Explore

Claude Code PRO — полный курс и гайд на русском: CLAUDE.md, settings, skills, subagents, hooks, MCP, плагины, CI. 8 лабораторных, библиотека промптов и готовый starter-kit. Здесь бесплатные курсы по c

Skill·MIT·★ 304·No key

Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.

Skill·MIT·★ 104·No key

MCP server + Claude Code / Codex hooks: phone push notifications and urgent alarms for AI agents via TMGR

Node.js·MIT·Few stars·No key

Hosted by author·MIT·Few stars·No key

Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to Syste

Node.js·MIT·★ 4·Few stars·No key

Local mail between coding-agent sessions on one machine: an MCP server and CLI on Bun and SQLite.

Node.js·MIT·★ 1·Few stars·No key

Zero-dependency linter and gate that blocks AI-generated comment slop: multi-line narrative comments, changelog markers, step-numbered filler. Write-time plugin for OpenCode, Claude Code hooks, pre-co

Node.js·MIT·★ 6·No key

Stop AI coding agents (Claude Code, Codex, Gemini CLI, Cursor) from installing npm/PyPI packages that don't exist — slopsquatting guard + MCP API for version-exact checks

Hosted by author·MIT·Few stars·No key

Mutation-tests every test your coding agent writes and blocks 'done' until the score passes (default 80%, up to two rounds). Claude Code, Codex, OpenCode, Pi. Java, Kotlin, Python, TS/JS, Go, C#.

Skill·MIT·★ 4·Few stars·No key

Scan Agent Skills before your coding agent installs them. Offline static analysis for prompt injection, hidden text, exfiltration and remote code, with install gates for Claude Code, Codex, OpenCode,

Skill·MIT·★ 3·Few stars·No key

Self-hosted memory server for AI agents. Share context across Claude Code, Codex, OpenCode, and ChatGPT over MCP.

Go·MIT·★ 72·No key

Help your agent remember what matters. Keep preferences, carry context across sessions, and bring your memory to the next agent.

Skill·MIT·★ 75·No key

Run several Claude Code sessions in parallel from any browser, phone included: live tmux terminals, per-session state from hooks (working / waiting for your permission), a shared board with hierarchic

Skill·MIT·★ 8·No key

12 个电商短视频 Agent Skills：3秒钩子、卖点分镜、图生视频提示词、edge-tts 配音、字幕花字、ffmpeg 自动成片、抖音/TikTok Shop/视频号导出、直播切片、多语言配音、封面A/B · Claude Code / Codex / Cursor

Skill·MIT·★ 80·No key

One skill registry for your whole team, in every AI coding agent, always up to date.

Skill·MIT·★ 33·No key

A very opinionated Claude Code plugin designed by a Rustacean obsessed with harness engineering

Skill·MIT·★ 3·Few stars·No key

Skill·MIT·Few stars·No key

Fast local CLI and MCP tool for compacting verbose test runners and build output.

Python·MIT·★ 42·No key

Pre-install verdicts for npm packages: GO, RISKY, FAKE, or MISSING. Built for humans and AI agents.

Docker·MIT·Few stars·No key

RealityGate: prove your AI-written code is real. Reality Score (0–100) for vibe-coded apps, a CI gate that blocks stubs, fake data, hallucinated npm packages & leaked secrets, a malware scanner for AI

Skill·MIT·Few stars·No key

palm: package manager for agent resources. Skills, subagents, instructions, hooks, MCP servers and plugins from any git repo into Claude Code, Codex, Copilot, Cursor, Gemini CLI and OpenCode.

Node.js·MIT·Few stars·No key

Find which APIs of your pinned Python dependencies changed after your coding model's training cutoff, and give the agent short AGENTS.md / CLAUDE.md notes from a static API diff. No model calls, no AP

Python·MIT·★ 10·No key