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/deeleeramone/pywry/autonomous_buildingnpx skills add deeleeramone/PyWry --skill autonomous_buildinggit 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/skills/deeleeramone/pywry/autonomous_building)<a href="https://agentmods.dev/skills/deeleeramone/pywry/autonomous_building"><img src="https://agentmods.dev/badge/skills/deeleeramone/pywry/autonomous_building.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 | $0.00019 | $0.01278 |
| Opus 5 | $0.00010 | $0.00639 |
| Sonnet 5 | $0.00004 | $0.00256 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
autonomous_building 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Application Building
This skill teaches agents how to use PyWry MCP's agentic tools to autonomously design, build, and export complete widget applications from a plain-English description.
When to Use These Tools
Use the agentic tools when you need to:
- Build a complete PyWry app from a description without manual step-by-step tool calls
- Deliver a full Python project (main.py, requirements.txt, README.md, widgets/)
- Interactively gather requirements from the user before generating code
- Show real-time progress to the user during long build operations
Available Agentic Tools
plan_widget — AI-Planned Widget Spec
Sends the description to the LLM via sampling and returns a validated WidgetPlan JSON object.
Use this to inspect the plan before committing to building.
# Returns a WidgetPlan JSON (no widget is created yet)
result = await client.call_tool("plan_widget", {
"description": "A crypto price dashboard with symbol selector and refresh button"
})
plan = json.loads(result[0].text)
# plan contains: title, html_content, toolbars, callbacks, width, height, ...
build_app — End-to-End Autonomous Builder
The primary tool for autonomous app building. One call:
- Samples a
WidgetPlanfrom the description - Registers the widget in the session
- Returns
widget_idand complete runnable Python code
result = await client.call_tool("build_app", {
"description": "Task tracker with add/remove buttons and completion percentage",
"open_window": False # set True to open a native window immediately
})
data = json.loads(result[0].text)
widget_id = data["widget_id"]
python_code = data["python_code"] # paste into a .py and run directly
The returned python_code is a fully self-contained Python script requiring only pywry.
export_project — Complete Python Project Package
Takes one or more widget_ids and generates a full project tree:
my_app/
main.py ← entry-point
requirements.txt ← dependencies
README.md ← quickstart docs
widgets/
<widget_id>.py ← one file per widget
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 · 184 lines · 19 tokens per session scan A dd50c1e3a2b2
autonomous_building is a skill published in the GitHub repository deeleeramone/PyWry (93 stars, last pushed 10d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,278 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.
Other skills, from other repositories
go-rig
Use this skill when building, reviewing, or refactoring Go code that must follow strict design discipline — ATDD/TDD workflow, explicit dependency injection, package-boundary discipline, and structured code review. Complements CLAUDE.md by focusing on process and design judgment rather than version-specific Go…
frontend-dashboard
Use this skill when editing the embedded dashboard frontend in this repository. It focuses on preserving the single-file embedded SPA model, keeping the UI lightweight, and avoiding unnecessary frontend tooling or dependencies.
go-review
Use this skill when the task is to review Go code in this repository. Focus on bugs, regressions, API compatibility, test gaps, concurrency risks, and violations of the zero-dependency and root-facade constraints.
project-ops
Use this skill when working on repository operations in this project, including build, test, lint, release, CI alignment, Makefile-driven checks, and operational packaging constraints.
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.
mcp-visual-output
Interactive MCP visual output via @json-render/mcp: upgrade plain JSON tool responses to dashboards rendered in sandboxed iframes inside MCP clients like Claude, Cursor, and ChatGPT. Use when a tool result would read better as a stat grid, data table, or status badge than as text. For the server itself (transport…