Claude
Tools

Custom Claude Code plugin with an autonomous agent and 7 rules for AL development in Business Central Per-Tenant Extensions.

Author, scaffold, and debug multi-agent workflows for Claude Code's Workflow tool — a skills-only plugin plus @workflow-toolbox, a compile-time TypeScript pattern library. Research preview.

VSCode extension for Claude Code + DeepSeek: real-time balance & token usage in the status bar, powered by local JSONL parsing — no proxy, no key exposure

Chrome extension designed to allow users ability to capture job from seek & linkedin. Update status and view stats in the jobs you capture and the

A repository combining skills and methodologies from superpowers, claude-code-security-review, Anthropic-Cybersecurity-Skills, theHarvester, and hackingtool for AI agents.

ResearchX — AI Research Operating System. Literature-driven AI research assistant for full scientific lifecycle.

Multi-agent orchestration framework for Claude — tool registry, memory, parallel runners, orchestrator/worker topology

Multi-step code review agent on Anthropic Tool Use, packaged as a GitHub Action. Three guardrails prevent runaway behavior.

Local bridge for the ChatPanel Chrome extension (Claude Code + Codex)

Pi extension to built with pocketflow dynamically workflows. Inspired on Anthropic's dynamic harness: https://claude.com/blog/a-harness-for-every-task-dynamic-workflows-in-claude-code

Chrome extension + local MCP server that lets any AI (Claude Code, Gemini CLI, or your own local LLM) drive your real browser session — no Playwright, no separate profile. Screenshots, page snapshots, clicking and typing with a visible cursor, plus a side-panel chat assistant for any OpenAI-compatible local model (Ollama, LM Studio, vLLM).

Symposium (συμπόσιον) — VS Code extension hosting dialogue sessions with multiple AI agent CLIs (Claude Code, Codex, Copilot)

VS Code extension that keeps Claude Code's Anthropic prompt cache warm — auto-pings before the 5-minute TTL expires.

The npm-audit for MCP servers: scan AI agent tools for dangerous permissions, prompt injection, and data exfiltration risks.

VS Code extension that syncs AI setup files and MCP configs (Claude Code, Copilot, Cursor, Codex, Antigravity and more) from a GitHub repo into every project automatically.

Companion layer for the Feishu <-> Claude Code bridge: make it work behind a proxy (proxy-split), a /ctx context-usage readout, and an ops playbook. Not a fork.

Minimal AI agent template in Python (Claude) — agentic tool-use loop, no framework

Agentic AI coding desktop (Claude + Ollama). 4-layer architecture: tool manifest + persona shell + briefings + WORM unlock layer. Electron + React + Node.

MCP server giving Claude full Telegram tools (read/send/edit/pin/react/files)

A harness for testing, benchmarking, and tuning PostgreSQL extensions in an isolated, reproducible environment.

Enhance the tool-calling capabilities of your Claude Code, enabling it to deliver performance comparable to or even surpassing Anthropic Opus 4.7 when utilizing APIs of other models such as Qwen, DeepSeek, Kimi, and Gemma.（增强你的claude code的工具调用能力，让你使用qwen、deepseek、kimi、gemma等其它模型api时，能够获得接近甚至反超anthoropic opus 4.7的水平。）

Reach your own Claude Code from a Slack DM — local brain, your tools & memory, Socket Mode, single-owner. MIT.

Drop-in vision capability pack for text-only reasoning LLMs. Contains an MCP server (mcp-vision-extension) and a companion Claude Code skill, locked into eyes-only mode. 给纯文本推理大模型即插即用的视觉能力扩展包。包含一个 MCP server（mcp-vision-extension）和一套配套的 Claude Code skill，全程锁定在"只当眼睛、不抢推理"的描述模式。

Reusable patterns for personal agentic automations — YouTube monitoring, free transcription, CrewAI tools, GitHub Actions scheduling, and attributed-sentiment prompting