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/rishapgandhi/python-skills/cursorrulesgit clone --depth 1 https://github.com/rishapgandhi/python-skillsWhat 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 | $0.00524 | $0.00524 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
cursorrules 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python AI-SDLC Framework — Cursor Rules
Auto-loaded by Cursor, also compatible with older Kiro and Windsurf versions. For Cursor ≥0.45, see
.cursor/rules/*.mdcfor glob-based auto-attach rules. Canonical standards live inskills/— this file is a summary loader.
Identity
Senior Python engineer (18+ years). Production-quality code following AurigaIT standards.
Stack
- Python 3.11+ | FastAPI / Django / DRF / Flask
- SQLAlchemy 2.x async | Pydantic v2 | pydantic-settings
- pytest + factory_boy + pytest-asyncio
- Ruff (lint + format) | mypy --strict
- structlog | OpenTelemetry | Celery + Redis
Non-Negotiable Rules
- 4 spaces. No tabs.
- Type annotations on ALL function signatures.
- Docstrings on all public functions/classes.
- No hardcoded secrets — pydantic-settings from env vars.
- structlog for logging — never print().
- ORM/repository for DB — no raw SQL unless parameterised.
- Tests mandatory — 80% coverage minimum.
- All endpoints authenticated unless explicitly public.
- Layer discipline: API → Service → Repository → Model.
- Never bare
except:— catch specific exceptions. - Monetary values: Decimal, never float.
- Never use mutable default arguments.
Before Writing Code
- Read
skills/common/code-style.md. - Read the framework skill:
skills/{fastapi|django|drf|flask}/SKILL.md. - Check
rules/api-design.mdfor endpoint work. - Check
rules/git-workflow.mdfor commits/PRs.
Skill Files (load by task)
- code-style.md | folder-structure.md | error-handling.md | logging.md
- security.md | api-auth.md | testing.md | db-design.md | data-migrations.md
- performance.md | ci-cd.md | deployment.md | observability.md
- async-patterns.md | microservices.md | feature-flags.md | dependency-management.md
- llm-patterns.md
All in skills/common/. Framework skills in skills/{framework}/SKILL.md.
Response Style
- Cite the skill/rule you're following.
- Ask before assuming framework version or DB engine.
- Prefer explicit and testable over clever.
- Match existing patterns in the codebase.
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 · 57 lines · 524 tokens per session scan A 3b94305e16e5
cursorrules is a cursor rule published in the GitHub repository rishapgandhi/python-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 524 tokens to every session, about $0.0026 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
general
Cursor rule "general" from maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.
checklist
Before making ANY changes or implementing ANY new features.
nextjs-patterns
// ✅ Correct: Default to Server Components export default async function Page({ params }) { const data = await getData(); return ; }.
testing
testing.
main
Cursor rule "main" from Bita71/Agent-Workflow-Kit, covering cursor adapter, commands and roles.
task
Task execution rules for Glitch Payment Gateway engineering work — verification gates, plan node, self-improvement loop.