Havuz

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

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

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

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

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

The Rails audit skill for AI coding agents, ranked by blast radius. 🚂☢️

AI-powered PR review tool — multi-armed code analysis, no bug escapes 🐙

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

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

Research Software Engineering skills for AI coding agents

Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, a

A Socratic supervision layer for AI coding agents.

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением

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

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

Candid reviews of Claude Code skills. File:line citations. Ranked actions. No filler.

Benchmark for the quality of LLM-generated test suites — anti-fragility, rigor, mocking discipline, reuse — scored against human baselines,

Free, AI PR reviewer that runs entirely in GitHub Actions. No hosting required.

Claude Code plugin — code quality hooks, knowledge graph, impact-aware reviews, decomposition enforcement. Babysitter for your AI's code qua

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

phpcpd-next is a token-based copy/paste (clone) detector for PHP 8.4+, a modernized, openly-licensed successor to Sebastian Bergmann's phpc

Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do li

The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.

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

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

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done cla

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

Checks coding agents' edits as they work by enforcing mechanical guardrails for clean code.

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then au

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.

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

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adver

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

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

Comprehensive multi-agent code review for Claude Code

检测并修复 AI 编码助手导致的中文乱码（mojibake）。支持 GitHub Action 和 Claude Code hook。Detect and repair Chinese text encoding corruption caused by AI coding as

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

Paste your code and get brutally roasted by AI — then refactored into something actually worth shipping.

The modern, intelligent codebase aware linter for environment correctness

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

AI code review pipeline — review, auto-fix, test generation & HTML report in one command. Zero dependencies, 6 AI providers (OpenAI/DeepSeek

Deterministic failure-mode scanner for TypeScript. Catches missing error handling around npm packages like Axios, Stripe, and Prisma before

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

Strips the AI tells out of prose, code, and academic writing. 152 patterns from real AI-vs-human analysis, two-pass rewrite, three-tier scor

CLI-first AI code review — BYOK, diff/scan/branch, pre-commit hooks. 100% open source (MIT).

Engineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUI

Design enforcement system, not a code generator. Two independent layers (Taste Guardian + Blind Spot ESLint). 7-phase design pipeline. Zero

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

Your SvelteKit app's code health, checked before it ships. Statically, no browser — SEO, Performance, Correctness, Security, Architecture, A