Havuz

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

svg-diagram, coding agents için tutarlı mimari ve akış diyagramları çizme kuralları ile SVG dosyalarını denetleyen bir linter sunan bir agent skill’dir.

Neden yükseliyor · 45 günlük bir repoda 588 yıldıza ulaşması görünür bir ilgiye işaret ediyor; agent skill ekosistemine kolay kurulum ve linter’la doğrulanabilen somut bir çıktı sunması dikkat çekmiş olabilir. Ancak son 28 gündeki 8 commit ve tek farklı yazar, yıldız ilgisinin geniş katkıcı veya bakım tabanıyla desteklendiğini göstermiyor.

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.

droast - a dockerfile linter that actually has opinions 🔥

seiso, proje dokümantasyonundaki Markdown dosyalarını tanımlı bir yazım ve yapı kuralına göre denetleyen bir CLI linter'dır.

Neden yükseliyor · AI tarafından üretilen dokümantasyonun doğruluğu ve coding agents için güvenilir bağlam ihtiyacı güncel bir sorun. Repo bir günlükken 74 yıldıza ulaşmış; bu ilk ilgiyi gösterir, ancak kalite veya benimseme kanıtı değildir. Son 28 günlük commit ve farklı yazar verisi ölçülmemiş.

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

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

Catch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks

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

Architecture quality gate for polyglot codebases: declare components and allowed dependencies, fail the build on drift

AGENTS.md contract for AI coding agents + zero-dependency linter + SessionStart hook. Works with Claude Code, Codex, Cursor, Copilot.

Deterministic textlint rules and CLI for catching prose slop in English Markdown.

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

A typescript-go toolchain, with evidence graph

iterleak, Go kodunda `iter.Pull` ve `iter.Pull2` çağrılarının `stop` fonksiyonu çağrılmadan kalıp goroutine sızıntısına yol açabileceği durumları bulan bir static analyzer.

Neden yükseliyor · 1 günlük bir repoda 30 yıldız ve son 28 günde 3 commit görünüyor. Zamanlama, Go iterator’larında gözden kaçabilen goroutine sızıntısı gibi somut bir hata sınıfına odaklanmasıyla uyumlu; ancak bu ilginin kesin nedenini veya kalıcı benimsemeyi mevcut verilerle doğrulamak mümkün değil.

Kotlin formatter and linter in Rust, drop-in ktfmt and ktlint (2.0 and 1.8) replacements with identical output.

Automated quality checks that nudge AI coding agents toward better habits

日本語文書の自然さと読みやすさを再現可能に診断するRust CLI / Deterministic diagnostics for natural and readable Japanese writing

A fast universal code security scanner, written in Rust. Batteries included: supports 14 languages, TUI for triage, secrets, post-quantum au

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

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

Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracot

Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.

Architectural linting for Swift developers and coding agents

Static analysis and state mutation auditor specifically designed for FrankenPHP's Worker Mode.

Agent skills for fallow. They teach coding agents (Claude Code, Codex, Cursor, and others) to check health, complexity, duplication, archite

MCP security scanner & config linter for AI coding agents. Finds leaked secrets, risky commands, broad permissions and invalid MCP servers i

Type-check the TypeScript & JavaScript code in your Markdown against your real project — in your editor, the CLI, and CI.

Lint CSS cascade layers across a whole project — contradictory order between files, silent name merges, unlayered rules winning.

Flag ATTACH DATABASE footguns — cross-database atomicity, alias shadowing, ambiguous unqualified tables.

Static Ansible linting in Go: the 38 ansible-lint rules decidable from YAML alone, byte-for-byte pep8 output, no Ansible runtime.

Static analysis for Redis Lua scripts — cluster-unsafe key access, unbounded loops, sandbox violations.

Language-agnostic linter for repository structure, files, and content

Static analysis and health checks for dbt projects.

Offline linter that marks LLM-sounding prose. Its statistical model is trained on 2.8B tokens of human text and 11 LLM families, with 0.96 m

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

Run commands like linters and formatters on staged git files

日本語の文章から「AI 臭さ」を機械的に拾う Rust 製の Linter

🇺🇦🇵🇱 A static analysis tool for OpenTelemetry Collector configurations. Built on OPA/Rego, it validates your pipelines, receivers, processor

Security-focused linter for Docker Compose files. Catches dangerous misconfigurations before they reach production. Grounded in OWASP and CI

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

Audits the .claude/ ecosystem — skills, commands, hooks, agents, settings, plugins, memory — for dead references, weak triggers, token bloat

A static analysis linter for Stellar Soroban smart contracts to catch input-independent resource cost anti-patterns before deployment.

Open-source design-system drift scanner — audit tokens, components, a11y & docs; score adoption; hand fixes to your coding agent. Local-firs

Is your CLI ready for AI agents? Automated checks to ensure optimum agentic CLI use: don't block agents, don't waste tokens, ensure safe use

AI code quality toolkit — deterministic linter for the AI coding era. 22 detectors, GitHub Action PR gate, zero LLM required.

A statistical code analyzer built from your repository's history.

Cache-line false sharing linter for Rust structs

Auditions Ruby scripts, gems, Rack apps, and Rails applications for the ability to run under Ractors: static analysis of Ractor-isolation vi

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