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.
git clone --depth 1 https://github.com/aiagentwithdhruv/ai-dev-stackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/aiagentwithdhruv/ai-dev-stack/10-backend-fastapi)<a href="https://agentmods.dev/rules/aiagentwithdhruv/ai-dev-stack/10-backend-fastapi"><img src="https://agentmods.dev/badge/rules/aiagentwithdhruv/ai-dev-stack/10-backend-fastapi/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/aiagentwithdhruv/ai-dev-stack/10-backend-fastapi"><img src="https://agentmods.dev/badge/rules/aiagentwithdhruv/ai-dev-stack/10-backend-fastapi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00324 |
| Opus 5.5 | $0.00000 | $0.00130 |
| Sonnet 5.5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
10-backend-fastapi 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 1mo 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
Backend stack:
- FastAPI
- Pydantic
- SQLAlchemy or SQLModel
- PostgreSQL
- Redis for cache/queue support
Backend rules:
- Use clean architecture.
- Routes/controllers should only handle HTTP concerns.
- Business logic must live in services.
- Database access must live in repositories.
- Validation must be done using schemas/models.
- Use dependency injection patterns where appropriate.
- Use async I/O where supported and beneficial.
- Use pagination for list endpoints.
- Use consistent response models.
- Use centralized exception handling.
API conventions:
- Follow RESTful naming.
- Version APIs when needed, e.g. /api/v1/.
- Use proper status codes.
- Return predictable response structure.
- Do not leak internal stack traces or raw database errors.
Preferred backend structure:
- backend/api/routes/
- backend/api/dependencies/
- backend/services/
- backend/repositories/
- backend/models/
- backend/schemas/
- backend/core/
- backend/utils/
- backend/tests/
Coding expectations:
- Add type hints to functions.
- Add docstrings for non-trivial service methods.
- Keep routes thin and declarative.
- Keep service methods focused and testable.
- Reuse existing utilities before creating new ones.
Do not:
- Put SQL or ORM-heavy logic inside route files.
- Put business logic inside Pydantic schemas.
- Put environment variables directly across many files; centralize in config.
- Mix unrelated domains in the same service file.
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.
- 1mo ago First seen · 55 lines · 0 tokens per session scan A fce8f588643c
10-backend-fastapi is a cursor rule published in the GitHub repository aiagentwithdhruv/ai-dev-stack (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 324 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 2026-08-31.
Other cursor rules, from other repositories
django
Django: models, views, ORM best practices.
cursorrules
You are building an AI/ML project with Python. The project uses PyTorch for model training, handles data pipelines with proper validation, tracks experiments systematically, and follows production ML engineering practices. Code is type-hinted, tested, and reproducible.
spring-boot
Spring Boot: annotations, dependency injection, JPA patterns.
python
Python best practices: type hints, pathlib, pytest, clean error handling.
bun
Bun runtime: Bun.serve, Bun.file, bundler, test runner.
pydantic
Pydantic: BaseModel, validators, Field, Settings.