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/python-developer-tooling-handbook/claude-plugins/new-python-projectnpx skills add python-developer-tooling-handbook/claude-plugins --skill new-python-projectgit clone --depth 1 https://github.com/python-developer-tooling-handbook/claude-pluginsWhat 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 | $0.00026 | $0.01308 |
| Opus 5 | $0.00013 | $0.00654 |
| Sonnet 5 | $0.00005 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
new-python-project 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 yesterday.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Project Setup Skill
This skill helps set up Python projects using modern tooling. Use it for:
- Creating new projects from scratch
- Adding Python tooling to existing directories
- Converting legacy projects to modern standards
- Setting up specific components (just testing, just linting, etc.)
First: ALWAYS Ask Clarifying Questions
Before creating anything, ALWAYS use AskUserQuestion to confirm key details. Even when the request seems obvious, there are decisions only the user can make.
Always ask about:
- Location - Where should the project be created? (current directory, specific path, temp directory)
- Tooling scope - Include type checking with mypy? What level of linting strictness?
- Testing - Set up pytest with coverage? Any specific test framework preferences?
Also ask when relevant:
- Starting fresh or existing code? - Determines if we use
uv initor add tooling to what's there - Package or application? - Packages are imported by others (
uv init --package), apps are run directly (uv init) - Any constraints? - Python version requirements, specific dependencies, org standards
Example questions for "create a CLI named foo":
Where should I create this project?
[ ] Current directory (/path/to/cwd)
[ ] Create in /tmp/foo
[ ] Other...
What tooling level do you want?
[ ] Full setup (pytest, ruff, mypy, pre-commit)
[ ] Standard (pytest, ruff, pre-commit - no type checking)
[ ] Minimal (just ruff)
Do NOT skip questions just because you can infer some details. The user deserves input on where their project goes and how it's configured.
Core Tooling
Use uv for everything Python:
| Task | Command |
|---|---|
| New package | uv init --package <name> |
| New application | uv init <name> |
| Add dependency | uv add <package> |
| Add dev dependency | uv add --dev <package> |
| Run in environment | uv run <command> |
| One-off tool | uvx <tool> |
Standard dev dependencies: uv add --dev pytest pytest-cov ruff pre-commit
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.
- yesterday First seen · 185 lines · 26 tokens per session scan A a09c806af1fa
new-python-project is a skill published in the GitHub repository python-developer-tooling-handbook/claude-plugins (6 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,308 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…