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/bmoff/code-first-design/code-first-design-creategit clone --depth 1 https://github.com/bmoff/code-first-designWhat 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 | $0.00013 | $0.02015 |
| Opus 5 | $0.00006 | $0.01007 |
| Sonnet 5 | $0.00003 | $0.00403 |
| Haiku 4.5 | $0.00001 | $0.00201 |
Grade A, and why
code-first-design-create 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating draft components and prototypes
Before you start: Read code-first-design.mdc to understand how the framework works, especially the "How it works" and "Components vs prototypes" sections. This rule helps you create either a component (individual UI piece) or a prototype (full application flow).
⚠️ IMPORTANT: You MUST ask planning questions BEFORE starting implementation. Do not jump straight to code. Clarify what the user wants first, then proceed.
Planning questions (ask these first)
Before creating anything, ask these questions to understand what the user wants:
-
What are you creating?
- Is it a component (like a button, card, or form - a single reusable piece)?
- Or is it a prototype (a complete page or flow that shows multiple components working together)?
-
What should it do?
- What's its purpose? What problem does it solve?
- What should users be able to do with it?
- What information does it need? (For components: what information does the component need to work? For prototypes: what pages or screens does it need?)
-
What should it look like?
- Any specific design requirements?
- Should it match existing components or have a new style?
- Any accessibility needs to consider?
-
How should it behave?
- Does it need to respond to user clicks or input? (If yes, it needs to be interactive)
- Or is it just displaying information? (If yes, it can be simpler)
-
If creating a prototype, also ask:
- What pages or screens does it need?
- What components will it use? Are they new or do they already exist?
- How should users navigate through it?
Workflow:
- If the user's request is vague, ask these questions explicitly
- If the user provides detailed information and you're confident about the answers, summarise your understanding and any assumptions you're making (keep it clear and concise)
- Only proceed to implementation steps once you have confirmed understanding
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 · 199 lines · 13 tokens per session scan A adc04eb73061
code-first-design-create is a cursor rule published in the GitHub repository bmoff/code-first-design (4 stars, last pushed 9mo ago), licensed MIT. It adds 13 tokens to every session and 2,015 once invoked, about $0.0001 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 2026-08-31.
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.