uv-workflow

uv-workflow is a skill for Claude Code, Codex from bahayonghang/my-ai-cli-toolkit. It costs 57 tokens per session (654 once invoked), scanned A, original, MIT.

A set of rules for running Python programs, tools, and tests through uv, a Python environment and package manager.

In plain words
What is it for?
Use it to run scripts, modules, one-off commands, tests, and standalone scripts, and to add or remove their dependencies.
Why use it?
It keeps Python execution and script dependencies consistent without relying on whichever Python installation happens to be active.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/bahayonghang/my-ai-cli-toolkit/uv-workflow
Any agent
npx skills add bahayonghang/my-ai-cli-toolkit --skill uv-workflow
Clone the repo
git clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for uv-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/uv-workflow.svg)](https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/uv-workflow)
Your own site
<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/uv-workflow"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/uv-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.00654
Opus 5 $0.00028 $0.00327
Sonnet 5 $0.00011 $0.00131
Haiku 4.5 $0.00006 $0.00065

Measured 5d ago against content hash 3978805ca64f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

uv-workflow 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 5d 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.

skills/developer-tools-integrations/uv-workflow/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

uv Workflow

Use uv as the entrypoint for Python execution and standalone script management.

Core Rules

  • Do not run python or python3 as the shell entrypoint.
  • Translate direct Python commands into the closest uv form before running them.
  • python inside uv run ... is acceptable because uv controls interpreter selection and environment setup.
  • When sandboxed or when cache writes may fail, set UV_CACHE_DIR to a writable temporary directory before running uv.
  • For standalone PEP 723 scripts, let uv manage inline metadata. Do not hand-edit metadata blocks.

Command Map

Need Use
Run a script uv run path/to/script.py
Run a module uv run -m package.module
Run a one-liner uv run python -c "print('hello')"
Run a dependency-provided tool uv run tool-name
Add an ad hoc dependency uv run --with package python -c "..."
Run tests uv run pytest or uv run -m pytest
Create a standalone script uv init --script path/to/script.py
Add a script dependency uv add --script path/to/script.py package
Remove a script dependency uv remove --script path/to/script.py package

Standalone Script Workflow

For a new single-file script:

  1. Initialize it with uv init --script path/to/script.py.
  2. Add dependencies with uv add --script path/to/script.py <package>.
  3. Edit the Python code normally.
  4. Run it with uv run path/to/script.py.
  5. Remove dependencies with uv remove --script path/to/script.py <package>.

Use uv init --script even when the script already exists conceptually and only needs to be created on disk.

Scope Boundary

Use this skill for Python execution, Python tools, tests, one-liners, and standalone PEP 723 scripts.

If the task is about a full Python project with pyproject.toml, use project-oriented uv commands instead of script-specific metadata commands. Keep uv as the entrypoint, but do not force uv init --script or uv add --script onto project workflows.

Read the full file on GitHub · 63 lines

Files

What ships with it

3 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.

Changes

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.

  1. 5d ago First seen · 63 lines · 57 tokens per session scan A 3978805ca64f

Subscribe to this mod's changes

uv-workflow is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 654 once invoked, about $0.0003 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.