Havuz

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.

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

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

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

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

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.

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.

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

日本語の文章から「AI 臭さ」を機械的に拾う Rust 製の Linter

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

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.

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

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

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

Architectural linting for Swift developers and coding agents

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

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

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

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.

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

Навык для ИИ-агентов (Claude Code, Codex, Cursor): упрощает русский технический текст по ГОСТ Р 58049—2017 — комментарии в коде, документаци

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

a cli based static python code reviewer

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

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

Token-efficiency linter for LLM prompts and payloads

Dead code detector for Dart and Flutter. Finds declarations that are never referenced — classes, functions, methods, fields, constants, enum

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

Run commands like linters and formatters on staged git files

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

The modern, intelligent codebase aware linter for environment correctness

Validate Mermaid diagrams in Markdown! Catch real syntax errors using the official parser, built for CI.

The tested, tool-agnostic AGENTS.md kit — verified templates, a CI linter, and migrators from .cursorrules/CLAUDE.md/Copilot/Windsurf/Cline/

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

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

fallow for Neovim — see your unused code, dups, and health in a native split

A CI/CD infrastructure tool that prevents PostgreSQL database migrations from causing catastrophic locks in production.

Ontology-driven codebase indexer and query service. Parses C#, TypeScript/JS, Go, Python, and SQL into an embedded graph database. Exposes M

Architecture linter for Swift — enforce Clean Architecture import rules via SwiftSyntax. A CI-ready guardrail for AI-assisted development.

Static security & correctness linter for Payload CMS. Zero-config, deterministic, ts-morph-based. Catches access-control gaps, unsafe Local

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

Delphi-native, MIT-licensed RAG + linter for Delphi/Pascal source code. Symbol-exact + fuzzy + tree-sitter lint. Pure Delphi at runtime.

Automated quality checks that nudge AI coding agents toward better habits

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

Static analysis and health checks for dbt projects.