Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tobitege/Flowery.Unonpx agentmods add rules/tobitege/flowery.uno/unoWrote 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/rules/tobitege/flowery.uno/uno)<a href="https://agentmods.dev/rules/tobitege/flowery.uno/uno"><img src="https://agentmods.dev/badge/rules/tobitege/flowery.uno/uno/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/rules/tobitege/flowery.uno/uno"><img src="https://agentmods.dev/badge/rules/tobitege/flowery.uno/uno.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 | $0.13609 | $0.13609 |
| Opus 5.5 | $0.05444 | $0.05444 |
| Sonnet 5.5 | $0.02722 | $0.02722 |
| Haiku 4.5 | $0.01361 | $0.01361 |
Grade C, and why
uno scanned grade C with 1 finding 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 today.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Base on system TextBox style, then customize --> How it starts
The opening of the file, as written. The whole thing — 1,541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flowery.Uno MANDATORY Development Notes
This file captures learnings and patterns discovered during Flowery.Uno development for future reference.
🚨 READ THIS FIRST (top crash-prevention rules)
If you only read the first ~50 lines of this file, read this section. These rules prevent the most common Uno “mystery” runtime crashes:
- ContentControls that rebuild
Content: ALWAYS detach before re-parenting.- Pattern:
_userContent = Content; Content = null; BuildVisualTree(); _presenter.Content = _userContent; - See “UIElement can only have one parent” (search for
### 19).
- Pattern:
- Never bind a
ContentPresenterback tothis.Contentin a control that later setsContent = _rootGrid(creates self-parenting / re-parenting issues).- See the anti-pattern example under
### 19.
- See the anti-pattern example under
- Don’t use
PathIcondynamically in code-behind (Uno can throwArgumentException: Value does not fall within the expected range.).- Use
Microsoft.UI.Xaml.Shapes.PathorFlowery.Helpers.FloweryPathHelpersinstead (search for### 18).
- Use
- Use
DaisyControlExtensions.Iconfor button icons - This is the GOLD STANDARD (see section below). - Ambiguous type names:
Path,Color, etc. often need aliasing/qualification.- Example:
using Path = Microsoft.UI.Xaml.Shapes.Path;(search for### 12).
- Example:
- Do NOT merge
ms-appx:///uno.toolkit.*/Styles/Generic.xaml.Uno.Toolkit.*packages do not shipStyles/Generic.xaml. Adding that dictionary will fail to load resources and can crash at startup. ShadowContainer only needs the package reference.
Neumorphic Takeaways
For the distilled, field-tested fixes and integration notes from recent stability work, see llms-static/neumorphic.md → Field-Tested Integration Notes (Session Takeaways).
ThemeShadow + Elevation Learnings
- ThemeShadow requires explicit receivers: add the receiver to
ThemeShadow.Receivers(see Uno tests in!uno/src/SamplesApp/UITests.Shared/Windows_UI_Xaml_Media/ThemeShadowTests). - Translation.Z defines shadow depth: the casting element must have a
TranslationZ (e.g.,0,0,6). - CornerRadius is respected when ThemeShadow is applied directly to
BorderorRectanglewith radius properties (no custom masking required). - WASM/Skia elevation: for rounded shadows, apply
SetElevationto the template’sBorder(e.g.,ButtonBorder), not theButtoncontrol itself.
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.
- today Changed · -11 tokens per session f2f9a1a74d57
- 2d ago Changed · +2 lines · +161 tokens per session 9475ec26be19
- 13d ago First seen · 1,539 lines · 13,459 tokens per session scan C dfa0d501cead
uno is a cursor rule published in the GitHub repository tobitege/Flowery.Uno (16 stars, last pushed today), licensed MIT. It adds 13,609 tokens to every session, about $0.0544 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other cursor rules, from other repositories
roslyn-mcp-overview
RoslynMcpServer — architecture, layout, version, DI.
roslyn-mcp-pitfalls
Known pitfalls and regression lessons from production use.
roslyn-mcp-docs-agents
Docs sync AGENTS/README, agent conventions, PowerShell, secrets.
roslyn-mcp-tools
MCP tool mapping — skeleton vs decompile vs symbols vs build.
roslyn-mcp-version-bump
Auto-bump Version after successful MCP self-build and reload.
roslyn-mcp-decompile
Assembly resolve, ILSpy decompile, NuGet/BCL fallback.