by Jamailar · Codex Skill · ★ 141
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
多app共享后端服务,一人使用AI管理多个app,实现一人集团化,打通一人公司的最后一公里。几乎支持所有后端服务,可接入Codex、Claude Code、Hermes、OpenClaw等任何主流AI工具。实现迭代、营销全程AI化
| Stars | 141 |
| Forks | 31 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 55.0341650787553/100 |
| Last Updated | 2026-06-22 |
| Created | 2026-06-09 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~13k |
These tools work well together with OPG for enhanced workflows:
Looking for a OPG alternative? If you're comparing OPG with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa
Context-Engine MCP - Agentic Context Compression Suite
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Lightweight agent orchestration dev tool that lives in your repo
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Explore other popular codex skill tools:
OPG is 多app共享后端服务,一人使用AI管理多个app,实现一人集团化,打通一人公司的最后一公里。几乎支持所有后端服务,可接入Codex、Claude Code、Hermes、OpenClaw等任何主流AI工具。实现迭代、营销全程AI化. It is categorized as a Codex Skill with 141 GitHub stars.
OPG is primarily written in TypeScript. It covers topics such as ai, cli, codex.
You can find installation instructions and usage details in the OPG GitHub repository at github.com/Jamailar/OPG. The project has 141 stars and 31 forks, indicating an active community.
The top alternatives to OPG on Agent Skills Hub include agnix, ClaudeR, Context-Engine. 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: