thehardwarestore.ai

unslop is a CLI tool that empirically detects repetitive defaults in AI-generated outputs (text or visual) and produces a reusable instruction file (skill.md) to eliminate those patterns. It works by generating a set of prompts for a given domain, running them through Claude Code to produce samples, analyzing the samples for repeated patterns (phrases, structures, visual defaults), and writing a focused 'unslop profile' that tells the model what to avoid. The tool supports both text domains (blog writing, emails, tutorials) and visual domains (landing pages, UI mockups) with optional screenshot rendering via Playwright. The architecture is a single Python script (unslop.py) that orchestrates a multi-step pipeline: prompt generation, sample generation via parallel Claude Code calls, screenshot rendering (visual only), pattern analysis, skill file generation, and a before/after comparison. It uses asyncio for concurrency, a custom terminal UI with live spinners and progress bars, and a robust subprocess wrapper for the Claude CLI that handles streaming JSON output, timeouts, retries, and permission denials. Key entry points are the CLI arguments (--domain, --type, --count, --concurrency, etc.) and the main async run() function. External dependencies are the Claude Code CLI (claude command), Python 3.10+, and optionally Playwright for visual domains. The output is a directory (unslop-output/) containing the skill file, analysis, prompts, samples, screenshots, and before/after comparison. The code demonstrates solid async patterns, clean separation of concerns within a single file, and a well-designed terminal UI abstraction. It is not a library but a self-contained tool that could be adapted for other AI model backends by replacing the claude() function.

This repository implements a Model Context Protocol (MCP) server that exposes the QuickBooks Online API as tools for AI agents such as Claude Code. It provides 143 tools covering full CRUD and search operations across 29 entity types (Customer, Invoice, Bill, Vendor, Employee, Account, Item, JournalEntry, Deposit, Transfer, TimeActivity, etc.) and 11 financial reports (Balance Sheet, Profit & Loss, Cash Flow, Trial Balance, General Ledger, etc.). The architecture follows a clean separation between handler modules (wrapping the node-quickbooks library with OAuth authentication) and tool definitions (Zod schemas registered with the MCP server). A singleton QuickbooksClient manages OAuth 2.0 token refresh and persistence, while environment feature flags (QUICKBOOKS_DISABLE_WRITE/UPDATE/DELETE) suppress tool categories. The codebase is heavily tested with Jest (100% coverage enforced in CI) and uses modern TypeScript (ESM). It handles QBO-specific quirks such as automated sales tax (AST), sparse vs full updates, and fallback patterns (e.g., delete via void/inactive). Despite its broad coverage, the implementation is highly repetitive (87 handlers, 90 tools) with liberal use of `any` types and hand-rolled ambient declarations for missing upstream typings. The project is actively maintained with recent commits and detailed design documentation, though version numbers and test counts show minor drift between README and CHANGELOG. Overall, this is a comprehensive, production-grade integration that prioritizes completeness and correctness over elegance.

The Kickbacks extension is a VS Code extension that monetizes IDE 'thinking' spinners in Claude Code and Codex by rendering clickable sponsored ads and sharing up to 50% of ad revenue with developers. It operates as a modular TypeScript application with a complex activation orchestrator managing subsystems for authentication, ad rotation, metrics, earnings, kill switch, consent, self-update, and UI components. The extension uses a local loopback server for secure communication between the extension and injected code in webviews/CLI, implements feature flags via sentinel files, and employs OS-native credential storage. Its architecture centers around adapters for Claude Code (webview and CLI) and Codex (webview), with centralized state management and serving gates controlling ad display based on kill switches, user preferences, and canary states. The code demonstrates strong engineering practices in areas like secure token handling, deduplication, and resilience patterns, though it remains tightly coupled to its specific ad-serving backend and third-party tool integrations.

EvoNexus is an AI-powered business operating system with a dashboard for managing various applications and services. It has features for managing systems, knowledge base, and user authentication, and uses Docker for containerization.

This repository is a curated collection of skill plugins for AI coding agents such as Claude Code, Codex, and Cursor. Each skill is a self-contained directory with a SKILL.md descriptor, executable scripts, reference documents, and templates. The ecosystem covers a wide range of capabilities: multi-provider media generation (images, video, audio), browser automation via CDP, macOS app telemetry auditing, document format replication, open-source preparation (secret scanning, license generation), Cloudflare Workers deployment, trend aggregation, and video processing. The skills are designed to be invoked by an AI agent reading the SKILL.md and executing workflows via CLI scripts. While primarily an application-oriented collection, some skills (e.g., happy-app-audit) incorporate data analysis and reverse-engineering methodology, giving it a hybrid character. The architecture is modular: each skill is independent, with consistent patterns for provider abstraction, async polling, and template-based output. This makes the repository a practical toolkit for extending agent capabilities rather than a standalone production service.

AgentHub (also known as Maestro) is an Electron desktop application that orchestrates a virtual software development team of 46 AI agents powered by Claude Code CLI. The system enforces a 'Harness Engineering' methodology: Skills (standardized slash commands), Hooks (pre/post tool interceptors), Gates (quality checkpoints G0–G6), and FileWatchers (auto-sync markdown files to database). The GUI is intentionally limited to monitoring and three core operations—most workflow is driven by slash commands within Claude Code sessions. Architecture follows a three-layer pattern: Vue 3 + TypeScript renderer communicates via Electron IPC (contextBridge) to a main process with ~16 singleton services (session-manager, task-manager, gate-keeper, hook-manager, etc.). Persistence uses sql.js (SQLite in-memory) with a debounced disk save and 13 migrations. The source of truth is markdown files in `.knowledge/` and `.tasks/` directories, which are watched by chokidar and synced to the database. The app supports bilingual UI (zh-TW/en) and runs on Windows, macOS, and Linux. Key features include: sprint-based project management with task dependency tracking, interactive terminal sessions (xterm.js + node-pty), cost tracking per session, Git integration, a gate pipeline with review workflows, and a skill/hook management system with hash-based idempotent deployment. The codebase is well-structured with reusable components and services, though it shows some technical drift (alpha dependencies, brand name mismatch, Windows-specific paths) and high complexity from the extensive agent definitions and knowledge base.

CodexMCP is a lightweight MCP (Model Context Protocol) server that acts as a bridge between Claude Code and OpenAI's Codex CLI. It exposes a single `codex` tool that allows MCP clients to invoke Codex CLI sessions programmatically over stdio. The server handles session persistence via UUIDs, supports multi-turn conversations, parallel execution, and sandboxed workspace modes. The core implementation consists of a subprocess wrapper that streams JSON lines from Codex's `exec` command, parses agent messages and thread IDs, and returns structured results. It also includes Windows-specific command-line escaping to handle prompt injection safely. The codebase is minimal (two source modules plus a CLI entry point) but demonstrates solid patterns for wrapping external CLI tools in the MCP protocol, with graceful shutdown handling and error reporting. It does not include tests or CI/CD configuration, but the architecture is clean and focused.

This repository is a curated list (awesome list) of AutoResearch use cases, implementations, benchmarks, and forks. It does not contain any source code, data, or executable components. The sole content is a README.md file that organizes links to external projects, each with descriptions and links to optimization traces. The repository serves as a directory for the AutoResearch community, not as a software application or data research pipeline. It is a static documentation resource with no runtime behavior, architecture, or data flows.

This repository implements a meta-skill (ex-skill) that generates digital personas of former romantic partners by analyzing chat histories from WeChat and iMessage. It is designed to be consumed by AI agent runtimes like OpenClaw, Claude Code, or DeepSeek Harness via the AgentSkills standard. The system guides users through conversational intake of relationship details (astrology, MBTI, attachment style), automatically decrypts and extracts WeChat/iMessage chat databases, analyzes communication patterns using LLM prompt templates, and writes a structured persona skill that can be interactively chatted with. The codebase consists of a SKILL.md orchestrator, six detailed LLM prompts (intake, analysis, persona builder, merger, correction handler), four Python tools (database decryption, message parsing, skill file management, version management), and an example persona. It is a specialized tool for cyber-immortality and digital persona creation, blending reverse engineering with psychological profiling.

This is a leaked internal source of 'Claude Code', a terminal-based AI coding assistant CLI built by Anthropic. The application is a monolith written in TypeScript with React/Ink for terminal UIs, running on the Bun runtime. In production, it provides an interactive REPL that connects to Claude LLMs to perform software engineering tasks: reading/writing files, executing bash/PowerShell commands, searching code with grep/glob, managing git operations, spawning sub-agents, running MCP servers, and more. It features a sophisticated permission engine, plugin ecosystem, skill system, IDE bridge (VS Code/JetBrains), and remote session support. The architecture is centered around a QueryEngine that orchestrates LLM API calls with streaming, tool loops, and retries. There are ~40+ tools (BashTool, FileEditTool, MCPTool, etc.) and ~50+ slash commands (/commit, /review, /config, /doctor). The codebase is extremely large (~1900 files, 512K+ lines) with significant internal complexity. However, it contains many stubs for removed internal packages (@ant/*, @anthropic-ai/mcpb, etc.), heavy use of bun:bundle feature flags, and countless ant-only conditionals (process.env.USER_TYPE === 'ant') that gate internal-only features. This means the source cannot be run as-is without Anthropic's infrastructure. While the engineering quality is high in places (clean TypeScript with Zod schemas, well-structured tool pipelines, a custom Ink renderer with Yoga layout), the codebase is not designed for external reuse or portability. It requires Bun, has many hardcoded internal service URLs, and the stubbed packages would need real implementations. For learning and inspiration, however, it offers excellent examples of: terminal UI architecture, permission engines, plugin systems, and AI agent tool frameworks.

DemoGPT is an open-source Python framework that provides two core capabilities: (1) an automatic Streamlit application generator that converts natural language descriptions into complete, runnable Streamlit apps through a multi-stage LLM pipeline (planning, task decomposition, code generation, assembly), and (2) the DemoGPT AgentHub, a modular library for building AI agents with built-in tools (web search, code execution, Wikipedia, weather, etc.), two agent types (ToolCallingAgent for single-step tasks, ReactAgent for multi-step reasoning), and a RAG (Retrieval Augmented Generation) system supporting Chroma, FAISS, and Pinecone vector stores. The codebase is primarily a library/application hybrid, with the Streamlit app acting as both a user interface and a demonstration of the generation pipeline. The architecture separates concerns into chains, prompts, task definitions, and controllers, but many components are tightly coupled to the specific generation pipeline. The AgentHub portion is more modular and reusable. Technical drift is medium: the code uses deprecated LangChain APIs (LLMChain, Chain.run), hardcodes older models like gpt-3.5-turbo-16k in some generated code, and has a broad dependency range. Maintenance appears active with recent commits and responsive issue triage, but the codebase would benefit from modernizing to LangChain's new LCEL syntax and updating default models.

This repository is a CLI tool (@webdevtoday/claude-agents) that enhances Claude Code with specialized AI agents for software development tasks. It provides 16 domain-specific agents (code-reviewer, test-runner, debugger, devops-engineer, etc.) that can be executed independently or chained together in workflows. The system integrates with Claude Code through hooks, commands, and MCP tools, featuring a memory system for agent coordination, voice notifications for task completion, and context-aware adaptation to project structures (particularly context-forge projects). The architecture follows a modular command pattern with core utilities for configuration, TTS, hooks, and agent management. The project has been explicitly archived as of June 2026 because Claude Code now provides native subagents, skills, hooks, and plugins functionality that replicates this tool's features. While the code demonstrates solid engineering patterns in several areas, it is no longer maintained and has been superseded by native capabilities in the platform it was designed to enhance.

This repository is a curated 'awesome list' of links to external Agent Skills repositories. It contains no application code, data pipelines, or executable software. Its sole function is to serve as a community-maintained index and directory. The README is meticulously organized by vendor and category, with contribution guidelines, quality standards, and a security notice. While it has no software components to extract, it is a highly effective and well-maintained directory for its domain. It is not a software application and has zero reusability as a codebase.