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/benknightdark/neo-skills/neo-python-managernpx skills add Benknightdark/neo-skills --skill neo-python-managergit clone --depth 1 https://github.com/Benknightdark/neo-skillsWrote 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/benknightdark/neo-skills/neo-python-manager)<a href="https://agentmods.dev/skills/benknightdark/neo-skills/neo-python-manager"><img src="https://agentmods.dev/badge/skills/benknightdark/neo-skills/neo-python-manager.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 | $0.00064 | $0.00847 |
| Opus 5 | $0.00032 | $0.00424 |
| Sonnet 5 | $0.00013 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade C, and why
neo-python-manager scanned grade C 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **Installation (Unix/macOS):** `curl -LsSf https://astral.sh/uv/install.sh | sh` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Installation (Unix/macOS):** `curl -LsSf https://astral.sh/uv/install.sh | sh` How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Environment Manager Skill
Trigger On
- The user asks "How do I install a package?" or "Which package manager is this project using?".
- The user requests to add, remove, or update Python dependencies.
- Need to initialize a virtual environment or execute a Python script but unsure whether to use
uv run,poetry run, orpython. - The project lacks explicit environment configuration and needs recommendations for suitable tools.
Workflow
- Perceive:
- Scan the project root for characteristic files:
uv.lock,poetry.lock,pyproject.toml,requirements.txt. - Check the system environment to test if tools are installed: execute
uv --versionorpoetry --version.
- Scan the project root for characteristic files:
- Reason:
- Determine the tool the project should use based on characteristic files (Priority:
uv>Poetry>pip). - Check tool availability: If the project is determined to use
uvbut it's not installed, or if the user wants to switch touv/Poetrybut the environment is not ready, mark it as "Pending Installation".
- Determine the tool the project should use based on characteristic files (Priority:
- Act:
- Tool Installation Suggestion: If the tool is not installed, must ask the user first: "Detected that the project uses [Tool Name], but it is not installed in your environment. Would you like me to provide the installation command and assist with the installation?"
- Output Commands: Provide the correct operation commands for the identified management tool.
- Execute Changes: If the user agrees to installation or dependency changes, provide CLI commands for user confirmation.
Tooling Commands Reference
1. uv (Recommended: Ultra-fast Tool)
- Detection Criteria:
uv.lockexists. - Installation (Unix/macOS):
curl -LsSf https://astral.sh/uv/install.sh | sh - Installation (Windows):
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" - Common Commands:
uv add <package>(Add package)uv sync(Sync environment)uv run <script.py>(Run script)
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.
- 6d ago First seen · 67 lines · 64 tokens per session scan C 3595636cda6c
neo-python-manager is a skill published in the GitHub repository Benknightdark/neo-skills (7 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 847 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pandas
Use when analyzing or transforming tabular data in Python. Covers vectorized operations, memory-efficient dtypes, correct joins, groupby patterns, and avoiding the silent errors pandas makes easy.
django
Use when building Django applications. Covers ORM query performance, model design, migrations, Django REST Framework, security defaults, and testing.
fastapi
Use when building APIs with FastAPI. Covers dependency injection, Pydantic v2 validation, async database access, authentication, background tasks, and testing.
python
Use when writing, reviewing, or modernizing Python 3.11+ code. Produces fully type-annotated modules, async I/O, dataclasses and protocols, pytest suites, and a lint/type gate built on ruff and mypy --strict.
mloda-plugins
Guide an AI agent through building mloda (https://github.com/mloda-ai/mloda) plugins: FeatureGroup, ComputeFramework, and Extender classes. Use to check the mloda-registry index for an existing plugin before writing one, when writing or reviewing a FeatureGroup/ComputeFramework/Extender implementation, or when…
python-executor
Execute Python code in a safe sandboxed environment via inference.sh. Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF…