code-quality — independent software & tools
-
adversarial-gatekeeper
AI Content Guard 2026: Adversarial Fact-Check Gate for Error-Free Code & Copy
-
gospect-mcp
Go-only, report-first code scanner exposed as an MCP server. Indexes a module, runs deterministic analyzers, and reports genuine bugs, dead code, stale docs & outdated APIs — never editing your code until you ask.
-
rails-senior-architect
Ultimate Rails CTO Toolkit 2026: Pro Opinionated Skills for Modern Apps
-
ai-pr-review-analyzer
AI-Powered PR Review Assistant 2026 – Automated Code Quality & Efficiency Tool
-
forgekit
One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.
-
idea-anvil
Best AI Coding Agent Pipeline Builder 2026 – Plan-Forge Drift-Proof Execution Contracts
-
codeguard
devr's codeguard tool for ci, testing and deployment
-
mcp-migrate
Find and fix what the MCP 2026-07-28 spec revision breaks in your server. 21 rules, 5 autofixers, and a readiness board.
-
octo-code-trail
Rustic SQLite Code Graph 2026 – 28 Languages, 238 Commands, Zero API Keys
-
desprawl
npx desprawl: visually browse any codebase. Scope and deliver cleanup work on legacy projects, tech debt and agentic-coding sprawl. Understand unfamiliar repos faster. One CLI+UI, usable by humans and agents.
-
agent-rules-kit
Diagnose AI agent instruction files like AGENTS.md, CLAUDE.md, and Cursor rules using this local read-only Python CLI.
-
polylint
Universal zero-dependency linter & formatter — one pure-Rust CLI (poly/polylint/polyfmt) for 300+ languages, in-process, one config.
-
claude-engineering-rules
Opinionated Claude Code engineering config: 11 always-on rules, 63 on-demand standards, 30 slash-command skills, 33 runtime hooks, 9 custom agents, 36 MCP servers, and a 774-item review checklist across 69 categories
-
hi-vibe
The vibe-coding seatbelt for Claude Code — catches AI coding mistakes · 바이브코딩 안전벨트, AI 코딩 실수를 막는 플러그인
-
cadence
Verification layer for AI-assisted development. Agents don't get to self-certify — settle gates re-check declared acceptance criteria and refuse until the evidence holds. CLI · Claude Code · Codex · MCP.
-
sober-coding
Analyze AI-generated code to find technical debt and get actionable fixes.
-
OpenSweep
AI agents that keep your codebase healthy — sweep repos, keep docs alive, file findings, and drive PRs to green. Free to self-host (ELv2).
-
GitRoast.ai
GitRoast.ai delivers evidence-backed, deterministic GitHub profile audits with actionable scoring, shareable cards, and project evaluation—no AI-generated scoring claims.
-
svelte-vitals
A static code-health checker for SvelteKit — SEO, Performance, Correctness, Security, and Architecture, from source. Not a runtime Web Vitals reporter.
-
ovecc
CLI-first, deterministic architecture intelligence. Builds an offline model of your repo to answer impact, cycles, dead code, duplication and security, and enforces your architecture as a contract in CI. No LLM in the loop; usable by coding agents over MCP.
-
maintainable-code-craft
A composable maintainability baseline for Codex coding tasks.
-
standards
Deterministic standards for Python, TypeScript, SQL, IaC, and repository policy.
-
kiss-my-diff
A tiny AGENT.md that helps coding agents write diffs you can kiss.
-
CodeEraser
An eraser against LLM-induced code & document entropy — clone/duplication/deadcode/structure judgment (Haskell core, Rust frontend) with Claude Code guard hooks, MCP, CI gates and a Tauri GUI
-
research-repo-doctor
Artifact Evaluation readiness checker for research code: static scan, safe fixes, verify ladder, appendix, and agent-ready gates. Local-first, no API key.
-
dxkit
Deterministic Stop-gate and code-graph context for AI coding agents: blocks only net-new findings and gives the loop a structural map of the codebase, locally, with no model in the gate.
-
moat
AI Coding Gatekeeper — Zero-config, real-time guardrails for AI-generated code. 零配置AI编码守门员，实时拦截架构/安全/回归问题。
-
claude-self-evolving-agent
Best Free LLM Autonomous Agent Plugin 2026 - Real-Time Security, Auto-Learn
-
archunit
ArchUnit TypeScript is an architecture testing library, to specify and assert architecture rules in your TypeScript app
-
@axiomatic-labs/claudeflow
Claudeflow — AI-powered development toolkit for Claude Code and Codex. Skills, agents, hooks, and quality gates that ship production apps.
