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/smorinlabs/py-launch-blueprint/new-python-projectnpx skills add smorinlabs/py-launch-blueprint --skill new-python-projectgit clone --depth 1 https://github.com/smorinlabs/py-launch-blueprintWrote 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/smorinlabs/py-launch-blueprint/new-python-project)<a href="https://agentmods.dev/skills/smorinlabs/py-launch-blueprint/new-python-project"><img src="https://agentmods.dev/badge/skills/smorinlabs/py-launch-blueprint/new-python-project.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.03886 |
| Opus 5 | $0.00024 | $0.01943 |
| Sonnet 5 | $0.00010 | $0.00777 |
| Haiku 4.5 | $0.00005 | $0.00389 |
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 4d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-python-project
Bootstrap a fresh Python project from smorinlabs/py-launch-blueprint. This
skill orchestrates the entire path from "I want a new project" to "the repo
exists on GitHub, is rebranded with the user's identity, and the initial
commit is pushed" — typically 60–90 seconds end-to-end.
Why a skill rather than just commands
The bootstrap is small only after you've done it ten times. The first time, a user hits a half-dozen "now what?" moments: gh not authed, package name not a valid Python identifier, post-init failing because the remote doesn't exist yet, etc. This skill encodes the right sequence with preconditions checked at the right time, so each "now what?" becomes a specific actionable prompt — never a surprise.
When to invoke vs. when not to
Invoke when: the user wants a brand new project derived from this template. They don't need to say "py-launch-blueprint" explicitly — phrases like "new Python project from this", "scaffold a project", "start a fresh project using this template" all qualify.
Don't invoke when: the user is inside an existing project (already
rebranded, carrying a press/press-receipt.toml) and just wants to modify
something — that's docs/POST_INIT.md checklist territory, not this
skill.
The runbook
Follow these steps in order. At each step the goal is user clarity, not mechanical execution — explain what's about to happen, especially before anything that creates resources on GitHub or writes to disk.
Step 0 — Confirm the user wants this template (filter step)
This skill triggers broadly on any Python project creation intent. Before doing ANY other work, ask the user whether they want this opinionated bootstrap. The skill is safe to enter on a wide net of phrasings BECAUSE it asks before acting — that's the whole filter-after-trigger contract.
Ask exactly one question, with this shape (adapt phrasing to the conversation; do not invent extra options):
"I can bootstrap this as a full py-launch-blueprint project — uv, ruff, lefthook, CI workflows, release-please, OIDC publishing, the whole production-quality setup. Or set it up minimally (just
uv init, no opinions). The template adds significant tooling; great for projects you'll maintain long-term, overkill for quick throwaway scripts.Use the py-launch-blueprint template? [Y/n]"
What ships with it
1 file 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.
- 4d ago First seen · 376 lines · 49 tokens per session scan A 8b358c94fcaa
new-python-project is a skill published in the GitHub repository smorinlabs/py-launch-blueprint (24 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 3,886 once invoked, about $0.0002 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.
Other skills, from other repositories
django-seedkit
Bootstrap a new Django project, or add components — auth (allauth, magic-link, axes, 2FA), payments (Stripe, dj-stripe), REST (django-modern-rest, django-bolt), Celery / Django Tasks, async views & WebSockets (ASGI, uvicorn worker, django-channels, channels-redis), Tailwind+DaisyUI, favicon, SEO meta tags + sitemap…
compose-python-stack
Design and generate a compatible project from the Python Template component layers or presets. Use when choosing a workload, framework, AI providers, data engines, interfaces, training and serving tools, deployment target, or IaC option; also use when a user wants a simple library, CLI, or API without AI.
maintain-python-template
Extend or repair the Python Template repository while keeping its catalog, Copier questions, templates, generated references, and tests synchronized. Use for adding a framework, provider, database, interface, ML tool, deployment target, preset, compatibility rule, or generated-project capability.
validate-python-stack
Validate the Python Template repository or a project generated from it. Use before committing, publishing, deploying, or reviewing a stack to check catalog compilation, rendering, dependencies, formatting, tests, security workflows, skills, and representative runtime behavior.
operate-ai-stack
Develop, test, and troubleshoot this generated AI or ML workload across its framework, model and embedding providers, retrieval stores, interfaces, training, serving, and observability layers. Use when changing prompts, tools, agents, RAG, MCP, inference, fine-tuning, evaluations, or provider integration.
deploy-python-project
Validate and deploy this generated Python project using its selected target, portable Docker base, and optional Pulumi or Terraform configuration. Use for deployment preparation, local container checks, cloud previews, release rollout, health verification, or deployment troubleshooting.