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.
npx agentmods add rules/open-source-legal/opencontracts/pdf-viewer-and-annotator-architecturegit clone --depth 1 https://github.com/Open-Source-Legal/OpenContractsWhat 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 | $0.00000 | $0.02830 |
| Opus 5 | $0.00000 | $0.01415 |
| Sonnet 5 | $0.00000 | $0.00566 |
| Haiku 4.5 | $0.00000 | $0.00283 |
Grade A, and why
pdf-viewer-and-annotator-architecture 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understanding the PDF Annotation System Architecture
Admin Tasks if you Edit PDF-related frontend code
- When working on document knowledge base and pdf-related frontend functionality, ensure you update our cursor rule here pdf-viewer-and-annotator-architecture.mdc such that it captures any material changes to our existing setup.
- When modifying filtering logic, ensure changes are applied consistently to both
useVisibleAnnotationsanduseVisibleRelationshipshooks to maintain unified behavior.
Context: Document Knowledge Base
The DocumentKnowledgeBase component serves as the main container for viewing and interacting with documents, particularly PDFs. It provides a comprehensive interface that combines document viewing with annotation capabilities, search functionality, knowledge extraction features, and a sophisticated dual-layer architecture for both document annotation and knowledge synthesis.
The system uses a sophisticated virtualized rendering approach for PDFs, where only visible pages (plus a small overscan buffer) are rendered to dramatically improve performance with large documents. This is coupled with an advanced annotation management system that allows users to view, filter, and interact with annotations overlaid on the document.
Intent: High-Performance Document System with Dual-Layer Architecture
The architecture aims to:
- Efficiently render large PDF documents using virtualization (only visible pages are rendered)
- Provide a flexible annotation system that can display/hide annotations based on user preferences
- Support various annotation types (spans, tokens, structural elements)
- Enable real-time filtering and selection of annotations
- Maintain consistent state across the entire application using Jotai atoms
- Ensure smooth scrolling and navigation even with hundreds of pages
- Offer dual-layer architecture for document viewing and knowledge synthesis
- Provide unified content feeds combining notes, annotations, and relationships
- Support version-controlled document summaries with version history
- Enable flexible, resizable panel layouts with auto-minimize capabilities
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 · 295 lines · 2,830 tokens per session scan A be6ebb9089e1
pdf-viewer-and-annotator-architecture is a cursor rule published in the GitHub repository Open-Source-Legal/OpenContracts (1,457 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,830 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 2026-08-30.
Other cursor rules, from other repositories
agent-development
Python agents are typically in folders named agent-py/ or agent/ and use the sdk-python/ package.
statusline
Turn the usage statusLine on or off (model + context% + 5-hour usage% in every project) without editing config by hand. Runs bin/install-statusline.sh, which installs the script to /.claude and merges the setting without clobbering other keys. Opt-in, global, run once per machine; /statusline off disables it.
add-linter
Add linter configs and GitHub Actions workflows for languages detected in the current repo. Use when the user wants to add linters, set up code quality checks, or after sync-scaffold suggests running /add-linter.
simplify
Structural-quality review of changed code — score against the four-dimension rubric, gate at 10/10, and (in auto-fix mode or with --fix) apply reuse/simplification/efficiency/altitude cleanups. Includes a diff-economy lens; correctness is /validate, full-repo survey is /audit.
create-pr
Create a pull request for the current branch and immediately subscribe to PR activity. Use when the user wants to open a PR, submit changes for review, or push and create a pull request.
conventional-commits
Always use Conventional Commits for git commit messages.