// mcp-serversstudy8677/⟨Python⟩★ 1,326◷ MIT[ claude ]
🔓Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.
// automationu7079256/⟨JavaScript⟩★ 1,214◷ MIT[ claude ]
🔓Open-source MCP server for comparing products and asking the buyer before purchase.
// uncategorizedcinderline/⟨JavaScript⟩★ 1,212◷ MIT[ claude ]
🔓Universal content reader MCP Server for 10+ platforms
// mcp-serversrunesleo/⟨Python⟩★ 962◷ MIT[ claude ]
🔓Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.
// skillsrampstackco/⟨Python⟩★ 935◷ MIT[ claude ]
🔓Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from…
// devtoolsvostride/⟨TypeScript⟩★ 888◷ NOASSERTION[ claude ]
🔓https://checkcc.org 是一个 Claude 运行环境检测与账号风险分析工具，面向正在注册 Claude 账号、订阅 Claude Pro、申请 Claude API、使用 Claude Code，或担心 Claude 封号、账号受限、订阅失败的用户。
// datayacuo/⟨TypeScript⟩★ 868◷ NOASSERTION[ claude ]
🔓Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and…
// automationtoby-bridges/⟨Python⟩★ 865◷ AGPL-3.0[ claude ]
🔓🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes da…
// automationcontext-machine-lab/⟨Python⟩★ 832◷ MIT[ claude ]
🔓Local observability map for AI coding agents. Watch Claude Code, Codex, and Cursor plans, tool calls, file changes, and progress in real time.
// automationsodiumsun/⟨HTML⟩★ 709◷ MIT[ claude ]
🔓Extract clean conversation logs from Claude Code's internal storage
// devtoolsZeroSumQuant/⟨Python⟩★ 677◷ MIT[ claude ]
🔓An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding ag…
// automationAr9av/⟨Python⟩★ 665◷ NOASSERTION[ claude ]
🔓Fire your SEO·GEO agency 🔥 A Claude Code skill that audits and optimizes SEO·AEO·GEO·LLMO·NEO(Naver) by itself — 월 50~350만 원짜리 'AI 검색 최적화' 대행, AI 에이전트가 대체합니다
// skillsleopard627/⟨JavaScript⟩★ 638◷ MIT[ claude ]
🔓
🔓A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via…
// devtoolsmindmuxai/⟨JavaScript⟩★ 563◷ Apache-2.0[ claude ]
🔓Claude Code plugin: run the Antigravity CLI (Gemini) as a collaborating sub-agent with intelligent model routing across the SDLC. Community project; not affi…
// pluginsyuting0624/⟨Shell⟩★ 368◷ MIT[ claude ]
🔓비개발자를 위한 한국 실무 AI 코워커 패밀리 — Claude Cowork·ChatGPT Work에서 /project 한 번으로 시작
// productivitymodu-ai/⟨Python⟩★ 302◷ Apache-2.0[ claude ]
🔓Main agent plans and reviews; cheaper sidekick edits. Devin Fusion pattern for coding agents (OpenCode first; Claude Code & Codex planned).
// automationmihneaptu/⟨CSS⟩★ 217◷ MIT[ claude ]
🔓Claude Code plugin: preserve and restore working state around /compact
// pluginsu-ichi/⟨Shell⟩★ 204◷ MIT[ claude ]
🔓OpenSpec Plus — Agentic skills that enhance OpenSpec's Spec-Driven Development through better discovery, requirements, design decisions, execution planning a…
// othersudokar/★ 200[ claude ]
🔓Architecture-first skill lifecycle for AI agents. 5 modes: CREATE → EVAL → EDIT → REVIEW → PACKAGE. Integrates Anthropic's eval engine (grader/comparator/ana…
// pluginssmixs/⟨Python⟩★ 177◷ MIT[ claude ]
🔓See your AI usage clearly — a macOS menu-bar gauge for Claude & Codex quotas.
// othermangiapanejohn-dev/⟨Swift⟩★ 151◷ MIT[ claude ]
🔓Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · C…
// automationZSeven-W/⟨Objective-C++⟩★ 148◷ MIT[ claude ]
🔓Claude Code skill for AI filmmaking — shot lists, keyframe & video prompts, with 10 director-style overlays (Spielberg, Kubrick, Wong Kar-wai, Nolan...).
// skillswuwangzhang1216/★ 138◷ NOASSERTION[ claude ]
🔓Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.
// skillsMrZoyo/⟨Python⟩★ 135◷ MIT[ claude ]
🔓Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
// plugins0xhimanshu/⟨Python⟩★ 134◷ MIT[ claude ]