PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.
Needs a Hand
// healthy but under-resourced — good places to contribute
// observatory (1821)
Claude Code marketplace of small, opinionated plugins by yegor256
A collection of learning resources for curious software engineers
Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures system audio + mic, cancels echo via WebRTC AEC3, tr…
Per-prompt cost & token analytics for Claude Code, straight from your local JSONL files. CLI + Streamlit dashboard, totals reconciled against ccusage. No Adm…
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
Cuánta cuota te queda, en todas tus cuentas de agentes: cada perfil de Claude Code de la máquina —no sólo el de por defecto— más Codex y los proveedores de o…
Profiler for Claude Code — where your tokens, money and time go (CLI + HTML report + MCP)
A Chrome browser shared in real time between you and Claude Code (CDP + Playwright MCP): you clear the captchas/logins, Claude operates and learns each site'…
AI pull-request reviewer: hybrid RAG + a code graph + Claude Code. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Cod…
An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration
Open-source local router for coding agents, connecting Claude Code to cloud and local on-device models.
Plugin de skills e agentes para Claude Code — workflows de engenharia reais, do PRD ao PR
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code durable memory — entirely offline.
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable sk…
Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
Claude SEO Skills — production Claude Agent Skills for the SE Ranking MCP server. Content briefs, AI Search share of voice, audits, backlink gaps, keyword cl…
Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, a…
AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.
Smart Learn - Claude Code interactive learning skill. Feynman Technique five-step pipeline: concept map + Feynman explanation + self-test + association + sum…
An open-source social media production system that turns a content calendar into on-brand copy, images, video, and client-ready delivery - with compliance an…
Public Solana MCP registry metadata for Vybe Solana API
Spotkit — a Claude Code skill that turns a feature description into minimal, abstract SVG product illustrations that all belong to one design system.
The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.
Agent skill that draws architecture, flowchart, sequence, data-flow and lifecycle diagrams as hand-placed SVG, to one linted house style.
Add expert SwiftUI Best Practices guidance to your AI coding tool (Agent Skills open format).