Anthropic agents

Management consulting skills for Claude Code, Cowork, Codex, and other agents. Strategy, operations, and transformation workflows for the full engagement lifecycle.

Waybar widget for Claude Code usage limits: session, weekly, per-model, and extra-usage spending. Progress bars, countdowns, pacing; OAuth refresh + Omarchy theming. Pure Bash; AUR package.

A local proxy server that relays Anthropic Messages API-compatible requests to the Kiro (Amazon Q) backend using Kiro CLI credentials.

A Claude Code skill that audits AI-generated frontend and rewrites it to remove generic AI-slop design patterns (purple gradients, Inter, default shadcn). The design counterpart to avoid-ai-writing.

Sistema de aprendizaje continuo para Claude Code: hooks que observan patrones de trabajo reales y los destilan en reglas atómicas con nivel de confianza, aplicadas en sesiones posteriores.

AI-Native-Code开发工作流方法论：4-Phase 框架 + 空项目/已有源码两种场景 + 反模式速查。让 Claude Code 等 AI agent 在共享契约下并行干活。

Spatial prompt engineering through interactive 3D concept graphs

An MCP server that allows users to dynamically add custom tools/functions at runtime

AI-powered prompt optimization hook for Claude Code. Transforms simple prompts into comprehensive, structured instructions using Claude Opus 4.6's advanced reasoning capabilities.

My forkable Claude Code setup with sync feature

Anthropic's Advisor Strategy as a drop-in DeepAgents middleware

SEO blog writer Claude skill — turn any URL, notes, or topic into a human-sounding blog post that ranks on Google. Fills every SEO field: title, meta description, FAQ schema, table of contents. Beats AI detectors.

Project-based Claude CLI session manager with automatic tmux setup and persistence

Personal agentic assistant built for thinking work

Unofficial community workarounds for Claude Code (empty thinking summaries; missing context-usage icon; no copy/paste of markdown).

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, then reversibly disables the dead weight. No proxy, no compression.

Claude Code plugin: a guided, controlled development orchestration harness that keeps your codebase read-only by default and grows with your taste - workflow, state management, and a crystallized-agent workshop built in, for designing and building durable, production-ready software in new projects or existing codebases.

Give Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before power-on, and catch bugs that live on the glass, not the logs.

Claude Code skill for product launch motion design — make launch videos, promos and demo reels from code. HTML/CSS/GSAP compositions, word-locked voiceover sync, real camera moves, film grade, broadcast-loudness mastering. A director's discipline, not a template.

Self-evolving SDLC enforcement for AI coding agents — hooks, skills, and one-command setup for Claude Code. Plan before coding, test before shipping, escalate when uncertain. Measures itself getting better over time.

C# SDK for the Anthropic API -- Claude chat completions, tool calling, and vision

Claude Code CLI 代理服务器 - 多租户、自动故障切换、Web 管理界面

Observee (YC S25) lets you build AI agents with 1000+ integrations using MCPs with managed OAuth, Security and Observability

AI-powered trading bot framework for Polymarket

Scan GitHub for exposed Anthopic API Keys

Multi-agent system for software development

Scrape JavaScript-heavy sites and extract structured data via reusable CSS schemas. Portable agent skill wrapping the Crawl4AI CLI and Python SDK.

SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command. TDD, planning, self-review, CI shepherd.

Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do list. A Claude Code skill.

An OpenCode plugin that sandboxes agent-executed commands using @anthropic-ai/sandbox-runtime

Multi-agent remote dashboard for Claude Code, Copilot, and Codex. Approve permissions, answer questions, and monitor token usage in real-time from a GeekMagic screen, Android widget, GNOME Shell, or VS Code.

Human-supervised AI code generation using Plan-Do-Check-Act methodology with TDD and refactoring. Works as Claude Code skill or standalone prompts.

Dynamic Shell Command MCP Server

Track your Claude API usage from your MacBook's notch

Intelligent model orchestration for Claude Code - routes queries to optimal Claude model (Haiku/Sonnet/Opus) based on complexity. It also includes many more features. If this project is working well for you and would like to support me, just help spread the word. Thanks!

Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subagents, skills, hooks, commands & MCP configs.

完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic 黑客松获胜者的实战配置，助力中文工程师高效理解与使用 Claude Code。

Claude Code plugin marketplace for Shopware development. Provides MCP servers, skills, agents, hooks, and commands to integrate development tools directly into your AI coding workflow.

The native macOS & iOS app for browsing AI agent memory files — Claude Code, OpenClaw, Codex, Cursor, Gemini

Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ tools. Companion-first alternative to Hermes Agent / OpenClaw / Claude Code.

Patches Claude Code to show files read / commands run, and live streams thinking inline (optional) WITHOUT verbose mode.

🪼 A personal AI assistant that lives in Telegram — every topic is its own isolated Claude Code agent with layered persistent memory and proactive cron heartbeats. Open skeleton of a real, running system.

Human-supervised AI code generation using Plan-Do-Check-Act methodology with TDD and refactoring. Works as Claude Code skill or standalone prompts.

Your agent team, on your machine. Open-source harness for multi-user Claude agents.

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

Open library of legal AI skills (SKILL.md) for MCP-compatible agents — 39 jurisdictions, 200+ plugins, Apache-2.0.

Open-source Claude agent skill that teaches Claude Code, Claude Desktop & Claude AI to create and edit professional motion graphics videos with Remotion. AI video editing, B-roll, captions, sound design — from one prompt.

Tool-agnostic 13-phase AI development pipeline — turns a task description into reviewed, committed code through automated design, adversarial review, security, test, and code-review gates. One bash engine, balanced Opus/Sonnet routing, self-healing commit review.

You put an agent into an Elpis, and it becomes Elpis; Be Elpis my friend.

Agent skill that rewrites rough prompts into polished, model-specific prompts — grounded in the official Anthropic prompting guides

One command to turn any codebase into an MCP server

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: tier routing (Sonnet 5 does the work), Requirements Ledger, enforced guard hooks, automatic teammate reaping

AgentKit is a production-ready starter template for building AI agents with web search capabilities

(Need to be maintained) Golang SDK for AnthRopic Claude AI. Provide complete encapsulated interfaces that are easy to quickly get started with.

Custom status line for Claude Code — rate limits, git branch, cost, diff stats

AI-powered self-healing system for OpenClaw Gateway • 4-tier autonomous recovery • macOS & Linux

Autonomous AI Company OS — 14 AI agents loop 24/7, ship real software

A Claude Code Marketplace

Use Claude Code CLI (Opus 4.6, Sonnet 4.5) for free via your Google Antigravity/Code Assist subscription. No Anthropic API key needed. Works on Linux, macOS, and Windows.

A tiny IDE for your AI CLI agents. Use them as browser style tabs. One click session resume.

CLI tool for GLM-5 and Claude Code integration. Switch between GLM & Claude easily, manage API tokens, and setup AI-powered development environment with a single command.

🎬 The FIRST MCP server for Kling AI video generation! Generate stunning AI videos directly from Claude.

Computer use CLI for AI agents

A Model Context Protocol (MCP) server that provides real-time cryptocurrency analysis via CoinCap's API. Enables Claude and other MCP clients to fetch crypto prices, analyze market trends, and track historical data.

Model Context Protocol management suite/factory. An MCP that can generate and manage other local MCPs in multiple languages. Uses the official SDKs for code gen.

Claudetools is a Python library that enables function calling with the Claude 3 family of language models from Anthropic.

Open-source Claude Code skills — 6 cognitive firewalls block AI hallucination, bias & sloppy reasoning. npx skills add

Claude Code Telemetry is a lightweight bridge that captures telemetry data from Claude Code and forwards it to Langfuse for visualization, with a secure local turnkey installation under a minute.

27 Skills that diagnose, build, and optimize every architectural layer of your Claude environment

An atelier for your Agent: spec-driven workflows, deep thinking, and code quality.

Personal finance copilot — real math, not AI guesses. 6 locales · 13 bank formats · Monte Carlo FIRE. claude.ai · Claude Code · Cowork. Open source, free.

Agentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experimental design, computational text analysis, manuscript QA, and transparent reporting.

Local-first MCP server for Google Health API v4 (Fitbit + Pixel Watch) — Claude/Cursor/Hermes

A fully featured C# implementation of Anthropic's Model Context Protocol (MCP)

One command to turn any codebase into an MCP server

A Cloudflare Worker proxy that enables Claude Code to use NVIDIA NIM API models

Self-hosted AI technical workbench. Visual, persistent, multi-stream. Development, architecture, and operational analytics without losing context.

Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.

Real-time Claude peak hours tracker — know instantly when session limits drain faster. 10 languages, live countdown, JSON API.

Claude Code skill for session handoffs — survives context compaction, chain-links across sessions.

Zettelkasten knowledge base template for Claude Code projects. Bootstrap + interactive interview.

Audit your Claude Code .claude/ setup — scans skills, commands, hooks, agents, and settings for dead refs, weak triggers, token bloat, and skill-listing-budget overflow.

Personal AI agent skills for Claude Code, Copilot, Codex, Gemini & Cursor — turn a PR or idea into marketing content, technical Slidev presentations, courses, changelogs, and rendered videos.

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

Think of it as screen-sharing for AI pair programming, but everyone can type.

Talk to anyone: /coach persona plugin for Claude Code — research any public figure from their YouTube + web, then talk to them

Claude Code & Codex skill: say "share this as a link" and any AI output — chat, artifact, or markdown — becomes a live public URL in ~10 seconds, with document tracking (aggregate view counts). A lightweight DocSend alternative for the simple case. Publishes via the ReportRoom MCP.

The validation layer for solo founders. Research, strategy, and validation on Claude Code - decide before you build. 3 agents, 29 skills. MIT.

Auto-summarize Claude Code sessions as local markdown — session summaries, keyword index, on-demand reports.

Cloud + Data + AI + Security from zero to hero. 122+ certs across 22 providers, 37 plain-English concepts, 15 hands-on builds, cross-cloud + AI service comparisons.

AppControl MCP is a local server connecting AI agents and IDEs like Claude, Cursor, and Windsurf to system history provided by the AppControl desktop app. Ask which apps used CPU, GPU, RAM, or disk, and what caused slowdowns, heat spikes, or webcam, mic, and location access. Built for deep historical monitoring and useful real-world PC insights.

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Opus 4.7. Eight-phase sink-guided pipeline, ~$1/run, OSS self-scan and coordinated disclosure.

Production-ready Claude Code plugins: skills, hooks, agents, slash commands, and MCP templates.

The validation layer for solo founders. Research, strategy, and validation on Claude Code - decide before you build. MIT.

Chainlit application built using AWS CDK, secured with Amazon Cognito, that allows you to interact with Anthropic's Claude language models from Amazon Bedrock.

Function calling using Amazon Bedrock with Anthropic Claude 3 foundation model

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

Full Apple Music integration for Claude via MCP — search catalog, manage library & playlists

Claude Code v2.1.88 源码深度分析笔记 — 架构解析 + 面试八股