Havuz

Six Claude Code skills that harden Opus 4.8 toward frontier behavior. Written by Fable 5, pressure-tested on the target model with transcrip

A Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.

Decoding Claude Code's leaked 512K-line source — hidden features, 43 tool definitions, system prompts, architecture patterns

增强 macOS Finder 右键菜单的轻量工具 · Supercharge the macOS Finder right-click menu

See which AI coding agent needs you — right in your tmux tab bar. A colored dot per window (working/blocked/idle) with off-screen sound aler

Convert Tabbit browser’s internal API into OpenAI and Anthropic Claude-compatible interfaces for seamless multi-account AI service integrati

Rust External 2026 - Full working installer for advanced software configurations and utilities.

Codex 三層多代理協作 Skill：Sol 統籌與複雜推理、Terra High／XHigh 處理視覺與操作、Luna Max 執行可重複工作。

A Dynamic Island for Windows: Claude Code & Codex usage, now playing, focus timer, calendar and system health in one native capsule. Local-f

One command, one throwaway public link for your localhost, several ports behind it (your app and its API). Then run your demo live: chat wit

Tells your AI agent which parts of your idea already exist on GitHub, which to adapt, and which to just write — every repo verified live. MC

A free, fast, native macOS Git client built with SwiftUI. Full commit graph with real topology, inline diff/blame, merge & rebase with confl

Run multiple Antigravity IDE profiles at the same time — each with its own accounts, settings, and extensions.

Open source Agentic Development Environment

Track what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tool

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

Anthropic API reverse proxy with prompt-cache injection and request body transforms

Safe Codex CLI setup installer with skills, AGENTS.md, profiles, and MCP defaults

Architecture-aware code search, dependency graphs, and impact analysis for Python, TypeScript, Rust, C#, Java, Go, Ruby, Rails, Free Pascal,

A multi-agent Dynamic Island for AI coding on macOS, with a lighter Windows edition. Track Codex, Claude Code, DSH and Kimi Code on both; ma

One command to turn any codebase into an MCP server

Generate Google Stitch compatible DESIGN.md files from any website using AI vision. Bring your own Gemini, OpenAI, Claude, or Ollama key. No

跨 agent 的 skill 管理器 + skill 推广工具，欢迎fork和pr。管理你所有 skill ，创建技能自带讲解pdf或ppt。支持各种Agent。

Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, o

Multi-agent Claude Code skill for building apps and stuff

项目成熟度审计工具：检查 GitHub 仓库、npm 包与网页，输出证据和整改清单。 / Project maturity auditor for GitHub repositories, npm packages, and websites with evidence-base

A native macOS menu bar app that shows your Claude.ai usage at a glance — colour-coded icon, live counter, reset timer. No API key needed.

AI commit messages from your local LLM - Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes.

The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability

adOmnia is the open-source, Go-powered IDE built for the AI era. Let agents write the code. You take control: run, test, debug, and ship, al

Free AI code reviews on every pull request. Bring your own key (OpenRouter free tier works), runs in your repo as a GitHub Action - no quota

Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows w

Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite st

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

Development discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search. Single plug

CodexMeter：本地运行的 Codex 用量监控桌面工具，支持 5 小时 / 7 天额度、重置时间、小组件和本地安全存储。

Turn private work into an NDA-safe credential that shows what you can build — and companies can trust more than a CV.

The remote-native terminal: your shell, the machine it runs on, and its files in one window. Durable SSH sessions, remote files, GPU and por

A local-first developer desktop workspace for databases, Git, SSH, object storage, and clipboard history.

Turn scattered, duplicated AI-agent Skills into per-Agent Rosters—with evidence, receipts, and exact undo.

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Archive pasted Codex chat images locally before temporary clipboard files disappear.

Minimize AI and Agent failures into minimal reproducible traces.

Write your repo rules in Markdown. AI enforces them — triages issues, reviews PRs, fixes bugs, merges code, cuts releases.

One-command installer for all AI Marketing Hub tools: Claude SEO, Claude Blog, Skill Forge, WP MCP Ultimate

A one-click installer that scaffolds a complete GitHub Copilot agentic coding environment into any project

Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

Context retrieval engine for AI agents — semantic + lexical search over codebases

A blank, working source of truth for Claude Code and Codex across macOS and Linux.