Anthropic agents

Stack-agnostic monorepo template where agents are the workflow: PM → implementer → fresh-context reviewer loops via Claude Code subagents, skills, and GitHub Actions

Unofficial Model Context Protocol server for Alza.cz — read-only catalog browser for AI agents. Uses Playwright to defeat Cloudflare bot protection.

Native Claude Agent SDK with Harness specialized become as team member.

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

Claude Code plugin & MCP server for searching award flights, comparing loyalty programs, and finding the best points redemptions. Works with Claude Code, Claude Desktop, and any MCP client.

Fixes broken prompt-caching for Claude Code and the Anthropic API - 8.2x cheaper

🦀 Clawd, a menu bar crab that shows your Claude Code sessions at a glance — walking while Claude works, bouncing when it needs you

🪨 Make Claude Code talk like a smart caveman ~75% fewer output tokens, 100% accuracy. Auto-enabled + statusline.

MCP server that connects Claude AI to Bitrix24 — CRM, tasks, disk, calendar, automations and more

Local, AI-native visual editor for single-file HTML — point at an element, say the change in plain language, review the diff + safety check, then write back. Never regenerates the page.

Rules your coding agent physically cannot ignore. Claude Code hooks that DENY the tool call and BLOCK the reply - stopping reactive patches, guessed citations, and premature 'done' claims. Also works as an LLM-agnostic rule pack.

Claude skill for spec-driven development: interviews you one question at a time until your unknowns run out, then harvests and verifies real open-source components. Turns an idea — or a half-planned project — into a PRD you can build from.

Open-source Agent Skill for Claude Code that makes Claude reason with explicit probabilities, base rates, and falsifiers. Distilled from 51 books; first in 18/18 blind passes vs baseline Claude and GPT-5.5, and benchmarked against 14 rival skills and prompt techniques with full cost telemetry (round 5).

MCP server for MAX messenger (max.ru) — user session, 8 tools: read chats, dump channels, send messages

Claude Code reimplemented in pure C — the lowest level it's ever been done

Three Claude Code skills for keeping a project's knowledge and your setup healthy: project-status (cold-start orientation), split-claude-md (CLAUDE.md maintenance), and salvage-session-archives (recover context from old session transcripts).

Highlight anything in a PDF, text or a figure, and ask about it without losing your place. A reading workbench for papers outside your field.

Self-hosted Pocket Claude — chat with Claude on your own Pro/Max subscription, Anthropic API key, or AWS Bedrock. Voice input via Groq Whisper + hands-free auto-mode with VAD auto-send. FastAPI backend + Android client + web UI. Multi-user, 7 languages.

Desktop app to switch Claude Code between any Anthropic-compatible provider (OpenRouter, gateways, local models) in one click. Safe, auto-backup, macOS/Windows/Linux.

Claude Code plugin that quizzes you on root cause and fix before it writes any code

A Claude Code copilot: flat /wise-* slash commands, a workflow engine, and autonomous git / PR / ticket-planning pipelines.

Claude in Chrome, powered by your local claude CLI. Drive your real logged-in Chrome from Claude Code, or chat in a side panel while you browse. No claude.ai login, no intermediary server, and it never steals focus.

MCP server that turns text prompts into premium iOS mobile UI mockups (PNG + HTML). Powered by Claude (Opus 4.7) + Playwright. Two backends: local CLI or Anthropic API. MIT.

Agent Skill that turns prompts into 9:16 animated explainer shorts — entirely in code (Python → SVG → ffmpeg, no browser, no After Effects).

Local MCP gateway with progressive tool discovery, description compression, and controlled access to large results.

Proven patterns for structuring any project so Claude Code operates at maximum autonomy — CLAUDE.md, skills, hooks, permissions, scripts, memory, MCP, monorepos.

End-to-end development skills for Claude Code: framework-specific expertise for frontend, backend, mobile, infra, and QA, with verification baked into every workflow.

Public credit-risk models report 0.90+ AUC using post-loan leakage. This one strips it and reports an honest 0.73, then runs a ReAct agent to audit the model.

Claude Code plugin that won't let the model skip steps

Free Claude Skill that formats & audits resumes so Workday, Greenhouse, Lever & iCIMS parse them correctly — no more blank Company/Dates/Title fields.

MCP server for multilingual dictionary lookups with word relations (synonyms, antonyms, hypernyms, translations, etc.) covering all languages via ConceptNet, Wiktionary, and Datamuse

Claude Skill for Seedance 2.5 / 2.0 prompt engineering (ByteDance, Dreamina, Jimeng, Doubao) — 6-block formula, @reference roles, staging, AI-UGC realism layer, native audio & lip-sync, debug matrix.

