Havuz

Claude Code skill for adversarial AI code & plan review. One AI writes, another tears it apart. Iterative fix loop until approved.

Universal zero-dependency linter and formatter. One pure-Rust binary (poly) that lints and formats ~30 languages in-process — ruff, oxc, bio

AI code-review desktop client, local-first and semi-automatic, for individual reviewers, built on pr-agent.

CLI to generate a narrative walkthrough of any diff

🔍 AI-powered automated code review tool that analyzes syntax, performance bottlenecks, and security flaws in pull requests.

AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code.

You pick the model per task, with review, evidence, and a PR at the end.

A SKILL that turns a code diff into an evidence-backed ledger of hidden assumptions, failure modes, and falsification tests.

Claude Code skills to help you think like a Senior Engineer.

A PR review router for herdr — Ctrl+click a GitHub PR / GitLab MR link and pick a reviewer (tuicr · hunk · diff · browser · or your own tool

Fast, local-first desktop app for reviewing GitHub pull requests — with AI that runs on your own machine. Built with Tauri 2 (Rust + React).

Software engineering discipline grounded in named primary standards (OWASP, ITIL, IETF RFCs, ISO, BABOK, SBAR, and more), shipped as a Claud

Risk-first agent skill for PR/branch review: blast radius, agent-authored checks, call-graph pincer, structural bar.

Automated, Pull Request reviews and Issue Triaging powered by Google Gemini. With full codebase context. Installable as a GitHub Action.

Local, BYOK code review for any language. No SaaS, no telemetry.

Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit.

Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approv

A coding assistant built on persistent multi-agent teams: durable members that discuss, chat, and re-sync continuously — Discuss -> Code in

Claude Code skill that audits your product until it stops finding things - then proves it. 24 lenses, 2 convergence loops, 0 hedging.

Beginner-friendly Sol-led orchestration for Codex with pinned Luna and Terra workers and verified review.

针对中文AI编程的Top 20 提示词，做skill用于辅助codex/claude生成代码

Simplified Technical English for Code - extract, adapt, and enforce ASD-STE100 rules for software documentation. 9-agent pipeline, 59-test b

Document-driven software engineering for coding agents, with Git worktrees, execution graphs, and independent review.

An open-source AppSec agent that reasons like an analyst: real scanners, your org's context, and a conversation instead of 400 findings.

Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.

MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive

Java 团队 AI 代码审查规则库（41 条五关清单 Claude Code Skill）+ Spring AI MCP Server 实操 demo

Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI wo

Two-pass code audit skill for Claude Code: adversarial Opus deep review + Codex second opinion

Isolated AI-powered code and plan reviews from the command line

Readable agent skills with optional declarative YON protocols you can inspect and validate. A personal, field-used pack by Alexandru Mares.

🤖 Self-Evolving Multi-Agent AI System | 116+ Skills | TrendRadar · Reviewer | Learn, Build & Evolve

Strict local PR review agent — npx needlefish. Reviews your diff with your local CLI runner (codex/claude/opencode) and blocks on real findi

A living architecture map for any codebase, any language, any coding agent. See what every change does to the structure, and stop it crossin

Make AI-written code production-ready, with proof. Agent skill for Claude Code, Codex, GitHub Copilot & Gemini CLI: locks behavior, finds bu

VELUNE CLI is an open-source AI engineering CLI that unifies local LLMs (Ollama), cloud AI providers, MCP servers, tools, memory, and projec

Open source GitHub companion — filter, prioritise, and track review status across all your repositories

Claude Code plugin: a supervisor plus specialist AI agents, an Opus review gate on all code, saved reports and a Team Board

The autonomous SDLC for Claude Code that won't pass a gate on an unproven verdict.

The open-source autonomous delivery agent for Claude Code.

agy-plugin-cc is a Claude Code companion for running Gemini CLI or Antigravity CLI (agy) as a cross-model task delegate and code reviewer, w

The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/g

企业自托管 AI Code Review Agent ，一键自动分析 GitLab MR 与 Push，并回填总评和行内 Discussion。

AI code-review cockpit: Claude reviews PRs into local artifacts; nothing reaches GitHub until you say so

Native macOS Markdown viewer and rendered-diff reviewer for documentation-heavy GitHub PRs (design docs, ADRs, skills, runbooks)

Send line-based Neovim review comments to a live Pi session

Supervisor/Lead/Peer governance for multi-agent coding — one policy core enforced identically on Pi and Claude Code, brief-scoped authority,

git diff for behavior: see what a PR changes as a sequence diagram

Explore codebases visually as an interactive call graph and export structured, low-token context directly to AI coding assistants.

不要偷偷上传代码啊魂淡！