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/mikecann/effect-sim/my-project-rulesgit clone --depth 1 https://github.com/mikecann/effect-simWhat 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 | $0.00356 | $0.00356 |
| Opus 5 | $0.00178 | $0.00178 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
my-project-rules 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.
What it actually says
General Guidelines
Some things you should always know about this project:
- This is a Convex project, all data is managed on the server by convex
- This is a React and Vite project, we should follow clean sensible best practices
- I will be keeping BOTH the convex dev server and the vite server running at all times, YOU DO NOT need to run these yourself, you should assume they are always running
- We are using Mantine for the styling, we should always use Mantine best practices
- This project uses Bun for its package management. You should use that unless you encounter errors or otherwise instructed to use npm
- To run tests you should use "bun run test" NOT "bun test"
- If you want to typecheck this project run "bun run typecheck"
- You should NEVER "npm build"
User Preferences
- I prefer to have event handlers at the lowest level possible rather than prop drilling callbacks up through multiple component layers. Keep the logic close to where it's used.
- I strongly prefer to inline event handlers directly in JSX rather than extracting them to separate functions. Use inline arrow functions for onClick, onChange, etc. unless the logic is complex or reused multiple times. This makes the code more direct and easier to read.
- Avoid unnecessary props that are never customized by parent components. If a prop always has the same value, make it a constant or hardcode it. Use shared constants in /shared/constants.ts for values that need to be consistent between frontend and backend.
- When breaking a large component into multiple related sub-components (like photo uploading/display functionality), organize them into a dedicated subfolder to keep related components together and make the codebase more maintainable.
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 · 24 lines · 356 tokens per session scan A 4a93e3f148ab
my-project-rules is a cursor rule published in the GitHub repository mikecann/effect-sim (10 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 356 tokens to every session, about $0.0018 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.