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/getstream/vision-agents/pythongit clone --depth 1 https://github.com/GetStream/Vision-AgentsWhat 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 | $0.00152 | $0.00152 |
| Opus 5 | $0.00076 | $0.00076 |
| Sonnet 5 | $0.00030 | $0.00030 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade B, and why
python scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
we use uv on this project, no python -m non-sense please. If you get in trouble with deps just stop and ask, better to have the human resolve things (no sudo brew kind of stuff please) What it actually says
never mock. tests use pytest. never adjust sys.path.
never write: except Exception as e avoid using getattr, hasattr, delattr and setattr; prefer normal attribute access.
docs should be short. docstrings should follow the google style guides for docstrings.
integration tests use @pytest.mark.integration
@pytest.mark.asyncio is not needed (its automatic)
description: when running python or tests globs: alwaysApply: true
we use uv on this project, no python -m non-sense please. If you get in trouble with deps just stop and ask, better to have the human resolve things (no sudo brew kind of stuff please)
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 · 29 lines · 152 tokens per session scan B 8532314d6d83
python is a cursor rule published in the GitHub repository GetStream/Vision-Agents (8,104 stars, last pushed 4d ago), licensed Apache-2.0. It adds 152 tokens to every session, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
test-plan
Plan Katalon True Platform/TestOps testing for a release, sprint, or feature. Use when you need to translate quality goals into scope, prioritize testing by requirement coverage and risk, decide what to test first, or build the executable plan structure (folders, suites, and sprint/release association) that stands in…
execution
Repository execution and verification commands.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.
clean-code
Clean code principles for maintainable, readable, and well-structured code.
python
Python best practices with type hints, async patterns, and modern idioms.