Havuz

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

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

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

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

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

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

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

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

Architectural linting for Swift developers and coding agents

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

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

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

A Socratic supervision layer for AI coding agents.

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

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

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

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

Comprehensive multi-agent code review for Claude Code

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

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

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

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

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

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

Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.

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

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

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

The modern, intelligent codebase aware linter for environment correctness

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

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

Run AI coding agents unattended for hours and ship PRs worth merging. Cybernetics-based multi-agent orchestration + cross-LLM peer review fo

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

A CLI tool that calculates the CRAP score (cyclomatic complexity x coverage) for Go projects.

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

Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches behavioral bugs, ty

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

Research Software Engineering skills for AI coding agents

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

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

🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing.

Continuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.

A terminal UI for Yocto/OpenEmbedded static analysis, style checks, layer validation, patch auditing and license compliance.

Additional linting rules for Rust projects

The chef's standard for AI agent work: twelve rules, a critique gate, and project memory. One skill. Craftsman's taste. Zero AI slop.

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

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

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

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

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