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/ghaida/intent/intent-ref-information-architecturegit clone --depth 1 https://github.com/ghaida/intentWhat 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 | $0.00038 | $0.03120 |
| Opus 5 | $0.00019 | $0.01560 |
| Sonnet 5 | $0.00008 | $0.00624 |
| Haiku 4.5 | $0.00004 | $0.00312 |
Grade A, and why
intent-ref-information-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 2d ago.
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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Information Architecture
Navigation Patterns
Every navigation pattern is a trade-off between findability, scalability, and cognitive load. There is no universally correct pattern — there's the right pattern for your content, users, and context.
Hierarchical (Tree)
The most common pattern. Content is organized in nested categories: top-level → subcategory → item.
When it works: Large content sets with clear categorical relationships. Users have a general sense of what category their item belongs to. Content creators can maintain consistent categorization.
When it fails: When categories overlap significantly (is a "wireless mouse" in Accessories, Computers, or Peripherals?). When the hierarchy is deeper than 3-4 levels — users lose orientation quickly. When the hierarchy reflects organizational structure rather than user mental models ("Products" → "Business Unit A" → "Division 2" → "Team Alpha's Output").
Watch for: The "miscellaneous" drawer. If you have a category called "Other" or "General" that keeps growing, your hierarchy isn't working. Also: category names that mean something to the organization but nothing to users.
Hub-and-Spoke
A central hub connects to independent sections. Each section is largely self-contained. Users return to the hub to navigate between sections.
When it works: Mobile apps with distinct functional areas (Messages, Camera, Profile). Products where tasks are independent — you don't need to combine search results with your shopping cart. Kiosk interfaces and set-top boxes where the input model favors focused navigation.
When it fails: When users need to move fluidly between sections. When tasks span multiple sections. When the "hub" becomes a dumping ground for everything that doesn't fit in a spoke.
Watch for: The desire to add cross-links between spokes. Once spokes start linking to each other extensively, the hub-and-spoke model is fighting the user's actual workflow. Consider switching to a different pattern.
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.
- 2d ago First seen · 225 lines · 3,120 tokens per session scan A ee4bc583d149
intent-ref-information-architecture is a cursor rule published in the GitHub repository ghaida/intent (142 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 38 tokens to every session and 3,120 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.