Global Claude Code config, synced between machines by one script: CLAUDE.md, writing rules, vendored skills and the bash environment commands run in, symlinked into ~/.claude and wherever Codex and other agents look

A collection of original skills independently designed and developed by Anna Tchijova, grounded in scientific methodology and established engineering best practices.

A memory hub and curated skill set for Claude Code — persistent memory that loads from any directory, plus a guided local setup.

Profile Claude Code context, discover repeated workflows, and regression-test your skills. Local-only, zero-dependency.

Three composable Claude Code skills that turn a one-line feature description into a production-quality vertical slice — persona, journey, UI, API, DB, tests — then implement it with atomic cycle commits.

CRBRO — persistent neural memory for AI agents (MCP server): a file-based brain with neurons, synapses and heat scores that survives across sessions. Works with Claude Code and any MCP client.

Agent skills that teach AI coding agents to use Decodo for web scraping

Claude Code integration plugin for DeepSeek Harness, providing native Claude conversations powered by the Claude Agent SDK, with approvals, session continuity, and DSH tool support.

中国大陆普通人三分钟用上 Claude Code——BYOK、无账户、不经手你的数据。MIT 开源。

Isolated Claude Code profiles via CLAUDE_CONFIG_DIR. No credential vault swap.

Windows system-tray monitor for Claude usage limits - live session/weekly meters, usage graph, alerts. Unofficial.

AI-powered WhatsApp receptionist that books appointments via Google Calendar. Built with FastAPI + Claude API.

Playing to Win strategy framework as a Claude Code skill. Pressure-test business ideas through Roger Martin and A.G. Lafley's choice cascade.

Run an open-source repo as its maintainer: triage the tracker, delegate the work, review hard, merge on green. One loop, one version, and per-repo differences in config instead of prose.

On-demand Model Context Protocol (MCP) server for Android — FCM push-woken, end-to-end encrypted via SNI-passthrough TLS, per-device ACME certs

PhanesLight as a Claude Code plugin: multi-agent orchestration and durable project memory. One command turns a repository into a wired, opinionated agent team. Manual install version at Aloim/phaneslight.

Agentic Engineering Worksheet — a trace-first handbook with labs, tiered Q&A

Modern, fully customizable Claude Code statusline. Single-file bash + jq, no plugin runtime, no network calls. presets, themes, 42+ data tokens, transcript-aware burn rate & cache hit metrics.

A Claude Code skill for quarterly AI fluency assessment using Anthropic's 4D Framework and Yegge's 8-Stage Developer-Agent Evolution Model

Turkish humanizer skill for Claude and Claude Code. Rewrites AI-sounding Turkish into Turkish a person would have written: native sentence architecture, register-aware dosing, technical terms kept. Türkçe humanizer / yapay zeka metni insanlaştırma.

Local OAuth proxy that auto-rotates Claude Code accounts across usage limits on macOS and Linux.

Claude.ai quota in the Chrome toolbar and the macOS menu bar — the extension plus a Swift menu bar app, one bar per account, fed over a loopback bridge.

26 Claude Code skills used daily on real projects: adversarial code review, shipping rituals, marketing asset pipelines, iPhone and desktop control, and multi-agent orchestration.

Research-grounded Agent Skill for writing professional LLM prompts — matches technique to model class, separates evidence from folklore.

A native macOS Kanban harness for Claude Code — cards are agent sessions that move themselves

Public Claude Code plugin marketplace — installable skills and agents for AI coding agents. Drop-in capabilities you add with one command.

Evidence-backed verification for action-taking AI agents. Compile the task into a contract once, then verify every run against real state and trajectory evidence with zero model calls.

Progressive Recursive Agentic Vulnerability Assessment Lifecycle — self-hostable agentic AI framework applying continuous LLM reasoning across all 10 phases of enterprise VA with progressive context chaining.

Open-source AI interior design agent. Turn room photos into scaled floor plans, wall elevations, photoreal renders and a design report where every change is justified. Runs as a team of agents in Claude Code.

Awesome list for Claude API usage: Console, docs, cost and usage reporting, pricing, cloud partners and alternatives.

GLAW — open-source virtual law firm AI-agent system: 183 skills, 181 commands, hard-gated matters, MCP/API intake, and X402 paid-agent charge matrix with Conway-style agent survival. Attorney work-product for licensed review, not legal advice.

MCP server for Zotero 10+. Read and write your library entirely offline through Zotero's native local API. No plugin, no API key, no cloud.

Seven universal skills, context file templates, global instructions, and a curated prompt library for Claude Co-work.

Free Calendly alternative run by a 24/7 AI agent: syncs all your calendars, finds the time that works across them, and books meetings for you, over WhatsApp, Slack, or the web. No irritating setup, and your data stays local.

