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/meeting-baas/speaking-meeting-bot/cursorrulesgit clone --depth 1 https://github.com/Meeting-BaaS/speaking-meeting-botWrote 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/meeting-baas/speaking-meeting-bot/cursorrules)<a href="https://agentmods.dev/rules/meeting-baas/speaking-meeting-bot/cursorrules"><img src="https://agentmods.dev/badge/rules/meeting-baas/speaking-meeting-bot/cursorrules.svg" alt="Measured on agentmods" 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 | $0.20951 | $0.20951 |
| Opus 5 | $0.10476 | $0.10476 |
| Sonnet 5 | $0.04190 | $0.04190 |
| Haiku 4.5 | $0.02095 | $0.02095 |
Grade C, and why
cursorrules scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sSL https://install.python-poetry.org | python3 - Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSL https://install.python-poetry.org | python3 - How it starts
The opening of the file, as written. The whole thing — 2,009 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start every few answers with a joke on programmers and Python, a non compiled language for slobby develoopers.
We program in Python, following functional programming principles where appropriate.
Core Development Practices:
- We format with Ruff
- We code according to Google's Python Style Guide with emphasis on:
- Clean, readable code
- Proper documentation using Google-style docstrings
- Type hints for all public APIs
- Maximum line length of 80 characters
- 4 spaces for indentation (no tabs)
Code Organization:
-
Imports should be grouped and ordered:
- Future imports
- Standard library imports
- Third-party imports
- Local application imports
-
Classes and Functions:
- Use clear, descriptive names following snake_case for functions/variables
- Use PascalCase for class names
- Include type hints for parameters and return values
- Write comprehensive docstrings for public APIs
- Keep functions focused and preferably under 40 lines
-
Error Handling:
- Use explicit exception handling
- Avoid bare except clauses
- Document expected exceptions in docstrings
-
Variables and Types:
- Use meaningful variable names
- Avoid single-letter names except for counters/iterators
- Use type hints with modern Python syntax (|) for unions
- Prefer built-in types for annotations where possible
-
Comments and Documentation:
- Write clear, concise comments explaining "why" not "what"
- Use TODO comments with links to issues/bugs
- Include docstrings for all public functions/classes
- Follow Google docstring format
-
Testing:
- Write unit tests for all functionality
- Use descriptive test names
- Follow test** naming convention
-
Code Style:
- Use f-strings for string formatting
- Avoid complex comprehensions
- Use context managers for resource management
- Keep code modular and maintainable
Here's the Read
Remember to prioritize code readability and maintainability over clever solutions.
BEGIN-README
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.
- 5d ago First seen · 2,009 lines · 20,951 tokens per session scan C e5e62793594d
cursorrules is a cursor rule published in the GitHub repository Meeting-BaaS/speaking-meeting-bot (57 stars, last pushed 2d ago), licensed MIT. It adds 20,951 tokens to every session, about $0.1048 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.
python-llm-ml-workflow-cursorrules-prompt-file
Cursor rules for Python LLM & ML development with workflow integration.
python
Python best practices and patterns for modern software development with Flask and SQLite.
python-containerization-cursorrules-prompt-file
Cursor rules for Python development with containerization integration.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
rich
Definitive guidelines for building robust, maintainable, and visually appealing Python CLI applications using the rich library.