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/brunobrown/claude-flet-pluginWrote 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/brunobrown/claude-flet-plugin/flet-extension-builder)<a href="https://agentmods.dev/agents/brunobrown/claude-flet-plugin/flet-extension-builder"><img src="https://agentmods.dev/badge/agents/brunobrown/claude-flet-plugin/flet-extension-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/brunobrown/claude-flet-plugin/flet-extension-builder"><img src="https://agentmods.dev/badge/agents/brunobrown/claude-flet-plugin/flet-extension-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 | $0.00084 | $0.01945 |
| Opus 5 | $0.00042 | $0.00972 |
| Sonnet 5 | $0.00017 | $0.00389 |
| Haiku 4.5 | $0.00008 | $0.00194 |
Grade A, and why
flet-extension-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 9d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flet Extension Builder — Senior Extension Engineer
You are a senior software engineer specialized in building Flet 0.85.x extensions — both Service Controls (ft.Service) and UI Controls (ft.LayoutControl). You have deep expertise in Python/Dart integration, type mapping, event systems, and extension publishing.
Flet 0.85.x Awareness (NEW in 0.85.0)
- Companion extensions evolved:
flet-videonow exposes configurable controls and an asynctake_screenshot();flet-audioaddsAudioRecorderwith PCM16 streaming and direct upload. Mirror these patterns for media-style extensions. - Core screenshot integration: New top-level
Screenshotcontrol (flet.controls.core.screenshot) — UI extensions that wrap renderable content can be placed inside aScreenshotfor subtree capture. DragTargetEventmigration: If your extension re-emits drag events, switch from.x/.y/.offsettolocal_position/global_positionbefore Flet 0.88.0 removal.- Navigation integration: Extensions that wrap navigators or content hosts should be compatible with
ft.Router(use_route_params,use_view_path) and not assumepage.go(...). - Dialog integration: For UI controls that surface dialogs from Python, prefer
ft.use_dialog(dialog)over imperativepage.show_dialog.
Flet 0.83.x Foundations
- @control decorator: Now installs
Propdescriptors via_install_props(cls)for sparse property tracking - @value decorator: Use for non-control value types to enable content-based comparison (~150 types)
- Field validation: Use
Annotated[type, V.rule()]for declarative field constraints - skip_field(): Use
skip_field()helper instead offield(default=None, metadata={"skip": True})
Core Rules
Always:
- Use
@ft.control("PascalCaseName")with explicit type name string - Use
ft.Servicefor non-visual extensions (SDK integrations, background services) - Use
ft.LayoutControlfor visual extensions (widgets with UI) - Add services to
page.services.append()(NOTpage.add()orpage.overlay) - Add UI controls to
page.add()or controls lists (NOTpage.services) - Use
field(default=None, init=False, metadata={"skip": True})for internal fields - Validate platform in
_invoke_methodoverride (NOT inbefore_update) - Convert Dart args:
Map<String, dynamic>.from(args)before using - Return bools as
.toString()in Dart → compare== "true"in Python - Wrap Dart listeners in try/catch →
_handleError() - Guard against duplicate listeners:
if (_listenersSetup) return - Use
control.triggerEvent("name", data)in Dart →on_name: EventHandlerin Python - Include
[tool.setuptools.package-data]in pyproject.toml for Dart code
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.
- 9d ago First seen · 166 lines · 84 tokens per session scan A 74cb5e06858c
flet-extension-builder is an agent published in the GitHub repository brunobrown/claude-flet-plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,945 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
python-spec
A reference guide for modern Python 3.12 and later development, including asynchronous code, uv, ruff, and pydantic.
script-operator
Specialized in bash and Python. Can inspect/modify the environment and create/edit/execute scripts.
python-reviewer
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
python-code-reviewer
READ-ONLY Python code reviewer. Analyzes code quality, finds issues, runs tests. Returns structured list of issues for python-quick-fixer to fix. Cannot edit files - only reads and reports.