by botingw · Codex Skill · ★ 609
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
uvx rulebook-ai packs add light-spec
uvx rulebook-ai project syncTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
One of 14 tools we ran end to end on the same task for our Open-Source Vibe Coding Tools page (2026-10-27).
Our pick (If you want house rules, not a workflow): It only adds rule files, and stayed closest to no tool: every check, 7.8 minutes, 1.7 times the usage, one question per app.
Result: one-sentence page: 4 of 4 checks · family ledger: 8 of 8 · opens by double-click · stopped to ask 2 times · 2.0 + 5.8 min, 1.7× the usage of no tool
| Stars | 609 |
| Forks | 93 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66/100 |
| Open Issues | 23 |
| Last Updated | 2025-10-03 |
| Created | 2025-04-12 |
| Platforms | claude-code, cli, codex, gemini, python |
| Est. Tokens | ~141k |
For bug report, use issues or use rulebook-ai command For real-time chat, community support, and to share your ideas, Join our Discord Have specific feedback or want a personal demo? Book a Chat on my Calendar Rulebook-AI: The AI Environment Manager is a command-line tool for packaging and deploying consistent, expert environments—rules, context, and tools—to your favorite AI coding assistants.
These tools work well together with rulebook-ai for enhanced workflows:
Looking for a rulebook-ai alternative? If you're comparing rulebook-ai 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.
Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI
Become 10x Vibe Coder. Awesome Vibe Coding guide, best practices, and tips for efficient and controlled AI ass
Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed
Ruler — apply the same rules to all coding agents
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: