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 See-Sol-Lab · Codex Skill · ★ 88
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is private-house-code-v2.5 safe to install? View the security audit →
Private House Code v2.5｜私宅级代码约束 Write the feature. Do not build a bank around it. 写一个功能就写功能，不要在它外面修一座银行金库。 v2.5 SKILL.md · GPT-6 Astra 适配版 · 中文测试记录 · English evaluation · Ponytail 查重报告 · Zenodo archive 2026-09-07 更新：GPT-6 Astra 适配版 新增 ：更短、更直接地表达私宅级要求，减少冗余设计、测试、哈希和审
| Stars | 88 |
| Forks | 2 |
| Category | Codex Skill |
| Quality Score | 43.3102712141029/100 |
| Last Updated | 2026-09-07 |
| Created | 2026-08-05 |
| Platforms | codex |
| Est. Tokens | ~15k |
These tools work well together with private-house-code-v2.5 for enhanced workflows:
Looking for a private-house-code-v2.5 alternative? If you're comparing private-house-code-v2.5 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.
Curated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed
AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query f
Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md fi
Codex Skills Library is a curated library of reusable Codex skills for developers, individuals, and teams.
Explore other popular codex skill tools:
private-house-code-v2.5 is 让 Codex 少烧 Token、少造复杂度，同时不降智的代码约束 Skill. It is categorized as a Codex Skill with 88 GitHub stars.
You can find installation instructions and usage details in the private-house-code-v2.5 GitHub repository at github.com/See-Sol-Lab/private-house-code-v2.5. The project has 88 stars and 2 forks, indicating an active community.
The top alternatives to private-house-code-v2.5 on Agent Skills Hub include codex-settings, awesome-ai-agent-skills, prompt-architect. 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: