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/mangome/cybird-watching/cursorrulesgit clone --depth 1 https://github.com/Mangome/cybird-watchingWhat 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 | $0.24977 | $0.24977 |
| Opus 5 | $0.12488 | $0.12488 |
| Sonnet 5 | $0.04995 | $0.04995 |
| Haiku 4.5 | $0.02498 | $0.02498 |
Grade B, and why
cursorrules scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get update Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(['git', 'status'], capture_output=True, text=True) This is a copy
95% identical to cursorrules — 132 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 2,793 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FastLED Project Rules for Cursor
🚨 CRITICAL: PYTHON EXECUTION REQUIREMENTS - NO EXCEPTIONS! 🚨
MANDATORY COMMAND EXECUTION RULES - ALL AGENTS MUST FOLLOW
🚨 ABSOLUTELY FORBIDDEN: Direct python/python3 execution
- ❌ NEVER use:
python3 <command> - ❌ NEVER use:
python <command> - ❌ NEVER use:
./python - ❌ NEVER use: Direct Python interpreter calls
✅ MANDATORY: Always use uv run
- ✅ ALWAYS use:
uv run python <command> - ✅ ALWAYS use:
uv run python -c "..." - ✅ ALWAYS use:
uv run python script.py
NO EXCEPTIONS - ALL PYTHON CODE MUST RUN THROUGH UV:
# ✅ CORRECT - Use uv run python
uv run python test.py
uv run python ci/ci-compile.py uno --examples Blink
uv run python -c "from ci.ci.module import func; func()"
uv run python ci/ci/build_info_analyzer.py --board uno --show-defines
# ❌ FORBIDDEN - Direct python execution
python3 test.py # NO!
python ci/ci-compile.py # NO!
python3 -c "import something" # NO!
python3 script.py # NO!
THIS RULE APPLIES TO:
- 🚨 All test execution
- 🚨 All script execution
- 🚨 All build commands
- 🚨 All analysis tools
- 🚨 All development commands
- 🚨 ALL Python code execution without exception
WHY: The project uses UV for dependency management and execution environment. Direct python3 calls bypass the controlled environment and may use wrong Python versions or missing dependencies.
ENFORCEMENT: Any agent using direct python3/python commands is in violation of project requirements.
🚨 UV RUN MANDATE - FINAL WARNING 🚨
IF YOU SEE ANY COMMANDS IN THIS PROJECT DOCUMENTATION THAT USE python3 OR python DIRECTLY:
- 🚫 DO NOT COPY THEM - They are legacy commands that must be updated
- ✅ ALWAYS REPLACE
python3withuv run python - ✅ ALWAYS REPLACE
pythonwithuv run python - 📝 UPDATE DOCUMENTATION when you find python3 commands
EXAMPLES OF MANDATORY REPLACEMENTS:
# ❌ If you see this in docs (WRONG):
python3 script.py
# ✅ Always use this instead (CORRECT):
uv run python script.py
# ❌ If you see this in docs (WRONG):
python -c "import something"
# ✅ Always use this instead (CORRECT):
uv run python -c "import something"
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 · 2,793 lines · 24,977 tokens per session scan B d8b3afca342b
cursorrules is a cursor rule published in the GitHub repository Mangome/cybird-watching (51 stars, last pushed 8mo ago), licensed MIT. It adds 24,977 tokens to every session, about $0.1249 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). It is 95% identical to cursorrules, differing in 132 lines, and is treated as a copy.
Other cursor rules, from other repositories
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.