scaffold

A command that creates a small starter PyWry application in a new directory. It makes a Python entry point, project settings, a README, and a standard Python ignore file.

In plain words
What is it for?
Starting a PyWry app with a selected interface type and preparing it to run or format with the documented commands.
Why use it?
It gives a new project the basic files and a runnable example without requiring you to assemble the structure yourself. The template changes according to the requested interface type, such as a widget, chat, chart, or dashboard.

Command

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 commands/deeleeramone/pywry/scaffold
Clone the repo
git clone --depth 1 https://github.com/deeleeramone/PyWry
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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 $0.00024 $0.00408
Opus 5 $0.00012 $0.00204
Sonnet 5 $0.00005 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 2d ago against content hash 03eca212e4aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scaffold 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 2d 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.

claude/plugins/pywry/commands/scaffold.md · 23 lines

What it actually says

Scaffold a new PyWry app in a fresh directory named by the first positional argument $ARGUMENTS. If no argument is given, ask the user for a name.

Before writing any files, call the get_skills MCP tool with the topic that matches --kind (default widget → skill component_reference, chatchat, tvcharttvchart, dashboarddata_visualization). Read the returned skill text before choosing the template.

Then create the following files in ./<app-name>/:

  1. main.py — a runnable PyWry app using PyWry().show*(...) appropriate to --kind. Keep it under 40 lines. Use headless‑friendly patterns (no hard‑coded block() call at module import level).
  2. pyproject.toml — minimal, pinned to pywry[mcp]>=2.0.0rc7. Use the user's Python version.
  3. README.md — one paragraph describing the app and a python main.py quick start.
  4. .gitignore — standard Python entries (__pycache__/, *.pyc, .venv/).

After writing files:

  • Run ruff format on main.py
  • Print the directory listing
  • Tell the user: cd <app-name> && pip install -e . && PYWRY_HEADLESS=1 python main.py to run headlessly, or drop PYWRY_HEADLESS=1 to see the native window

Do not install the package or run the app automatically. The user should review the generated code first.

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. 2d ago First seen · 23 lines · 24 tokens per session scan A 03eca212e4aa

Subscribe to this mod's changes

scaffold is a command published in the GitHub repository deeleeramone/PyWry (93 stars, last pushed 9d ago), licensed Apache-2.0. It adds 24 tokens to every session and 408 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 2026-08-30.