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 WhatIfWeDigDeeper/agent-skills --skill uv-depsgit clone --depth 1 https://github.com/WhatIfWeDigDeeper/agent-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/whatifwedigdeeper/agent-skills/uv-deps)<a href="https://agentmods.dev/skills/whatifwedigdeeper/agent-skills/uv-deps"><img src="https://agentmods.dev/badge/skills/whatifwedigdeeper/agent-skills/uv-deps/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/whatifwedigdeeper/agent-skills/uv-deps"><img src="https://agentmods.dev/badge/skills/whatifwedigdeeper/agent-skills/uv-deps.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 | $0.00090 | $0.02540 |
| Opus 5.5 | $0.00036 | $0.01016 |
| Sonnet 5.5 | $0.00018 | $0.00508 |
| Haiku 4.5 | $0.00009 | $0.00254 |
Grade A, and why
uv-deps 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 2mo 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UV Deps
Arguments
Specific package names (e.g. fastapi asyncpg), . for all packages, or glob patterns (e.g. django-*).
The text following the skill invocation is available as $ARGUMENTS (e.g. in Claude Code, /uv-deps fastapi asyncpg sets $ARGUMENTS to fastapi asyncpg; other assistants pass arguments similarly). If invoked with no arguments, $ARGUMENTS is empty.
If $ARGUMENTS is help, --help, -h, or ?, skip the workflow and read references/interactive-help.md.
Workflow Selection
Based on user request:
- Security audit (audit, CVE, vulnerabilities, security): Read references/audit-workflow.md
- Dependency updates (update, upgrade, latest, modernize): Read references/update-workflow.md
- Ambiguous (no clear intent, or invoked with no args): Read references/interactive-help.md
Shared Process
1. Create Worktree
Create an isolated git worktree so the main working directory is never modified:
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
BRANCH_NAME="py-uv-deps-$TIMESTAMP"
WORKTREE_PATH="${TMPDIR:-/private/tmp}/$BRANCH_NAME"
git worktree add "$WORKTREE_PATH" -b "$BRANCH_NAME"
If git worktree add fails due to a sandbox permission error:
git worktreerequires write access to the parent temp directory — the per-run$WORKTREE_PATHis nested under it. Grant that access in your assistant's settings (in Claude Code: add the resolved path — the value of$TMPDIR, or/private/tmpif$TMPDIRis unset or empty — to the sandbox allowlist insettings.json) and retry.
All subsequent steps operate within $WORKTREE_PATH. Discovery, syncs, edits, and commits all happen there. Code blocks in reference files that show cd "$WORKTREE_PATH/<directory>" must run that cd explicitly — the working directory does not carry over between blocks.
2. Verify Tool Access
Verify that uv and uvx are available and can reach PyPI. See references/uv-commands.md for verification commands and troubleshooting.
What ships with it
4 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.
- 2mo ago First seen · 160 lines · 90 tokens per session scan A e1db96fd81c5
uv-deps is a skill published in the GitHub repository WhatIfWeDigDeeper/agent-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 90 tokens to every session and 2,540 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
astropy
Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.
dask
Scales pandas, NumPy, and custom Python research workflows beyond memory or across clusters with Dask. Covers DataFrames, Arrays, Bags, Futures, chunking, schedulers, and distributed diagnostics. Use for partitioned file processing, scientific array computation, or parallel tasks whose memory and dependency structure…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
bioservices
Provides a Python interface to bioinformatics services including UniProt, KEGG, ChEMBL, Reactome, QuickGO, and UniChem. Used for cross-database protein annotation, pathway retrieval, chemical identifier mapping, and integrated biological data workflows with BioServices.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
polars
High-performance DataFrame library for Python ETL, analytics, and pandas migration. It supports expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.