Anthropic agents

Agentic-DART — autonomous detection & response agent. Architecture-first, not prompt-first. Starts as agentic DFIR; designed to expand toward agentic SOC and beyond.

66 curated Claude Code skills for Flutter / Dart development, testing, release, and AI-assisted design-to-code pipelines.

Run Claude Code from a USB drive - no installation required. Downloads the official binary, stores all config portably. Windows, macOS, Linux.

Claude Code deletes your sessions after 30 days. Save them — config, chat history, daily auto-sync, machine migration.

Svensk komplement-stack till Anthropics Claude for Small Business. 11 Claude Skills för Bokio, moms, AGI, K10 och svenskt regelverk.

🎨 Extract complete design systems from websites and generate AI-ready skill.md files to replicate exact design elements efficiently.

A suite of plugins for freight forwarding workflows — air, sea, road, rail, and time-critical. Maintained by DCS Premium Freight SRL.

MCP server for Standard Notes with end-to-end encryption (protocol 004). Read/write notes from Claude while keeping E2EE intact.

A Claude skill for rigorously solving math problems — equations, proofs, optimization, geometry, and more, with step-by-step reasoning and verification.

Open-source CLI for managing private React component registries — publish, install, search, and share components with your team. Works with any AI agent that supports SKILL.md (Claude Code, Cursor).

Claude Code usage tracker and local dashboard for Pro/Max subscription limits - weekly cost-per-percent trend, quota forecasts, threshold alerts. ccusage-compatible.

Still trusting results that AI generated, tested, and declared successful by itself? This Claude Code methodology adds evidence markers, audit gates, anti-hallucination rules, and Validation Theater detection to keep AI-assisted development verifiable.

说人话 — AI痕迹消除与文本人性化改写,查重率从60%降到30%以内

29 free, open-source plugins for Claude Code & Cowork — Google Drive, WhatsApp, YouTube, WordPress, Apollo & more. Built on the SOSA™ security framework.

A context-first, spec-driven, strictly sequential development workflow plugin for Claude Code — keeps your CLAUDE.md/.claude spec always fresh and grounds every decision in Context7 + Microsoft Learn.

Give an LLM a URL and a goal — it drives a real browser, fills forms, and returns structured data. The browser that scripts itself.

High-performance Model Context Protocol (MCP) server gateway for Claude Pro. Seamlessly bridges Claude Web UI with local environments, file systems, and secure execution layers.

HERO - Harness for Engineering and Run-time Orchestration: a runtime control system around foundation models for autonomous software-engineering missions.

Keep Claude Fable 5 (or Opus) as your daily driver without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: model-tier routing, Requirements Ledger, enforced guard hooks

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai K-12 segment — School Assistant orchestrator plus 12 specialist subagents.

Local-first Rust CLI that tailors your resume to a job posting through an adversarial agent loop, and never invents experience you don't have.

The clean slate a fresh Claude Code should start from — clean context, locked credentials, guarded egress. Isolated profile, pick-and-choose.

Read job-alert emails, score fit with AI, get a ranked summary via email.

See how many tokens your AI coding agents really burned.

🔊 Cross-platform Claude Code plugin that plays distinct sounds when Claude finishes a task vs. when it needs your input — so you know whether to check results or go respond. Works on macOS, Linux & Windows. Non-destructive install, no config files touched.

Never lose your Claude Code session. A macOS launchd agent that pings Claude every 4 hours to prevent the 5-hour quota window from expiring.

John, an agent harness designed for building knowledge-dense applications.

Desktop multi-agent orchestrator for the Claude Agent SDK. Command a hierarchy of AI agents — chiefs, specialists, advisors, workers — with CodeGraph code intelligence, Claude-Code-grade context compaction and per-agent cost tracking. Open-source agentic AI / Claude orchestration.

An open-source agentic harness for scientific literature analysis. Coordinates frontier models to extract data, replicate findings, and perform systematic reviews with full provenance tracking.

Self-hosted, secured HTTP API around headless Claude Code — per-app keys, all tools locked off, zero deps. Use Claude from your own apps.

Bring Fable-style design taste to any AI coding agent. Free MIT design system for Claude, Opus 4.8, Codex, Cursor, Gemini & Antigravity. By Dr. Antoniou, free from UploadCheck.

Reversible macOS patcher for Claude Desktop ASAR tweaks, including third-party inference routing, Computer Use experiments, and an optional desktop pet overlay.

Audit your Salesforce RevOps. Then fix it. A Claude Agent Skills pack for Salesforce admins and RevOps practitioners.

Agent Skills for BESSER — deep BESSER knowledge for AI coding agents: UML class modeling, code generators, troubleshooting, and contributor workflows.

把 Anthropic 官网发布的技术博客内容，转化为中文音频解读，让你在碎片时间听懂最前沿的 AI 发展

AI-powered Fortune 500 business operating system for Claude Code — 15 executive agents, governed initiative lifecycle, Decision Authority Matrix, and 17 slash-command workflows.

AI-901 (Azure AI Fundamentals) study buddy built natively for Claude Code: exam-realistic questions, Microsoft Foundry labs, and study plans, grounded in Microsoft Learn via MCP, with subagents, skills, slash commands, and deterministic hook guardrails.

A principal-level, 16-division multi-agent Council for Claude Code. Drop-in ~/.claude/ config: 15 Floor + 160 Library rules, 121 skills, 32 agents, 33 commands, 14 hook-enforced quality gates. Runs on any machine, any project, every IDE. MIT.

Chrome extension for translating supported AI courses into 32 languages with local study tools and exam-safe translation

The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.

Compile any Claude Agent Skill into a multi-agent Workflow — a meta-workflow that recovers the parallelism hidden in a skill's prose and emits a fan-out · pipeline · adversarially-verified Workflow.

oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.

🪄 A terminal AI coding agent — BYOK, 12 providers, MCP, and a second-brain that gives the AI durable cross-session memory. Built from scratch in TypeScript.

Build file-backed, self-evolving Agent Cores.

30 free, verified agents, skills & packs for Claude Code - install with 'npx vanara install <name>'. Apache-2.0. From the Vanara catalog (213 items).

YOLO — a reasoning-first, feature-aware workflow framework for Claude Code. Git is the source of truth; status is derived, never stored.

Skill router and context picker for Claude Code, Cursor, and Aider. Auto-picks the right skill for every prompt, with prompt-injection filtering for MCP.

Local-first, multi-agent job-search assistant: finds close-match roles and tailors your résumé + cover letter to the ones you choose. You review and send — never an auto-applier. Runs on your own Claude subscription.

Discipline + security starter kit that keeps Claude Code (or any LLM agent) on course across sessions: repo-based memory that survives compaction, enforced hooks & permissions, and a phased workflow — consistent, traceable, safe. Clone it or install as a plugin.

Agent-specific payment workflows and examples for TDM

Turn a how-to video into a reusable skill for your AI coding agent — watched locally, no API keys.

A configurable status line for Claude Code - model, effort, workspace, and live context/rate-limit, claude usage monitor bars.

A cache doctor for Claude Code: find the money your prompt cache is leaking.

Self-hosted, privacy-tiered memory for your AI agents.

CLI + Claude Code plugin that spends your Claude Code subscription 5-hour quota on real parallel work, stopping at a threshold. Metered against the real Anthropic usage endpoint.

Local-first CLI that audits Claude Code transcripts for spend by model, avoidable context-carry waste, always-on config cost, and AI-fluency signals. Runs fully offline by default; opt-in tiers gate any egress.

Build, edit and run Glaze (Raycast) Mac apps from Claude Code or ZCode for free, using your own subscription instead of Glaze credits. Then publish to the Glaze Store.

Remove Claude/AI attribution from a GitHub repo in one command clean commit history, force-push, and refresh the Contributors graph so @claude disappears.

The battle-tested Claude Code kit behind HasBrainsAI — agent skills, subagents & slash commands for production multi-agent systems. Install in one command.

Model Context Protocol servers for the official Robinhood Crypto Trading API — the credentialed brokerage API at trading.robinhood.com, documented at docs.robinhood.com/crypto/trading.

Android home screen widget to track your Claude AI usage. Sideloadable APK.

Auto-updated index of MCP servers shipping on GitHub, refreshed every 15 minutes

The structurally-verified context layer for AI coding agents. Cut 50-90% of your agent's token spend.

Exacting Agent Skills for serious thinking, reading, research, and translation.

Cut the cognitive overload of orchestrating many Claude Code agents: a tiny desk device (Arduino + OLED, macOS) that shows which session needs you and jumps you to it. Personal/non-commercial (CC BY-NC 4.0). ESP32 Wi-Fi remote next.

