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 skills/causify-ai/helpers/notebook.refactor_to_utilsnpx skills add causify-ai/helpers --skill notebook.refactor_to_utilsgit clone --depth 1 https://github.com/causify-ai/helpersWrote 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/skills/causify-ai/helpers/notebook.refactor_to_utils)<a href="https://agentmods.dev/skills/causify-ai/helpers/notebook.refactor_to_utils"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/notebook.refactor_to_utils.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 | $0.00012 | $0.00806 |
| Opus 5 | $0.00006 | $0.00403 |
| Sonnet 5 | $0.00002 | $0.00161 |
| Haiku 4.5 | $0.00001 | $0.00081 |
Grade A, and why
notebook.refactor_to_utils 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 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.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
You are an expert Python developer
I will pass you a Python file paired with a Jupyter notebook using jupytext in
py:percent format
Constraints
-
For all the code follow the rules from
.claude/skills/coding.rules.md -
Important Notes
- Always sync before editing:
uvx jupytext --sync notebook.py - Always sync after editing:
uvx jupytext --sync notebook.py
- Always sync before editing:
Scenarios
This skill handles two complementary scenarios:
Scenario 1: Moving Existing Functions to Utils
When you need to extract functions from an existing notebook and move them to utils
Scenario 2: Adding New Code to Utils
When you need to add new functions or code to an existing utils file corresponding to the notebook
Workflow
Step 1: Identify or Create the Utils File
- Find or create the library/utility file that corresponds to the notebook
- Naming convention: Notebook name with underscores
- E.g.,
Lesson94-Information_Theory.ipynb->Lesson94_Information_Theory_utils.py - E.g.,
tutorial_advanced.ipynb->tutorial_advanced_utils.py
Step 2: Organize Code Structure in Utils File
- The utils file should have a structure that mirrors the flow of the notebook
- Use section separators to organize code by notebook sections
- Example:
# ############################################################################# # Cell 1: Visual Bin - Population of Marbles # ############################################################################# def cell1_draw_bin_with_marbles_interactive(...): ... def _cell1_helper_function(...): ... # ############################################################################# # Cell 2: Entropy Calculations # ############################################################################# def cell2_calculate_entropy(...): ... `
- Example:
- Add the functions in the part of the utility file that corresponds to the notebook
- Group related functions together
- Use private functions (prefix with
_) for helpers not called from the notebook
Step 3: Move or Add Functions
For Moving Functions (Scenario 1):
- Copy all functions from the notebook to the utils file (without changing code)
- Remove the functions from the notebook
- Update notebook cells to call the utils functions
For Adding Functions (Scenario 2):
- Implement new code directly in the utils file
- Create caller code in the notebook that imports and uses the functions
- Add the code in the appropriate section following the utils file structure
Step 4: Update Notebook to Call Utils
- Replace function implementations with imports and function calls
- Pattern:
import notebook_name_utils as utils
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 · 113 lines · 12 tokens per session scan A b44d58ed302c
notebook.refactor_to_utils is a skill published in the GitHub repository causify-ai/helpers (145 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 806 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
tdd
Strict Python TDD workflow using pytest (Red-Green-Refactor).
python-cli-ops
CLI application patterns for Python. Triggers on: cli, command line, typer, click, argparse, terminal, rich, console, terminal ui.
whisper-voice
Native macOS menu bar app for live voice-to-text with auto-type using WhisperKit on Apple Silicon.
test-generator
Генерация pytest-скелетов из Python-модуля по AST с ghostwriter-эвристикой значений аргументов (bool→True/False, int→0/-1/1, str→sample/пустая, list/dict→пустые, Optional→None). Скрипт testgen.py парсит функции/async-функции через ast, пропускает приватные (), генерирует @pytest.mark.parametrize с assert-заглушками.…