Havuz

An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.

Free open-source toolkit to understand, audit and rescue vibe-coded or legacy codebases: source-linked maps, team handoff, human-approved fi

Simple Reviewer: a Codex skill for AI-assisted coding and Vibe Coding. Explain code, visualize workflows, and verify goals with evidence. |

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works

Measures how much code LLM agents waste. 5 tasks, sandboxed, weekly snapshots, contestable references.

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

Disciplined AI coding mode. Understand deeply, write minimally, never hallucinate, stay consistent. Based on Ponytail & LLM Wiki.

Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Cod

Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampering, hold the CRAP bar on cha

Measures how much code AI coding agents add, from patches benchmarks already publish

Multi-language cognitive complexity linter, as a single static binary

perch, Jev ve TypeSafe API anahtarıyla kodu tarayan ve doğal dille tanımlanmış kurallara göre olası sorunları raporlayan bir CLI aracıdır.

Neden yükseliyor · 12 günlük yaşına kıyasla 226 yıldız ve son 28 günde 114 commit dikkat çekici erken ilgi ve geliştirme temposuna işaret ediyor. Ancak yalnızca 3 farklı yazar var; bu nedenle ilginin sebebini veya geniş kullanıcı benimsemesini bu verilerden doğrulamak mümkün değil.

gap-trap, coding agent kullanan repolara projeye özel kalite kuralları ve bu kuralları CI veya test sürecinde denetleyen gate'ler ekleyen bir agent skill'dir.

Neden yükseliyor · 14 günde 180 yıldız ve son 28 günde 34 commit, yeni projeye yönelik belirgin ilgiyi ve geliştirme hareketliliğini gösteriyor. Ancak proje çok genç ve farklı yazar sayısı 2; bu veriler yaygın benimsemeyi veya uzun vadeli sürdürülebilirliği kanıtlamıyor.

Keep Go packages flat without losing their internal boundaries: file-level private and package scopes for declarations, methods and struct f

Static analysis for the debt AI agents leave in PHP: 34 rules, Claude Code hooks, git-diff review, a Rector and Pint fix pass, Pest expectat

Research Software Engineering skills for AI coding agents

An architectural audit where a finding is admissible only once its cost is measured from git history. A doctrine for coding agents plus a st

Audits a repository for how ready it is for AI coding agents, and returns a prioritized fix backlog with evidence for every finding.

Claude için fonksiyonların cyclomatic complexity değerini ölçüp karmaşık kodu refactor etmeye yönelik bir skill sunuyor.

Neden yükseliyor · 32 günlük repo yaşına karşılık 402 yıldız dikkat çekiyor; ancak bu ilginin nedenini doğrulayacak son 28 günlük commit veya farklı yazar verisi yok.

Watch for bugs like a hawk! gohawk is a set of static analyzers for Go, focused on concurrency and resource-lifetime bugs.

Code review via the change impact measure

FSharp refactoring tool - The tool clarifies the (agent-generated or old) code's intent, reduces non-alphanumeric noise, and uses built-in .

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

Measure and stop structural erosion in AI-written TypeScript. Slop Check finds the mess, the Deslop tools clean it. Based on SlopCodeBench (

simplify-codebase, AI coding agent'larına mevcut bir codebase'deki gereksiz karmaşıklığı kanıt arayarak belirleme ve güvenli biçimde azaltma iş akışı sağlayan bir Agent Skill'dir.

Neden yükseliyor · 34 günlük yaşında 498 yıldıza ulaşmış olması dikkat çekiyor; ancak bu ilginin kaynağı veya kullanım düzeyi verilen ölçümlerden anlaşılamıyor. Son 28 günde 2 commit ve 2 farklı yazar var; kısa geçmiş nedeniyle sürdürülebilir aktivite hakkında güçlü kanıt yok.

Code-quality skills by Max Kanat-Alexander.

Architectural linting for Swift developers and coding agents

Coverage, security and code quality for coding agents

A Gradle plugin for auditing Kotlin Multiplatform iOS export surfaces and measuring linked binary size. Finds Objective-C declarations for r

LintEval: Benchmarking LLMs on Linter-Guided File Refactoring (EMNLP 2026 Findings) — multi-language benchmark for linter-guided refactoring

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

Portable skills for coding agents — self-contained Markdown procedures that run the same under Claude Code, Codex, or any host that reads th

Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call un

Code Buster reports dependency wiring, dead code, cycles, duplication, complexity, architecture-policy violations, feature flags, security a

AI code review with DeepSeek: headless PR review automation that verifies PR descriptions claim-by-claim against real code, checks docs agai

Evidence-based audit methodology and read-only Laravel context tools for existing AI coding agents.

A practical Codex skill for evidence-backed repository health audits

Fork-and-fill bootstrap for AI coding agents (Claude Code first, Codex/Gemini via AGENTS.md) — agents, skills, hooks, tiered rules (P0/P1/P2

Контроль качества 1С-разработки для Claude Code: стандарты, принципы ООП и паттерны, XML метаданных, блокирующие гейты и проверяемый след пр

An eraser against LLM-induced code & document entropy. Support if you like it!

Cheaper and better Greptile alternative runs on your own github actions.

Help your agents find the smoking gun they're looking for. Optimization evidence for agents: find complexity hotspots.

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

Find and repair substance defects in AI-assisted prose, code, docs, and agent output. Reports defects, never authorship. Structural tests ov

Coding agents için SPEC, test gauntlet’i ve kanıt raporu odaklı bir geliştirme iş akışı sunuyor.

Neden yükseliyor · 63 günde 738 yıldız dikkat çekici ilgiye işaret ediyor; ancak son 28 günde commit ve farklı yazar yok. Bu nedenle yükselişin güncel geliştirme ivmesiyle sürdüğüne dair kanıt bulunmuyor.

A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS inste

AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 30K+ npm downloads.

Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.

Seven Agent Skills for NestJS implementation, architecture, OOP, code and feature audits, runtime performance, and safe Git publication.

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, specu