Native macOS menu bar app showing Claude Code usage (session / weekly / Sonnet / credits) — no backend, notarized, brew install

A clean multi-line status line for Claude Code: context bar, grouped 5h/7d rate-limit bars with a pace overlay (target + over/under delta), git branch, token count and session time.

An experimental OpenClaw skill for Agent-to-Agent Marketplace based on Anthropic concept

The workspace layer for Claude Code — browse every session, persistent project memory, MCP awareness, and per-project launch control. Terminal UI and desktop GUI. Zero runtime dependencies.

AI-generated animated explanations of code — paste any function, get a cinematic animation of what it does

Autonomous web-app pentest engine — a multi-agent pipeline wielding 30+ offensive-security tools as skills, PoC-validated findings. Built on Anthropic's defending-code harness + Building Effective Agents.

Open Model Hardware Standard - AI agent hardware control

See what Claude Code actually did. Local-first observability for every session: which tools ran, what each sub-agent was told, which turn blew the budget. Cost, tokens, error alerts, full-text search. SQLite on your machine, nothing leaves it.

Agentic-DFIR — autonomous digital forensics & incident response agent. Architecture-first, not prompt-first: typed read-only MCP tool surface, SHA-256 audit chain, senior-analyst playbook.

Caveman mode skill for Claude. Fewer output tokens, longer usage before hitting limits.

An opinionated agentic workflow to turn well-defined units of work into shippable code with minimal human input.

Open-source collection of shared AI agent skills for emdly.com.

Claude Code skill: Fable 5.1 decides, Opus 5 / Sonnet 5 / Haiku 4.5 execute. Five wiring patterns (advisor, architect+delegate, agent teams, workflows, /goal), effort routing, fallback traps, 16-block prompt kit, pinned agent lanes.

"Infrastructure for continuity across discontinuity — for AI instances and the humans who work with them."

从 PRD/产品点子到可运行 Agent 产品的架构蓝图与参考实现，包含 17 个 Harness 组件、生产级脚手架、技能模板和测试。

Many Claude Code projects. One window. Zero hunting. A lean, dark, macOS-native lite IDE for the power Claude Code user.

Chrome extension for translating supported AI courses into 32 languages with local study tools and exam-safe translation

Claude Sonnet 5 API examples in Python: claude-sonnet-5 quickstart, effort levels, and migrating from Sonnet 4.6.

Mission control for Claude Code: see and steer every session, subagent, /loop and todo list from one local dashboard. Zero dependencies.

A pixel-art mission control for your Claude Code agents — every project is an office, every agent is a character

Full unofficial agentic Infomaniak MCP server — guided automation of web hosting, mail, kDrive, domains and DNS.

Claude Code plugin: Full-lifecycle open-source contribution workflow. 12 phases from issue discovery to PR merge. /contribute command.

Local-first memory, observation, and autonomy layer for Claude. A background daemon that learns from your sessions.

Bast is a free, open-source CLI built to bring security to AI-powered terminal operations. It integrates with Bastio AI Security Gateway to protect your data before it reaches the LLM.

Web admin panel and MCP server for Claude Code — phase gates, scope locks, and human approval for agentic coding sessions.

Give Claude Code persistent memory across sessions. Hybrid BM25 + vector semantic search, auto-structuring via LLM, and 4-channel retrieval (MCP + hooks). Your AI assistant finally remembers.

Autonomous research agents for Claude Code - passively research and inject helpful context

Plug vas3k.club into your AI — search members, cite posts, pull links right in chat. Remote MCP server on Cloudflare Workers.

Discoclaw: CLI-first Discord bridge for agent runtimes

Your repo's engineering department. 7 AI agents ship PRs autonomously — from coverage gaps to features. Zero dependencies. Just Claude Code.

Discord AI 多智能体团队（明朝六部制）：兵部/户部/礼部/工部/吏部/刑部/司礼监。Claude 驱动，Oracle Cloud 免费服务器一键部署。Clawdbot skill。

A personal orchestration tool for Claude Code agents

Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.

Claude Code plugin that scaffolds a validated multi-agent ecosystem (orchestrator + N sub-agents + M skills/MCPs) from a natural-language brief. A step up from skill-creator — with semantic validation, trigger-fire evals, and custom MCP scaffolding.