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/AI-Learning-Gems/AI-Learning-Gems.github.ioWrote 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/ai-learning-gems/ai-learning-gems.github.io/python-env)<a href="https://agentmods.dev/rules/ai-learning-gems/ai-learning-gems.github.io/python-env"><img src="https://agentmods.dev/badge/rules/ai-learning-gems/ai-learning-gems.github.io/python-env/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/ai-learning-gems/ai-learning-gems.github.io/python-env"><img src="https://agentmods.dev/badge/rules/ai-learning-gems/ai-learning-gems.github.io/python-env.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 | $0.00386 | $0.00386 |
| Opus 5.5 | $0.00154 | $0.00154 |
| Sonnet 5.5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade C, and why
python-env scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **ALWAYS** double-quote file paths in `rm` commands to prevent word-splitting on spaces, e.g. `rm -rf "/path/to/folder/"`. What it actually says
Python Environment
This project uses a conda environment named ai-learning-gems.
Terminal Commands
PREFERRED: Use the full path to the Python executable. This works reliably in all contexts (interactive shells, IDE subprocesses, subagents, non-interactive scripts):
$(conda info --base)/envs/ai-learning-gems/bin/python script.py
FALLBACK: If you are in an interactive terminal where conda has been initialized, you can activate the env:
conda activate ai-learning-gems
WHY: conda activate requires shell hooks from conda init which are loaded by .zshrc/.bashrc. IDE-spawned subshells (Cursor, Antigravity, Windsurf) often don't source these files, causing CondaError: Run 'conda init' before 'conda activate'. The full path approach bypasses this entirely.
Rules
- ALWAYS use
$(conda info --base)/envs/ai-learning-gems/bin/pythonwhen running Python in terminal commands, especially in workflows and subagents. - For
pipanduv pip, use:$(conda info --base)/envs/ai-learning-gems/bin/pipor activate first if in an interactive shell. - NEVER use bare
pythonorpipwithout the env path or activation. - NEVER use the base conda env or system Python.
- ALWAYS double-quote file paths in
rmcommands to prevent word-splitting on spaces, e.g.rm -rf "/path/to/folder/".
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 · 33 lines · 386 tokens per session scan C 3ee296eb6869
python-env is a cursor rule published in the GitHub repository AI-Learning-Gems/AI-Learning-Gems.github.io (23 stars, last pushed 4mo ago), licensed MIT. It adds 386 tokens to every session, about $0.0015 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). 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.