Code

AI-stack-agnostic repo governance: 1,137 rules, MCP server, Learning Brain, Builder Wizard, and Pantheon agents for Claude, Gemini, Cursor, Copilot, Codex, and AGENTS.md

Strips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.

MCP server that runs Claude Code as tools — start coding agents, poll their progress, and control permissions from any MCP client

Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.

A terminal coding agent that shows every edit as a diff before it writes, and asks before running a shell command it cannot vouch for

CodeAtlas MCP server — 57 tools + 8 resources that expose live codebase architecture (routes, sequences, diffs, impact analysis, architecture violations, read-only SQL access) and AI-driven code review (per-entry-point review, evidence-gated findings, cus

Search, discover, and install 500+ AI agent skills from the SkillFlow marketplace.

npm MCP — search packages, bundle sizes, vulnerabilities, compare downloads.

Comment on AI-generated webpages; feedback flows back to your coding agent. Free, MIT, local-first.

AI Agent Team - 拥有24/7专业AI开发团队：产品经理、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人。全新Thread Manager让AI拥有记忆！支持任务线程管理、自动Git版本控制、完整上下文恢复。一键安装，开发效率飙升200%！集成drawnote、tidymydesktop、softcopyright、changelog-generator和thread-manager五大智能Skill。

Multi-engine AI agent security scanner — one scan, four engines, one report

Authorized, local-first application security assessment run by the coding agent you already use

Your agent says the phase shipped; git says it didn't. CASP validates a project's recorded state against git and blocks the push on drift. Deterministic, local-only, zero telemetry. Works with Claude Code, Cursor, Aider.

Reusable Agent Skills for Claude Code, Cursor, Codex, Copilot and other AI coding agents — research, observability instrumentation, and skill authoring.

Send the task. Caraka runs it. — a thin bridge from Telegram to the coding agent already installed on your machine.

Add inline, range-anchored comments to Google Docs - the one comment op the Google APIs can't do.

AI-powered API testing MCP server — automated API test automation that discovers endpoints from source code (no OpenAPI spec needed), tests every endpoint per role (RBAC) with real harvested IDs, and reports a stability verdict + an importable Postman col

Who-called phone lookups: community verdict, spam rating, operator and reviews (ktozvonil.net).

SOLID/OOP/DRY, the 23 GoF patterns, pattern scaffolding, and heuristic code-smell detection.

Turns your Prisma schema into typed MCP tools, with destructive writes gated behind human approval