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 pledgeandgrow/pledge-skills --skill uvgit clone --depth 1 https://github.com/pledgeandgrow/pledge-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/pledgeandgrow/pledge-skills/uv)<a href="https://agentmods.dev/skills/pledgeandgrow/pledge-skills/uv"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/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/pledgeandgrow/pledge-skills/uv"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/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 | $0.00034 | $0.01880 |
| Opus 5 | $0.00017 | $0.00940 |
| Sonnet 5 | $0.00007 | $0.00376 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade C, and why
uv-docs 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.
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.
- **No Rust or Python required** — installable via curl or pip How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uv — Extremely Fast Python Package & Project Manager
Version: uv 0.11.x | Source: https://docs.astral.sh/uv/
uv is an extremely fast Python package and project manager, written in Rust. It serves as a single tool to replace pip, pip-tools, pipx, poetry, pyenv, twine, virtualenv, and more. It provides comprehensive project management with a universal lockfile, runs scripts with inline dependency metadata, installs and manages Python versions, runs and installs CLI tools, includes a pip-compatible interface, supports Cargo-style workspaces, and is disk-space efficient with a global cache for dependency deduplication.
Key Benefits
- 10-100x faster than pip — written in Rust
- Single tool — replaces pip, pip-tools, pipx, poetry, pyenv, twine, virtualenv
- Universal lockfile — cross-platform
uv.lockfor reproducible installations - Project management —
uv init,uv add,uv sync,uv lock,uv run,uv build,uv publish - Script execution — inline dependency metadata (PEP 723),
uv runwith--withfor ephemeral deps - Python version management — install, pin, and switch between Python versions
- Tool management —
uvx/uv tool runfor ephemeral tools,uv tool installfor persistent - Pip-compatible interface — drop-in replacement for
pip install,pip compile,pip sync - Workspaces — Cargo-style workspaces for scalable multi-package projects
- Global cache — deduplication of dependencies across projects
- Cross-platform — macOS, Linux, and Windows
- No Rust or Python required — installable via curl or pip
File Index
| File | Topics |
|---|---|
getting-started.md |
Installation (standalone, PyPI, Homebrew, WinGet, Scoop, Docker, Cargo), first steps, features overview, upgrading, shell autocompletion, uninstallation |
projects.md |
Creating projects, project structure (pyproject.toml, .python-version, .venv, uv.lock), managing dependencies (standard, optional, dev groups, sources, editable, build deps), project config (requires-python, entry points, build systems, packaging), workspaces, building and publishing |
scripts.md |
Running scripts without/with dependencies, inline script metadata (PEP 723), declaring script deps with uv add --script, shebang executables, alternative indexes, locking script deps, reproducibility with exclude-newer, Python versions, GUI scripts (.pyw) |
tools.md |
Running tools with uvx, --from for package name differences, version selection (@version, --from), extras, alternative sources (git, branches, tags, commits), plugins with --with, installing tools, upgrading tools, Python versions, legacy Windows scripts |
python-versions.md |
Managed vs system Python, requesting versions (--python, version formats), installing Python, viewing and finding Python, automatic downloads, discovery rules, project Python versions, pinning, upgrading, pre-releases, free-threaded Python, PyPy, distributions |
pip-interface.md |
Creating virtual environments, using arbitrary environments, environment discovery, installing packages (PyPI, git, local, editable), installing from files (requirements.txt, pyproject.toml, extras, groups), uninstalling, locking with uv pip compile, syncing with uv pip sync, constraints, build constraints, overrides, inspecting environments (list, show, check, tree, freeze), declaring dependencies (pyproject.toml, requirements.in), pip compatibility differences |
indexes.md |
Defining indexes ([[tool.uv.index]]), index priority, default index, pinning packages to indexes, search strategies (first-index, unsafe-first-match, unsafe-best-match), authentication (credentials, providers), flat indexes, --index-url and --extra-index-url |
caching.md |
Dependency caching semantics (registry, URL, git, local, flat indexes), cache safety, clearing cache (clean, prune, prune --ci), caching in CI, cache directory location, --refresh and --reinstall |
