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/documentation-system)<a href="https://agentmods.dev/rules/lacymorrow/paperclip-hub/documentation-system"><img src="https://agentmods.dev/badge/rules/lacymorrow/paperclip-hub/documentation-system/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/documentation-system"><img src="https://agentmods.dev/badge/rules/lacymorrow/paperclip-hub/documentation-system.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 | $0.00000 | $0.01674 |
| Opus 5.5 | $0.00000 | $0.00670 |
| Sonnet 5.5 | $0.00000 | $0.00335 |
| Haiku 4.5 | $0.00000 | $0.00167 |
Grade A, and why
documentation-system 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation System
Overview
The Shipkit documentation system uses dynamic file-based loading from the /docs directory at the project root. It supports both .mdx and .md files with full production-ready security features.
Architecture
Core Components
- Main Library: src/lib/docs.ts - Core documentation loading and processing
- Search Service: src/server/services/docs-search.ts - Documentation search functionality
- Pages: src/app/(app)/docs/[[...slug]]/page.tsx - Dynamic routing for docs
File Structure
/docs/ # Root documentation directory
├── index.mdx # Main documentation index
├── *.mdx, *.md # Root level docs
├── content-management/ # Organized by topic
│ ├── index.mdx # Section index
│ └── *.mdx, *.md # Section documentation
├── development/
├── integrations/
└── snippets/
Security Features (Production-Ready)
Input Validation & Sanitization
- Path Traversal Protection: All file paths validated using
path.resolve() - Slug Validation: Regex patterns prevent malicious input
- Content Sanitization: HTML sanitization prevents XSS attacks
- Size Limits: Files limited to 5MB, content to 1MB
Rate Limiting & DoS Prevention
- Maximum 100 documents total
- Maximum 20 directories per level
- Maximum 50 files per directory
- Maximum depth of 5 levels
- Input length limits enforced via Zod schemas
Error Handling
- Comprehensive error logging without information leakage
- Graceful degradation on missing files
- Proper HTTP status codes
- No stack trace exposure in production
File Format Support
MDX Files (.mdx)
- Full React component support
- Frontmatter metadata required
- Dynamic imports supported
- Processing via remark/rehype
Markdown Files (.md)
- Standard markdown syntax
- Frontmatter metadata required
- Converted to React components
- Syntax highlighting support
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 · 250 lines · 0 tokens per session scan A 399842025ae7
documentation-system is a cursor rule published in the GitHub repository lacymorrow/paperclip-hub (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,674 tokens. 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.
documentation-system compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| documentation-systemlacymorrow/paperclip-hub | Cursor rule | 15 | yesterday | MIT | A | 0 | Cursor |
| always-push-pritsmemeworks/adhx | Cursor rule | 19 | 5d ago | MIT | A | 279 | Cursor |
| curriculum-docsrogerSuperBuilderAlpha/hult-cohort-program | Cursor rule | 4 | 16d ago | MIT | A | 0 | Cursor |
| documentation-systemshipkit-io/bones | Cursor rule | 21 | yesterday | none | A | 0 | Cursor |
| expojimmypocock/cursor-rules | Cursor rule | 8 | 1y ago | MIT | A | 3 | Cursor |
| ponytailDietrichGebert/ponytail | Cursor rule | 188k | 13d ago | MIT | A | 604 | Cursor |
| angular-20angular/angular | Cursor rule | 101k | today | MIT | A | 0 | Cursor |