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 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/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/skills/causify-ai/helpers/notebook.refactor_to_utils"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/notebook.refactor_to_utils.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 16 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 17 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 107 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Excessive Agency · line 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00878 |
| Opus 5.5 | $0.00005 | $0.00351 |
| Sonnet 5.5 | $0.00002 | $0.00176 |
| Haiku 4.5 | $0.00001 | $0.00088 |
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 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.
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 — 127 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:percentformat
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
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
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
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 Changed · +14 lines fe2feddb0d45
- 1mo 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 (152 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 878 once invoked, about $0.0000 per session on Opus 5.5. 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.
python-cli-ops
CLI application patterns for Python. Triggers on: cli, command line, typer, click, argparse, terminal, rich, console, terminal ui.
python-project
Modern Python project architecture guide for 2025. Use when creating Python projects (APIs, CLI, data pipelines). Covers uv, Ruff, Pydantic, FastAPI, and async patterns.
uv-workflow
Use when a coding agent needs to run Python code, modules, one-liners, tools, tests, or standalone scripts through uv, or create and maintain PEP 723 scripts with uv init/add/remove --script. Avoid direct python/python3 shell entrypoints.
temp-file-python-analysis
Inline Python in shell scripts has quoting issues.