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/commands/brunobrown/claude-flet-plugin/flet-review)<a href="https://agentmods.dev/commands/brunobrown/claude-flet-plugin/flet-review"><img src="https://agentmods.dev/badge/commands/brunobrown/claude-flet-plugin/flet-review/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/commands/brunobrown/claude-flet-plugin/flet-review"><img src="https://agentmods.dev/badge/commands/brunobrown/claude-flet-plugin/flet-review.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 | $0.00014 | $0.01951 |
| Opus 5 | $0.00007 | $0.00975 |
| Sonnet 5 | $0.00003 | $0.00390 |
| Haiku 4.5 | $0.00001 | $0.00195 |
Grade A, and why
flet-review 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 10d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/flet-review — Review Flet Code
You are performing a comprehensive code review of Flet code. First, determine whether the code is a Flet app or a Flet extension, then apply the appropriate checklist.
Step 1: Identify Code Type
Scan the codebase to determine:
- App: Contains
ft.run(main),@ft.component,page.render_views() - Extension: Contains
@ft.control("Name"),ft.Serviceorft.LayoutControl - Both: App that uses a custom extension
Step 2: App Checklist
If reviewing a Flet app, check all of these:
Entry Point & Rendering
- Uses
ft.run(main)— NOTft.app() - Uses
page.render_views()orpage.render()— NOTpage.add() - Does NOT call
page.update()manually (declarative mode handles this) -
page.render(Component)passes reference, NOTpage.render(Component())
State Management
-
@ft.observablecomes BEFORE@dataclass(order matters) -
ft.use_state()used for local form fields (not@ft.observable) - Observable lists use
.append()/.clear()to trigger re-renders - State created outside components in
main()when handlers need access - No direct mutation of observable list elements (
items[0] = x)
Hooks
- All hooks called inside
@ft.componentonly (never in regular functions) - Hooks NOT inside conditionals or loops (fixed order required)
-
use_effectcleanup usescleanup=parameter (NOT return value) -
use_effectdependencies array is correct ([] for mount-only) -
use_refused for mutable refs that shouldn't trigger re-renders
Components
- All components use
@ft.componentdecorator - Context accessed via
ft.use_context(AppCtx)(not passingpageas prop) - Factory functions used in loops to avoid closure traps
- Async handlers use try/except for error handling
Navigation
-
view_ref[0].show_drawer()used (NOTpage.show_drawer()) - PAGE_BUILDERS dict maps page IDs to component functions
- Router clears
page.viewsbefore adding new views (imperative router pattern) -
on_view_pophandler implemented for router-based navigation - 0.85.0+: New apps prefer
ft.Routerover hand-rolledon_route_changefor nested routes/loaders - 0.85.0+:
ft.Router(manage_views=True, ...)paired withpage.render_views(App)(notpage.render) - 0.85.0+:
View(route=ft.use_view_path())in view-stack mode (unique Navigator key per stack level) - 0.85.0+:
use_route_outlet()only called inside layout-route components (routes withchildren) - 0.85.0+: No
page.go(route)— usepage.navigate(route)(sync) orawait page.push_route(route)(async) - 0.85.0+:
pop_views_untilpaired withon_views_pop_until(noton_view_pop)
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.
- 10d ago First seen · 150 lines · 14 tokens per session scan A 57dd6886b27d
flet-review is a command published in the GitHub repository brunobrown/claude-flet-plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,951 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 2026-08-31.
Other commands, from other repositories
critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.
check-architecture
Angular Architecture Review.
react-patterns
Review React code for performance and composition patterns — 50+ rules ranked by impact.
fec-review
Conduct a standardized review of the specified file or recently changed front-end code, output a graded review report and save it as a Markdown file.
web-review
Review a web (HTML5) project for structure, architecture, maintainability, and risk.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.