-
fallow
Deterministic codebase intelligence for TypeScript and JavaScript. Quality, risk, architecture, dependencies, duplication, and safe cleanup evidence for humans, CI, and agents. Optional runtime intelligence layer (Fallow Runtime) adds production execution
-
solhint
Solidity Code Linter
-
clines
Measure your codebase from the terminal — lines per language, duplicate code, complexity, token cost for AI agents, comment drift, change coupling, a refactor verdict per file, and what is safe to hand to an agent. JSON output, CI exit codes, PR diff mode and an MCP server. One dependency, 100% test coverage.
-
rust-doctor
Your agent writes bad Rust. This catches it.
-
Toolchain
A reusable CLI that scaffolds a complete dev toolchain - ESLint, Prettier, Husky, commitlint, and strict TypeScript - into any JS/TS project with one command.
-
claude-sdlc-wizard
SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command. TDD, planning, self-review, CI shepherd.
-
argus-mcp
🔍 Enhance code quality with Argus MCP, an AI-driven code review server using a Zero-Trust model for safe and efficient development.
-
dynos-work
A Claude Code plugin that checks its own work, learns from mistakes, and fixes your code while you sleep.
-
hallucinate.md
The open standard for telling AI not to hallucinate.
-
jaipilot
Deterministic guardrails that cut down agentic drift for high-quality agentic Java changes — a local Java Enterprise Harness for Codex, Claude Code, and stdio MCP agents.
-
rhiza
A collection of reusable configuration templates for modern Python projects
-
py-lintro
Making linters play nice... Mostly.
-
drift
Claude Code plugin that tells your agent when it is about to build something that already exists. Two-line install, no dependencies, answers in under 100 ms. Also a standalone static analyzer for structural drift.
-
evolve-loop
Self-improving AI pipeline that autonomously discovers, builds, audits, and ships improvements to any codebase. 4 agents, 5 phases, eval gating, continuous learning. Plugin for Claude Code & Gemini CLI.
-
evolve-loop
Autonomous CI/CD for AI-written code: plans, builds, and adversarially audits changes to any repo — a different model reviews the builder — shipping only what passes deterministic gates. Failures become durable lessons; runs are checkpoint-resumable & context-optimized. Claude Code · Codex · Gemini.
-
deprecated-tracker
Find and manage deprecated code in TypeScript and JavaScript projects. Tracks declarations and every usage, with inline diagnostics, ignore rules and export.
-
appstore-review-skill
Audit iOS apps against Apple’s App Store Review Guidelines before submission with automated compliance checks for multiple frameworks.
-
quodeq
AI-powered code quality and security scanner. Open source, MIT, runs locally. <🧭>
-
agent-review
Analyze git code changes to generate structured review reports using flexible AI models and integrated workflows.
-
claude-code-best-practices
Next.js app for Claude code best practices built with Fumadocs. Document and explore content sources, routes, and MDX docs for fast, scalable docs sites. 🐙
-
duphunter
Detect near-duplicate Python code using AST analysis to find structural clones despite renaming, supporting efficient AI-assisted refactoring workflows.
-
claude-doctor-skill
Audit projects for security, broken hooks, tests, and CI issues across 20+ languages with adaptive scoring and actionable fixes.
-
Claude-cod-top-2026
Still trusting results that AI generated, tested, and declared successful by itself? This Claude Code methodology adds evidence markers, audit gates, anti-hallucination rules, and Validation Theater detection to keep AI-assisted development verifiable.
-
DevS69-sdetkit
Evolving developer productivity + QA automation toolkit for reliable workflows and fast feedback.
-
codex-workflows
Controlled, reviewable agentic coding workflows for OpenAI Codex CLI with task-specific subagents, explicit planning, TDD, and quality gates.
-
sirsi-pantheon
Sirsi Pantheon — Infrastructure hygiene CLI. Finds waste CleanMyMac misses, audits network security with auto-rollback, gives AI tools persistent memory. Install: brew install sirsi-pantheon. Free forever.
-
skills
Claude Code skills for git workflows, GitHub automation, security audits, code refactoring, and project tooling
-
crie
Universal meta-linter using containerized execution
-
code-review-skill
Automate code reviews for general code projects with modular parallel checks, config-driven scope, and clear reports.
-
SCAManager
Self-hosted code quality service for GitHub — 25 static analyzers + Claude AI review on every push/PR, scored 0-100, with score-based PR auto-approve/merge and Telegram, Discord, Slack, Email and n8n notifications.