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/gemini-cli-extensions/data-agent-kit-starter-pack/managing-python-dependenciesnpx skills add gemini-cli-extensions/data-agent-kit-starter-pack --skill managing-python-dependenciesgit clone --depth 1 https://github.com/gemini-cli-extensions/data-agent-kit-starter-packWhat 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 | $0.00138 | $0.00740 |
| Opus 5 | $0.00069 | $0.00370 |
| Sonnet 5 | $0.00028 | $0.00148 |
| Haiku 4.5 | $0.00014 | $0.00074 |
Grade A, and why
managing-python-dependencies 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- managing-python-dependencies — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Dependency Management Rule
[!CAUTION]
BEFORE any
pip install: You MUST first detect the project's existing dependency manager and use it correctly. Do NOT override the project's established tooling.
Dependency Manager Detection
Before installing ANY Python package, check the workspace for these files in priority order:
- Signal:
uv.lockorpyproject.tomlwith[tool.uv]- Tool: uv
- Install:
uv add <package> - Setup:
uv sync
- Signal:
pyproject.tomlwith[tool.poetry]- Tool: Poetry
- Install:
poetry add <package> - Setup:
poetry install
- Signal:
Pipfile- Tool: Pipenv
- Install:
pipenv install <package> - Setup:
pipenv install
- Signal:
environment.yml- Tool: Conda
- Install:
conda install <package> - Setup:
conda env create -f environment.yml
- Signal:
requirements.txtonly- Tool: venv + pip
- Install:
.venv/bin/pip install <package> - Setup:
.venv/bin/pip install -r requirements.txt
- Signal: None of the above
- Tool: venv + pip (default)
- Install:
.venv/bin/pip install <package> - Setup:
.venv/bin/pip install -r requirements.txt
Default: venv + pip
If no dependency manager is detected, use venv + pip + requirements.txt as the default:
# Initialize environment
python3 -m venv .venv
# Add dependencies
.venv/bin/pip install <package>
# Preserve state
.venv/bin/pip freeze > requirements.txt
Rules for venv + pip workflow:
- Always use
.venv/bin/pipor.venv/bin/python(explicit path). - After installing, run:
.venv/bin/pip freeze > requirements.txt. - When setting up:
.venv/bin/pip install -r requirements.txt.
Prohibited
- NEVER run
pip installglobally - NEVER override an existing dependency manager with a different one
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 · 84 lines · 138 tokens per session scan A 7ad459a5a818
managing-python-dependencies is a skill published in the GitHub repository gemini-cli-extensions/data-agent-kit-starter-pack (177 stars, last pushed today), licensed Apache-2.0. It adds 138 tokens to every session and 740 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
esm
Use when working directly with the esm Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.