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 OpenHands/extensions --skill uvgit clone --depth 1 https://github.com/OpenHands/extensionsWrote 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/openhands/extensions/uv)<a href="https://agentmods.dev/skills/openhands/extensions/uv"><img src="https://agentmods.dev/badge/skills/openhands/extensions/uv/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/openhands/extensions/uv"><img src="https://agentmods.dev/badge/skills/openhands/extensions/uv.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 | $0.00046 | $0.00675 |
| Opus 5.5 | $0.00018 | $0.00270 |
| Sonnet 5.5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade C, and why
uv 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 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.
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.
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.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uv (Python)
Use uv as the default tool for Python dependency + environment management when the repo has uv.lock, mentions uv in its docs/Makefile, or already uses a .venv created by uv.
Quick decision rules
- If the repo has
uv.lockandpyproject.toml: treat it as a uv-managed project. - If the repo has only
requirements.txt: you can still useuv pipfor fast installs. - Prefer project commands (
uv add/remove/sync/run/lock) over rawpipunless the repo explicitly usesuv pip.
Installation (if needed)
Prefer a packaged install method when available. If you use the official installer, review it first (avoid blindly piping into a shell) and follow the latest instructions in the official docs.
# macOS/Linux (official installer)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell, official installer)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Common operations
Initialize a new project
uv init
# or
uv init my-project
Create / use a virtual environment
uv venv # creates .venv
# If you need a specific version, match the project's declared requirement
# (e.g., pyproject.toml / CI config), not an arbitrary latest version.
uv venv --python 3.x
# optional activation (not required for uv commands)
source .venv/bin/activate # macOS/Linux
# .venv\\Scripts\\activate # Windows
Add / remove dependencies (updates pyproject.toml and uv.lock)
uv add requests
uv add 'requests==2.31.0'
uv add -r requirements.txt
uv remove requests
Lock + sync (reproducible installs)
uv lock # (re)generate uv.lock
uv sync # create/update .venv to match uv.lock
If you pulled new changes and uv.lock changed, run uv sync.
Run commands inside the project environment
uv run python -m pytest -q
uv run python main.py
uv run ruff check .
Using uv as a fast pip replacement (requirements workflows)
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 96 lines · 46 tokens per session scan C e321822ec057
uv is a skill published in the GitHub repository OpenHands/extensions (167 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 675 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
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.
notebook.refactor_to_utils
Move or add notebook code to a utils.py library file.
notebook.split_header_cells
Split notebook header cells so each cell has a single header and comment.
python-cli-ops
CLI application patterns for Python. Triggers on: cli, command line, typer, click, argparse, terminal, rich, console, terminal ui.
notebook.split_cells
Split Jupyter notebook cells so each cell performs only one logical task.