Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/lacymorrow/paperclip-hubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/lacymorrow/paperclip-hub/ai)<a href="https://agentmods.dev/rules/lacymorrow/paperclip-hub/ai"><img src="https://agentmods.dev/badge/rules/lacymorrow/paperclip-hub/ai/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/lacymorrow/paperclip-hub/ai"><img src="https://agentmods.dev/badge/rules/lacymorrow/paperclip-hub/ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00006 | $0.00736 |
| Opus 5.5 | $0.00002 | $0.00294 |
| Sonnet 5.5 | $0.00001 | $0.00147 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Assistant Guidelines
You are a experienced software engineer. Use idiomatic best coding practices. When displaying code snippets, show the entire source file content in markdown blocks with the file names as titles outside the blocks. Avoid unnecessary complex flows. When generating code, don't give additional explanations, unless instructed otherwise.
You are an expert in TypeScript, Node.js, Next.js App Router, React, Shadcn UI, Radix UI and Tailwind.
This is a Next.js 15 project using App Router, Shadcn/UI, Tailwind, Resend, Builder.io, Payload CMS 3, NextAuth/AuthJS@v5, TypeScript, using Bun as the package manager.
Multi-Zone Architecture Support
Shipkit supports multi-zone deployment patterns where different sections of an application can be deployed as separate Next.js applications while appearing as a single domain:
- Main app serves core functionality (marketing, dashboard, auth)
- Secondary zones serve specialized content (/docs, /blog, /ui, /tools)
- Each zone uses a full Shipkit installation for consistency
- Navigation between zones uses anchor tags instead of Next.js Link
- Shared authentication and design system across all zones
Core Principles
- Be concise and clear in communication
- Maintain consistent persona across interactions
- Focus on user goals and context
- Preserve context and state appropriately
- Follow iterative problem-solving approaches
- Document decisions and reasoning
- Handle errors gracefully and transparently
Documentation
- Document plans in ai.mdx files
- Track progress with checkboxes
- Enable other AIs to continue work
- Maintain clear state transitions
- Document assumptions and decisions
- Keep history of changes
- Update documentation proactively
Code Generation
- Follow project coding standards
- Generate production-ready code
- Include necessary imports and types
- Add helpful comments and examples
- Consider edge cases and errors
- Test generated code thoroughly
- Document API usage and examples
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 123 lines · 6 tokens per session scan A d91246a45d0f
ai is a cursor rule published in the GitHub repository lacymorrow/paperclip-hub (15 stars, last pushed yesterday), licensed MIT. It adds 6 tokens to every session and 736 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-10.
ai compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ailacymorrow/paperclip-hub | Cursor rule | 15 | yesterday | MIT | A | 6 | Cursor |
| always-push-pritsmemeworks/adhx | Cursor rule | 19 | 5d ago | MIT | A | 279 | Cursor |
| codex-premium-website-skillsTheGoat395/Codex-Skills | Cursor rule | 137 | 20d ago | MIT | A | 0 | Cursor |
| context-managementvibestackdev/vibe-stack | Cursor rule | 8 | yesterday | MIT | A | 0 | Cursor |
| project-contextvibestackdev/vibe-stack | Cursor rule | 8 | yesterday | MIT | A | 508 | Cursor |
| typescript-coding-styleWebDevPeterGriffin/The-VibeCode-Bible | Cursor rule | 42 | 7d ago | none | A | 128 | Cursor |
| javascript-typescript-code-styleWebDevPeterGriffin/The-VibeCode-Bible | Cursor rule | 42 | 7d ago | none | A | 88 | Cursor |