Anthropic agents

A practical, opinionated Claude Code workflow: a task-rubric loop that makes AI-written code trustworthy, a lean CLAUDE.md pattern, and a lab for versioning your own setup

whoami: a Claude Code skill that scans your machine + interviews you to build a portable profile, giving any AI coding agent (Claude, Cursor, Codex) instant context about who you are.

Real-time Claude Code usage in your macOS menu bar — burn-rate ETA · 7-day sparkline · custom alerts · CSV/JSON export · 4 languages (EN/KO/JA/ZH)

AI-driven pentest orchestration that hands Claude the full PTES methodology over real MCP tool calls. 80+ tools, 33 verification probes, scope guard on every request. Python orchestrator + React/Ink TUI.

A Claude.ai Personal Skill that generates a structured, seven-block session handoff so you can continue work in a new conversation without losing context, rediscovering decisions, or re-explaining your project state.

Install, update, and run Claude Desktop (incl. Cowork's local VM) on Arch Linux, verified against Anthropic's GPG signature.

Track your AI carbon footprint in Claude Code and plant trees to offset it via Tree-Nation

Claude skill for identifying material changes, silent risks, and interpretation traps in SEC filings (10-K, 10-Q, 8-K). Built by CMD+RVL.

Critical thinking plugin for Claude Code. Three specialized agents (advocate, adversary, judge) argue, stress-test, and judge any idea using a shared argument graph, 10 reasoning traditions, and persistent memory.

The web wrangler for agents. Give your AI a real browser and never touch the web yourself again.

集中版控 Claude Code 使用者層級設定(skills / hooks / settings.json / CLAUDE.md),以 symlink 連回家目錄 — 換機或重灌時 git clone + install.sh 一鍵還原。

Persistent AI governance for Claude Code — three-tier council deliberation, P10 pre-execution plans, and deterministic confidence scoring grounded in your own past decisions.

MCP server giving Claude AI access to 20+ NYC public-record datasets across 9 city agencies via 18 tools — NYC property due diligence in plain English: violations, liens, sales, ownership, permits, rent stabilization, and more.

Reusable Go base agent on the Google ADK — multi-provider (Gemini, Vertex, Claude on Anthropic + Vertex), MCP-native, with AGENTS.md, skills, and permissions wired up.

An autonomous orchestration harness for Claude Code: brief it like a teammate, it conducts Claude Code in your seat. Git stays locked.

The calm, terminal-first workspace for Claude Code — run claude, with files, Git, diffs & MCP on demand, and munu, a notch mascot that watches Claude for you. Local-only, no telemetry.

ClawTouch open hardware layer — CircuitPython firmware for a Raspberry Pi Pico 2 + the frozen USB-CDC wire protocol it speaks. MIT.

MCP server for WHMCS automation - AI-powered client management and hosting operations

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

Live NOC dashboard + control center for AI coding agents: pixel-art office floor, phone/Telegram/Slack alerts, cost guardrails, task queue with worktrees + test gate. Designed for Claude Code — other agent CLIs (Codex, Gemini, Grok, aider) join the floor too.

macOS 26 (Liquid Glass) como skill drop-in para Claude Code, Cursor y Gemini CLI.

Specialized Claude Code subagents for enterprise development, with persistent project memory and orchestration rules.

A Bash statusline for Claude Code: model, git state, context window, 5-hour and weekly plan limits, subscription cycle, cost, tokens, cache ratio, LOC, plus live tool, subagent and todo activity in compact labeled lines. Subscription, API-key, Bedrock, Vertex and OpenRouter backends; JSON config for presets, layouts, colors and thresholds.

The Middle East's first open source agentic harness. Designed for governed self-evolution.

Cuts what your coding assistant spends per task, and shows you the numbers. Works with Codex, Claude Code, Hermes, GG Coder and any command-line agent.

Universal engineering judgment for Claude Code. Read before editing, reuse before writing, verify before shipping.

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.

A cute desktop pet with a live Claude token usage meter - session & weekly rate limits in a thought cloud above your Windows taskbar. Free, open source, one-press install.

A modular, local AI companion featuring a RAG pipeline with FAISS and SentenceTransformers for semantic long-term memory. Powered by GGUF models via llama-cpp-python

Claude agent skill that plans multi-step work as a dependency graph. Subagent fan-out, layered fan-in, model tiering, verification retry loops, human approval gates. No framework, just instructions.

Personal collection of Claude Code plugins and skills: development workflows, cross-model review, issue-to-PR automation. The same marketplace installs in Codex CLI.

Local operations hub for Claude Code — a grid of real claude CLI sessions with live working/waiting status, usage & cost tracking, multi-account profiles, and revivable sessions. No API keys, no cloud, $0.

Claude skill that builds a permanent memory of your career and tailors an ATS-safe, evidence-backed resume for every job you apply to. 2-click install.

AI-driven incident response toolkit. Reconstructs the full attack path of a cloud or Windows breach, maps every step to MITRE ATT&CK, and stages human-approved containment. AWS · Azure · GCP · Windows. Apache-2.0.

Cẩm nang thực chiến Mastering Claude Code (tiếng Việt): 16 chương biên soạn từ tài liệu chính thức của Anthropic — CLI, workflows, MCP, subagents, skills, hooks, plugins, CI/CD & tối ưu context.

See where your Claude Code tokens actually go. Profiles the session logs Claude Code already writes, scores each project's context hygiene 0–100, and generates fixes backed by your own measured numbers. Local, zero deps, no telemetry.

AI video editing skill that watches your footage before cutting. Vision model analyzes every frame, scores usability, drops bad takes, reorders by narrative, then renders with ffmpeg. For Claude Code, Cola, OpenClaw. 会看画面的 AI 自动剪辑 Skill——先用视觉模型看懂素材再决定剪哪几秒。

Persistent per-project memory for Claude Code, Kiro, Cursor & Codex - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, searchable session history.

AI advisory board as a Claude Code skill + MCP server: verifies every quote word-for-word against public-domain sources, or abstains. Fail-closed fidelity. | Совет советников как скилл для Claude Code и MCP-сервер: каждая цитата сверяется дословно с источником в общественном достоянии, иначе отказ.

予言 Yogen — a 500-agent AI swarm that debates your idea and predicts the outcome. Self-host free with your own Anthropic key.

Run Claude 3.5 Sonnet and Opus models locally with this desktop coding assistant for Windows, macOS, and Linux.

Branching AI chat canvas: fork any reply, compare branches, never lose context. ChatGPT alternative built on Claude. Free during beta.

A quiet study-buddy skill for Claude Code. Body-doubling focus sessions, distraction-killing ritual, and markdown logs that prove you showed up. Made for neurodivergent brains.

繁體中文寫作 skill 工具鏈 for Claude Code：humanizer-tw（去 AI 味）+ good-writing-zh（節奏打磨：PG／余光中／王鼎鈞 + 技術文件保守模式）+ fable-econ／fable-explore（Amanda Askell 寓言式概念學習）

A Rust SDK for Anthropic's Claude API that won't panic on you — no unwrap/expect/panic, denied at compile time. Typed structured output and tools derived from Rust structs, streaming, thinking, caching, batches.

Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.

Claude Code plugin (Agent Skill) for BPMN 2.0 - read, explain, create & edit .bpmn process diagrams with clean auto-generated layout, validation, and control-flow linting (deadlocks, stuck tokens). Works with Camunda Modeler & bpmn.io.

🛠️ Simplify your Claude Pro subscription process with clear guides on account setup, renewal, and usage to enhance your coding experience.

Перегоняет книгу, курс или подкаст в набор вызываемых Claude Code скиллов. Русская локализация cangjie-skill с тройной проверкой и приёмкой живой маршрутизации.

Approve Claude Code permission prompts right from your menu bar — no terminal switching — plus live status for every AI coding agent (Claude, Codex, Copilot, Antigravity).

A Claude skill that audits or builds any website/UI against ~60 research-backed conversion & design-psychology principles. Auto-detects live URL vs local code.

Unattended PRD delivery for Claude Code

Turn social-media creators' videos into a searchable, curated knowledge base — Next.js download/manage app + GPU transcription (faster-whisper) + RAG

Cut your Claude API bill: local proxy that auto-routes every request to right model. Zero code changes.

養成型 AI 伴侶框架｜Raise an AI companion who remembers, reflects, and grows with you.

Local prompt-cache economics for LLM agents: split cache reads/writes from input spend, reconcile dollars to invoices, and surface concrete TTL/marker fixes.

AI-assisted D&D 5e session management for Roll20 + D&D Beyond, built on MCP — live combat, map prep with Claude-vision walls, and a voice HUD.

Run Claude Code on an unrooted Android phone via Termux + proot-Ubuntu, with free model access through a local 9Router proxy.

A virtual software company for Claude Code: 19 agents, 38 workflows, 16 quality gates. Takes an application project from idea to release.

A standalone agent harness in Rust: a provider-agnostic loop, MCP tools, a path jail and prompt-injection interlock, sandboxed shell, scheduled triggers, and an eval rig that grades the trace.

Claude Code Visual Studio extension

Edit your Warcraft III maps by talking to Claude — an MCP server for reading and editing .w3x/.w3m map files.

Skills Board, the agent-native skills registry for teams. Free forever.

Persistent memory for Claude Code. Survives compaction and session boundaries: anti-patch reconcile-on-write with LLM-judged de-duplication, a forced PROGRESS.md handoff, a live PLAN.md anchor with an enforced directive ledger, FTS5 search, MCP tools and a GUI. Pure stdlib Python, zero runtime dependencies.

Claude Code records what you work on into Jira, Linear, GitHub Issues, Trello or Vikunja, automatically

Open-source, self-hostable AI service desk - email becomes tickets, AI drafts replies and works them with real tools, humans approve anything risky. BYOK, SSO, MCP.

Routed delivery system for coding agents: 32 skills covering requirement to release, for Claude Code, Codex, and OpenCode

Clone any UI screenshot into one faithful, interactive single-file HTML page — an AI coding-agent skill.

🔥 Two drop-in text files that make Claude Code write less and talk less — a CLAUDE.md fragment and a prompt that tunes the rules you already have. Nothing to install.

Unofficial Windows always-on-top widget for remaining Codex and Claude usage

Turn a business's scattered data into a queryable knowledge graph — and plug it straight into Claude. A macOS CLI and Claude Code skill, built on graphify.

TradingView Premium × Claude MCP setup — drive your own TradingView Desktop session via Chrome DevTools Protocol for chart analysis, signals, and backtesting from Claude Code. Analysis only, no order execution.

Unofficial desktop client for the Claude Code CLI — session history, live chat, editor with LSP and debugger, git, and plan limits

MCP server for the Neural DSP Quad Cortex — build, edit and control presets and scenes from Claude or any MCP client, over the reverse-engineered USB-HID protocol. macOS + Windows.

8-agent LangGraph flood-monitoring & disaster-response system — 10 real-time data connectors, Anthropic/Gemini LLM reasoning, Google Maps + deck.gl frontend

Unofficial guide to the Claude Code GitHub integration: cloud sessions, Actions workflows, CLAUDE.md and guardrails.

Guide to Claude API usage: getting Console access, reading cost and usage reports, and keeping API spend in view.

Runnable Python examples for claude code api: first request, streaming and tool use, key from the environment.

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, and multi-turn session continuity.

Claude Opus 5 alternatives compared: Fable 5, Opus 4.8, Sonnet 5 and Synexa, with only sourced attributes.

Free, open-source toolkit (Anthropic Agent Skill) for cancer patients, their caregivers, and anyone organizing treatment — runs the operational side around the doctors: documents, consultations, next steps, second opinions, cross-border care. Not an AI doctor.

Multi-account switcher for Claude Code and Claude Desktop: claude-swap (cswap) plus a maintained patch series.

A practitioner guide for the Anthropic CCAR-P exam (Claude Certified Architect - Professional). 21 chapters covering all 38 objectives across the seven exam domains.

Intelligent token and context optimization for Claude Code — an Agent Skill + CLI that makes Claude smarter about what it consumes.

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

Go client library for interacting with the Anthropic safety-first language model REST APIs.

Production-ready Agent Runtime for Claude Code — Dashboard visualization, Team mode, Plugin daemons, Memory system, and one-command setup

Koro — voice-first AI agent that actually does things. Search, code, execute — all via Telegram voice.

MCP server giving Claude live access to SAP systems via ADT — read, edit, search, test, and diff ABAP across landscapes without installing anything on the SAP stack.

AI cloud-cost investigator. Dual-model (Opus + Sonnet) reasoning over AWS / GCP billing exports with a 7-layer command validator. Paranoid mode by default — never touches your cloud unless you opt in. By MatrixGard.

Claude Code plugin to spawn and manage autonomous background agents with persistent state, worktree isolation, and auto-completion hooks

Self-hosted family meal planner. A Claude-powered agent plans the week, builds the grocery cart, and learns what your household likes. Ships with Willys.se support. Store backends are pluggable.

The only fully open source Cloud Agnostic Semi-Declarative Python framework for AI agents. Build single agents or multi-agent teams with streaming events, parallel execution, and full observability. Cloud-agnostic, simple, no PhD required. Use its industry first Sixth Sense to have agents communicate globally in real time over any boundary.

Composable, model-agnostic AI agent skills for multi-agent analysis, verification, research, and multi-model council review. Works with Claude Code, Gemini, Codex, and OpenCode.

Connect OpenClaw agents across teams and enterprises to share, discover, and collaborate on custom automation tools securely and efficiently.

Send prompts to Claude.ai directly from your command line!

🏠🤖 HomeAssistant Add-on for Claude Desktop MCP integration. Control smart home devices, create automations, and manage your home with natural language through Claude.

Turn a YouTube URL or a thinker's name into a two-voice podcast — every quote checked verbatim, rendered locally by Kokoro TTS.

Claude Code handoffs that preserve decisions, failed approaches, constraints & next steps

A collection of self-improving Claude Code components. The /learn command extracts patterns from docs and code to permanently enhance your skills.