Claude
Tools

Write an agent plugin once, ship it to every harness — Claude Code, Codex, Pi, and OpenCode. Skills, commands, subagents, hooks, MCP, and shared tools from one TypeScript definition.

🔍 Discover + safety-vet Claude Code extensions before you install them - a 0-100 trust score for discovery + a 1-5 static-scan risk verdict, SHA-pinned install. Skills/MCP/plugins/commands.

Orchestrator-first multi-agent methodology + Claude Code plugin: a per-project .fray/ thread board, dispatch/reconciliation hooks, and a board CLI.

A one-file door-guard for coding agents — first-class on Claude Code (permissionDecision deny); portable to any agent with a blocking pre-exec hook.

Web animation skills for Claude Code — GSAP, SVG, Lottie, micro-interactions, page transitions, and 60fps performance, installed straight into your agent.

Kinetic typography skills for AI coding agents — turn text into beat-synced, animated type for social, titles, and lyric videos.

macOS menu-bar mission-control for your Claude Code sessions — see, hear and reply to every agent so none sits idle waiting on you. Rust + Tauri, event-driven on native hooks, fully local.

Free security guardrails for apps built with AI coding tools (Claude Code, Cursor, Lovable, Bolt). Drop-in rules + OWASP/LLM/MCP policy + secret-scanning hooks & CI gate.

Batch sentiment analysis tool for CSV files using the Anthropic Claude API.

Cross-platform Node status line for Claude Code, plus /handover, /handover-check, dialogue, grill-me and an RCA skill - conflict-safe mergeful installer (macOS/Linux/Windows).

The 21 agentic design patterns, distilled to concepts (no code) — a design-phase reference for building AI agents. Works as a Claude Code skill.

A Claude Code Stop hook that blocks fake checkpoints — turns that hand already-decided work back to you instead of doing it.

Intelligent design brief router — entry point for the modular design skill system (color, effects, fonts, icons)

Natural Australian workplace English for ESL professionals — a Claude skill that polishes emails, Teams & Slack messages and saves ready-to-send files.

Keep AI-driven work tracked in Linear: a Claude Code / Codex skill + hook that find or create a ticket and move it through your workflow. A public example of how Prime Radiant works.

Claude Code skill that converts any project into a multi-tenant SaaS — auth, organizations/teams, RBAC, plans & billing (Stripe/HYP), invites.

YouTube and YouTube Shorts marketing skills for Claude Code and Codex: high-CTR titles, SEO descriptions, retention hooks, thumbnails, and a content plan. Publish via Publora. MIT.

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.

命理圆桌会 · A multi-school Chinese BaZi (Four Pillars) roundtable reading skill for Claude

用 Claude Code 指挥 Remotion 出视频的工作台脚手架:三层架构 + hooks 守规矩 + skills 编排流程 | maintained by 陈与小金

Open Source version of Claude Managed Agents. Anthropic SDK compatible. Supports agents, sessions, environments, files, memory stores, skills, deployments, message batches, vaults, and webhooks.

Makes a company, product, book, or personal brand legible, desirable, and inevitable, then writes the copy to match. An agent skill built on the Ekram Method.

Claude Code skill: pick the right loop type (/goal, /loop, /schedule) and write stop conditions that actually hold. From the Claude Code team's loops taxonomy + real overnight autonomous runs.

Claude Code Skill：把一个原子知识点自动展开成单文件、离线可用的交互式 HTML 原子课件——含权威定义、贯穿项目案例、实操判断题、可视交互 Demo