examples

A command for listing bundled PyWry example programs or running one without opening a graphical window.

In plain words
What is it for?
Finding examples, running a selected script in headless mode, reporting its exit status and created widget IDs, showing recent output, and identifying missing optional Python dependencies.
Why use it?
It provides a quick way to see available examples and check their output without modifying the example files.

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/examples
Clone the repo
git clone --depth 1 https://github.com/deeleeramone/PyWry
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 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 $0.00016 $0.00279
Opus 5 $0.00008 $0.00139
Sonnet 5 $0.00003 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured 2d ago against content hash 08af38b54ac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

examples 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/examples.md · 18 lines

What it actually says

If $ARGUMENTS is empty:

List every script in the PyWry examples directory. For each, print <filename> — <one‑line description from the script's module docstring>. Find the examples directory by running python -c "import pywry, os; print(os.path.join(os.path.dirname(pywry.__file__), '..', 'examples'))" and listing *.py files there (or fall back to ./pywry/examples/ if running from the repo).

If $ARGUMENTS names an example:

  1. Verify the file exists (case‑insensitive match on filename stem).
  2. Run it with PYWRY_HEADLESS=1 python <path> and a 20‑second timeout.
  3. Capture stdout and stderr.
  4. Report: exit code, a summary of any widget IDs created (parse from stdout), and the last 40 lines of output.

Do not modify the example file. Do not pip install anything. If the example requires an extra (e.g. pywry[openai], pywry[anthropic]), surface the ImportError and tell the user which extra to install.

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 · 18 lines · 16 tokens per session scan A 08af38b54ac6

Subscribe to this mod's changes

examples is a command published in the GitHub repository deeleeramone/PyWry (93 stars, last pushed 8d ago), licensed Apache-2.0. It adds 16 tokens to every session and 279 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.