docker.md |
Available images (distroless, debian, alpine), installing uv in Docker (copy binary, installer), installing projects, using the environment, bytecode compilation, cache mounts, intermediate layers, non-editable installs, pip interface in Docker, image provenance |
ci-integrations.md |
GitHub Actions (setup-uv, Python setup, matrix, syncing, caching, uv pip, private repos, trusted publishing), GitLab CI/CD |
git-auth.md |
SSH authentication, HTTP authentication, persistence of credentials, --raw option, Git credential helpers, gh CLI |
reference.md |
Configuration hierarchy, project metadata settings, configuration settings (add-bounds, cache-dir, compile-bytecode, concurrent-*, index-strategy, link-mode, no-binary, no-build, python-downloads, resolution, system-certs, torch-backend, trusted-publishing, upgrade), environment variables reference (cache, Python, project, indexes, deps, publishing, tools, network, config) |
integrations.md |
Jupyter (within project, kernels, standalone, non-project, VS Code), marimo (standalone, inline script metadata, within project, non-project, running as scripts) |
authentication.md |
HTTP credentials (netrc, uv credentials store, native storage preview, keyring providers, persistence), TLS certificates (rustls backend, system certs, custom certs with SSL_CERT_FILE/SSL_CERT_DIR/SSL_CLIENT_CERT, insecure hosts), uv auth CLI (login, logout, token, helper, storage backend), third-party services (Azure, Google, AWS, JFrog, Hugging Face HF_TOKEN) |
resolution.md |
Dependency resolution concepts (direct vs transitive, platform markers, platform-specific vs universal resolution, limited/required environments, dependency preferences, resolution strategies, pre-release handling, multi-version resolution with fork-strategy, constraints, overrides, exclusions, reproducible resolutions with exclude-newer) |
cli-reference.md |
Full CLI reference (uv auth, run, init, add, remove, version, sync, lock, export, tree, format, check, audit, tool, python, pip, venv, build, publish, workspace, cache, self, help, global options) |
preview.md |
Preview features (enabling with --preview/UV_PREVIEW/--preview-features, available features list including add-bounds, centralized-project-envs, json-output, pylock, native-auth, auth-helper, malware-check, etc., disabling with --no-preview) |
policies.md |
Versioning policies (crate versioning, cache versioning, lockfile versioning), project structure and files (pyproject.toml, project environment .venv, centralized environments preview, uv.lock lockfile, pylock.toml PEP 751 relationship) |
What ships with it
18 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.
- authentication.md 5.4 KB
- caching.md 4.2 KB
- ci-integrations.md 5.9 KB
- cli-reference.md 7.8 KB
- docker.md 4.7 KB
- getting-started.md 6.1 KB
- git-auth.md 2.7 KB
- indexes.md 5.0 KB
- integrations.md 3.0 KB
- pip-interface.md 8.7 KB
- policies.md 3.4 KB
- preview.md 2.5 KB
- projects.md 13 KB
- python-versions.md 5.9 KB
- reference.md 16 KB
- resolution.md 5.0 KB
- scripts.md 4.7 KB
- tools.md 4.3 KB
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 · 118 lines · 34 tokens per session scan C d444c9963066
uv-docs is a skill published in the GitHub repository pledgeandgrow/pledge-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,880 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
python-runtime
Use this skill when the user needs to install, upgrade, or troubleshoot Python and pip environments. Covers four-tier fallback strategy: (1) DesireCore HTTP API for in-app installation, (2) DesireCore built-in Hatch CLI for Python version management, (3) system package managers (brew/apt/dnf/winget), (4) community…
mark2video
A function that adds a text watermark to a video. You can choose the watermark text, font size, font type, and color.
search_specify_type_file
A file-search function that finds files with a specified extension, such as .txt, .py, or .pdf, under a given folder.
course
A Python helper that displays tutorials, group information, source-code links, and other resources for the python-office library in a terminal.
python-repo-quickstart
Quickly analyzes Python repositories to understand their purpose, structure, and setup requirements. Use when Claude needs to onboard to a new Python codebase, understand project structure, identify entry points, determine dependencies, or generate setup instructions. Trigger when users ask to "analyze this Python…
python
Use when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms, src/ layout + pyproject.toml with uv, ruff+mypy+pytest gate. NOT a FastAPI/ASGI service (that is fastapi), NOT a deep pytest suite (that is…