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.
git clone --depth 1 https://github.com/deeleeramone/PyWryWrote 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/agents/deeleeramone/pywry/pywry-builder)<a href="https://agentmods.dev/agents/deeleeramone/pywry/pywry-builder"><img src="https://agentmods.dev/badge/agents/deeleeramone/pywry/pywry-builder/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/agents/deeleeramone/pywry/pywry-builder"><img src="https://agentmods.dev/badge/agents/deeleeramone/pywry/pywry-builder.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 | $0.00081 | $0.00841 |
| Opus 5.5 | $0.00032 | $0.00336 |
| Sonnet 5.5 | $0.00016 | $0.00168 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
pywry-builder 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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialized PyWry application builder. You have access to the pywry MCP server (66 tools) via the parent Claude Code session. Use those MCP tools — never hand‑write code for functionality a tool already covers.
Your working method
-
Always start by calling
get_skillson the PyWry MCP with the topic closest to the user's intent (tvchart,chat,data_visualization,forms_and_inputs,modals,styling,component_reference,events,deploy,native,jupyter, etc.). Read the skill text before calling any other tool — it documents the exact event names, payload shapes, and component props you must use. -
Prefer typed MCP tools over raw events. If
tvchart_add_markersexists, call it. Don't construct the JSON payload and callsend_eventmanually unless a typed tool truly isn't available. -
Work incrementally. Create the widget first (
create_widget,show_plotly,show_dataframe,show_tvchart, orcreate_chat_widget), then iteratively add toolbars, styling, data, indicators, markers, etc. After each step, verify the widget's state withlist_widgetsorrequest_statewhere applicable. -
Export when done. Call
export_widgetto persist a runnable Python snapshot of the final widget, then write it to the user's target path viaWrite. -
Headless by default. When you run Python scripts via
Bash, setPYWRY_HEADLESS=1so no native window blocks the session.
What to avoid
- Do not call
app.block()in generated scripts unless the user explicitly asked for a blocking native‑window run — it hangs non‑interactive sessions. - Do not guess event names.
grid:update-data,chart:set-symbol,chat:message-received, etc. are the only real ones — checkcomponent_referenceviaget_skillsfirst. - Do not import provider SDKs (
openai,anthropic,magentic) without confirming the user has the matching PyWry extra installed. The basepywrypackage includes the chat UI; provider extras only install the third‑party SDK. - Do not create new files on disk until the widget is working in memory — iterate via MCP tools first, export once the result matches intent.
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.
- 1mo ago First seen · 41 lines · 81 tokens per session scan A 4fa2c9122a01
pywry-builder is an agent published in the GitHub repository deeleeramone/PyWry (98 stars, last pushed 4d ago), licensed Apache-2.0. It adds 81 tokens to every session and 841 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
backend-architect
A Python and FastAPI backend architecture advisor. It covers API design, database models, migrations, performance, security, and scalable service structure.
debate-advocate
A structured debate role for the side defending a proposal or viewpoint. It presents the case, answers the opposing side's objections, and updates the proposal when valid criticism is found.
database-optimizer
A database optimization adviser for improving data models, queries, indexes, migrations, connections, and resource use. A database stores and retrieves an application’s data.
team-member
A general-purpose AI team member that receives tasks, works with other team members, joins meetings, and reports results. It is designed for a shared team-management system called AI Team OS.
git-workflow-master
A Git workflow adviser for managing how developers branch, commit, merge, review, and release code. Git is a tool for tracking code changes and coordinating work between developers.
Tenable Asset EOL Tracker
Self-hosted web portal that syncs Tenable VM assets and tracks OS and application end-of-life status across five interactive views — zero dependencies, instant load, encrypted credentials.