Claude Code skills for content creators. Cut silence from video, normalize audio, remove filler words.

The open-source Claude skill for UI/UX design. 84 UI styles, 192 color palettes, 74 font pairings, 99 UX guidelines & 161 industry rules across 22 stacks. Works with Claude Code, Cursor & Windsurf.

Talk to Claude Code on your own machine, from your phone, over Telegram. No tunnel, no webhook, no cloud relay.

Run Claude Code natively inside Oh My Pi — AskClaude tool + switchable 1M/200K context window

Offline HTML viewer for Claude Code JSONL session transcripts. Six UI languages, light/dark theme, no backend, no CDN.

A Claude Code plugin that turns the words you reach for while working into your own study material. Instead of someone else's word list, you learn the language your real projects speak, and you review it right where you work. Everything stays on your computer. Build your own Quizlet or Duolingo out of your own data.

Copy-paste Claude Code hooks that actually do something — auto-format, block dangerous commands, test gates, notifications. Dependency-free, current schema.

Claude Code plugin: run several agents in parallel from one terminal — a dispatcher, a worktree per task, and docs as the single source of truth.

MCP server for Yandex Webmaster — SEO, indexing, search queries (Russia). Part of WWmcp — 114 MCP servers for emerging markets.

tig-style terminal (TUI) viewer for Claude Code & antigravity & opencode session logs — read-only, reads ~/.claude/projects directly, no copying

A task board Claude fills in for itself: a Claude Code plugin that mirrors Claude's task list onto a per-project board, with MCP tools and a local web panel.

Chrome Bridge by frsorrentino — your real, logged-in Chrome as an MCP server for Claude Code: 60 measured, token-efficient tools. ChromeOS included.

MyCase MCP. Connect Claude to your MyCase legal practice management system. Ask Claude to look up cases, find contacts, check your calendar, review billing — all without leaving your conversation.

Claude Code skill: review and modernize legacy Java 8 code to Java 21 with AI. Generates a 1-100 score. Specialized for financial systems.

Claude Opus 5.5 directs and renders films in JavaScript: brief → sound (file, YouTube, generated, or AI voiceover) → director's treatment → frame-exact MP4. A Claude Code skill + plugin.

Interactive human-in-the-loop desktop GUI & Model Context Protocol (MCP) server for AI agents

Lightweight Claude Code status line — one ~170-line Bash script, zero dependencies (no jq, Node, Python, daemon or config). ~8 ms per render. Session name, git branch, model, effort bar (with ultracode), context window, 5h/7d rate limits, prompt-cache countdown.

Official Instagram Graph API MCP — multi-account read, publish, comments, analytics + review-gated DMs for Instagram Business/Creator accounts. ToS-safe, no private API.

Unlock Claude Code with DeepSeek V4. Get Anthropic's agent tools with 95% lower costs and local vision.

Self-hosted AI agent platform

Smart status line for Claude Code — model, cost, context, usage limits, VPS health with auto-focus. Pure bash + jq, no Node.js. Featured on Habr (9.3K reads).

Terminal-aesthetic OpenClaw Gateway control panel — real-time agent monitoring, billing-aware cost display (subscription/API/local), Subdued Succulent theme, Chart.js telemetry

Terminal-based multi-agent orchestrator for Claude Code — run AI coding agents across multiple repos with a unified TUI, DAG-based task scheduling, and AI-powered coordination

LLM-driven financial sandbox town · NPCs gossip, form opinions, trade · Built with FastAPI + Anthropic + Godot 4.5

Autonomous Terraform agent — takes a prompt or Jira ticket, runs a full validation pipeline, and opens a GitHub PR. No human in the loop.

Daily curated news digest for your domain. Claude Code plugin. Zero API keys, fully local.

Document-based project control for AI-human collaboration: an append-only event log plus a generated status projection, so any agent can take over a long-running project from files alone. Optional deterministic guard toolbelt.

A Claude Code plugin that transforms business plans into production-ready products through Plan Casting — a 25-stage AI agent pipeline. Try the Transmuter app at transmuter.3mergen.com

Bio-inspired swarm orchestrator for Claude Code. 16 mechanisms from honeybee and ant colony research, 148 algorithmic tests. One file, zero dependencies.

Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a deterministic Elixir semantic graph and agent-ready Repo Map for LLMs.

UFC-style visual arena where two AI agents compete on coding tasks. Electron + React + pixel art fighters.

A minimal, fully commented Python executive AI agent. For students, teachers and junior devs who want to understand agentic AI from the ground up.

AI RAG agent that reads company documents and answers questions like a trusted senior colleague. Built with Claude API, FastAPI, React, ChromaDB.