#code-quality

Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call unfinished work done, and a lessons loop that closes each escaped bug's class. One Go binary, no runtime deps, works with 20+ agents.

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

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

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

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

AI 코딩 비서(Claude·Codex·Gemini)가 확인도 안 하고 '다 됐어요' 하는 걸 자동으로 막아주는 품질 안전장치 — 비개발자·바이브코더를 위한 한국어 우선 하네스.

AI Content Guard 2026: Adversarial Fact-Check Gate for Error-Free Code & Copy

A Claude Code skill that finds the engineering controls your repository does not have — CI that never runs on pull requests, a check target that quietly rewrites files, a migration with nothing in front of it — and hands back a numbered plan. It changes nothing until you pick.

Claude Code harness — fewer tokens, fewer bugs, audit-ready. 11 engineering skills. Apache-2.0.

Architectural taste for TypeScript coding agents. Minimize conceptual surface area, create boundaries deliberately, and generate code humans can navigate, review, and evolve.

Three domain-specific code quality assurance tools for Claude Code — generic, AI/ML, and quantitative trading. Based on Clean Code heuristics.

Engineering craft for Claude Code — TDD, verification, code quality, and SDLC discipline.

Open Claude Code plugins for shipping AI output that's actually good. By Josh Matthews / LogicLeap Ltd.

Project Intelligence Platform for AI Coding Agents. Scan, audit, generate, and monitor context files (CLAUDE.md, AGENTS.md, CURSOR.md, GEMINI.md) for 6 AI agents. Auto-detect drift, one-click fix, CI integration, MCP server.

Claude Skills that hold AI-generated and AI-reviewed code to a rigorous, production-grade engineering bar — automatically.

Kill-tested guard skills for AI coding agents , self-invoking quality gates that catch AI failure modes in security, tests, docs, dependencies, and diffs before the agent says "done." Works with Claude Code, Codex, and Cursor.

Claude Code skill that reviews other skills and slash commands for research-backed authoring anti-patterns (skill smells)

Evidence-first code review and refactoring skills for Claude Code and Codex. Find root causes, reject unnecessary refactors, and make the smallest safe change.

A Claude Skill that writes code comments explaining why, not what, and never deletes an existing comment without asking.

Hallwright: Deterministic pre-commit guardrail, living project memory, and subagent orchestration for Claude Code, Cursor, Copilot, Antigravity, and AI coding assistants.

Deterministic UI policy, discovery and quality gates for coding agents.

Best Free LLM Autonomous Agent Plugin 2026 - Real-Time Security, Auto-Learn

SPEC-First AI DevKit for Agentic Code 2026 — 24 Agents, 52 Skills, TDD/DDD Gates

Claude Codeを実務で確実に動かすためのハーネス(土台)テンプレート — CLAUDE.md索引・rules・skills・役割特化agents・機械検証toolsの最小構成

Open-source Claude Code plugin marketplace framework and distribution CLI deploying fast quality guardrails (ruff, pyright, biome, clippy), MCP tools, and language packs.

Shared engineering standards for Claude Code: scaffold new projects, extract and audit the rules of existing ones (TypeScript, Python, Angular, .NET, Flutter), enforced by linters, hooks and CI.

Install a reasoning layer at the point of creation: one-line intent notes that tell AI (and humans) WHY code, plans, and content exist. Claude Code drop-in + tool-agnostic convention.

Local-first evidence console for AI-assisted software work

Evidence-grounded structural feedback for Codex coding agents, delivered after code changes and before the next decision.

🕵🏼‍♂️ Code Sheriff: Security Review Agent

Diff-scoped pre-PR Rust quality gate as a Claude Code skill: clippy, dead code, unused deps, security audit, and quality heuristics — triaged by severity with a go/no-go verdict.

Discipline layer for AI coding agents (Claude Code & Codex): task router + three pipeline modes with run controls, premortem reviews, TDD gates, evidence-based acceptance, and crash-safe resume. Noncommercial license, 138 behavioral evals.

Agent-ready SvelteKit architecture standard and injectable audit kit

A Claude Code hook that blocks git commit until your quality gate has actually run on the staged code. Gate-agnostic, fail-safe, 31 tests.

Skill de Claude Code que audita si tus pruebas sabrían ponerse rojas. Instalable como plugin desde el marketplace. La misma herramienta que el repositorio hermano, empaquetada para que la use tu asistente.

Agent 작업의 신뢰성 높이기 · Improving the Reliability of Agent's Work

Sistema de qualidade e auditoria com gates declarativos para Antigravity e Claude Code

A deterministic anti-entropy guardrail for human and agent-generated codebases. Makes repository cleanliness testable and merge-blocking.

Universal quality and safety guard plugin for OpenCode AI agents (Dual-Mode: v1 & v2)