No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by pavel-molyanov · Claude Skill · ★ 245
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is molyanov-ai-dev safe to install? View the security audit →
Claude Code Framework Фреймворк для AI-First разработки с Claude Code. В основе — spec-driven pipeline: сначала детально планируем работу через интервью с пользователем и исследование кодовой базы, согласуем спецификации, и только потом пишем код. Каждый этап проверяется специализированными агентами-валидаторами. Код пишется через TDD. Quick Start Новый проект: → → начинаем фичи Новая фича: → → → (или ) → Быстрая задача без спеки: Как устроена методология Документация проекта — Project Knowledge Вся документация проекта хранится не в CLAUDE.md, а в отдельном скилле Project Knowledge — наборе файлов в : CLAUDE.md остаётся минимальным — название проекта, ссылка на Project Knowledge, дефолтная ветка. Агент подгружает только те файлы из Project Knowledge, которые
| Stars | 245 |
| Forks | 75 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 57.3077801017216/100 |
| Open Issues | 4 |
| Last Updated | 2026-07-20 |
| Created | 2025-12-22 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~17k |
Looking for a molyanov-ai-dev alternative? If you're comparing molyanov-ai-dev with other claude skill tools, these 5 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
An open-source AI marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analyti
Repo for the Claude Code Marketplace to use with the Claude for Life Sciences Launch. This will continue to ho
Report issues related to MCP integration with Claude here.
A tool for autonomous agents like OpenClaw to discover and learn skills autonomously
Explore other popular claude skill tools:
molyanov-ai-dev is AI-First Development Methodology for Claude Code & Codex CLI — spec-driven pipeline, 20+ skills, 20+ agents, team execution. It is categorized as a Claude Skill with 245 GitHub stars.
molyanov-ai-dev is primarily written in JavaScript.
You can find installation instructions and usage details in the molyanov-ai-dev GitHub repository at github.com/pavel-molyanov/molyanov-ai-dev. The project has 245 stars and 75 forks, indicating an active community.
molyanov-ai-dev is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to molyanov-ai-dev on Agent Skills Hub include claude-codex-settings, digital-marketing-pro, life-sciences. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: