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/romkey/i2c-directory/rails-projectgit clone --depth 1 https://github.com/romkey/I2C-DirectoryWhat 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 | $0.00316 | $0.00316 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
rails-project 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
Links Project Conventions
- Stack: Rails 8.1, Ruby 4.0.5, PostgreSQL 16, Redis 8, Sidekiq 8
- Frontend: Bootstrap 5.3 via cssbundling-rails, Stimulus, Turbo, importmap-rails
- Auth: OmniAuth OpenID Connect + optional local account from environment variables
- Testing: Minitest with fixtures, Capybara + Selenium for system tests — write tests for every change and regression tests for every fix
- Linting: RuboCop with rubocop-rails-omakase — run via
docker compose -f docker-compose.lint.yml run --rm rubocop - Local dev: Use compose files:
docker-compose.dev.yml,docker-compose.test.yml,docker-compose.lint.yml(see README) - CI: GitHub Actions on push/PR to
mainandstaging; Docker images on version tags and staging merges - Documentation: Update
CHANGELOG.mdandREADME.mdwith every user-facing change
Key Architectural Patterns
- Service objects live in
app/services/for external API integrations - Background jobs use Sidekiq; use plain queue names (no
queue_name_prefix) - Environment config via dotenv-rails (
.envfiles) - Version lives in
VERSION; Docker setsAPP_VERSIONfrom git tags
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 · 23 lines · 316 tokens per session scan A a65cdf3445f1
rails-project is a cursor rule published in the GitHub repository romkey/I2C-Directory (11 stars, last pushed 21d ago), licensed MIT. It adds 316 tokens to every session, about $0.0016 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
cursorrules
🚨 ABSOLUTELY FORBIDDEN: Direct python/python3 execution.
sync-api-endpoints
When HTTP routes change, update the HTML index page and API docs together.
compile-after-changes
After significant code changes, build with pio run to confirm the firmware compiles.
arduino-skills
Route Arduino and embedded work through the shared skills tree with board-aware and evidence-aware constraints.
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.