Borrowing it
Nothing to install: this file belongs to dotnet/maui-labs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dotnet/maui-labs/main/.github/skills/maui-devflow-debug/SKILL.mdgit clone --depth 1 https://github.com/dotnet/maui-labsWrote 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/dotnet/maui-labs/maui-devflow-debug)<a href="https://agentmods.dev/skills/dotnet/maui-labs/maui-devflow-debug"><img src="https://agentmods.dev/badge/skills/dotnet/maui-labs/maui-devflow-debug/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/skills/dotnet/maui-labs/maui-devflow-debug"><img src="https://agentmods.dev/badge/skills/dotnet/maui-labs/maui-devflow-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.01311 |
| Opus 5.5 | $0.00045 | $0.00524 |
| Sonnet 5.5 | $0.00022 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
maui-devflow-debug 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevFlow Debug
Use this skill for the active debugging loop after a MAUI app has DevFlow
packages and builder.AddMauiDevFlowAgent() registered.
When to Use
- Build and run a MAUI app on Android, iOS, Mac Catalyst, macOS, Windows, or GTK.
- Choose or create a simulator/emulator for a project.
- Wait for a DevFlow agent, inspect the visual tree, tap/fill UI, or capture screenshots.
- Recover from DevFlow connection failures after the app is integrated, including broker, port, and Android adb forwarding issues.
- Debug Blazor Hybrid content through DevFlow WebView/CDP commands.
- Read app logs, network captures, preferences, device info, or recordings through DevFlow.
- Iterate on an app bug with a build -> deploy -> inspect -> fix loop.
Route Elsewhere
- If DevFlow packages or
MauiProgram.csregistration are missing, usemaui-devflow-onboard. - If the failure is a generic build or SDK issue with no DevFlow angle, use normal .NET/MAUI diagnostics.
Optional Session Feedback Nudge
If you have retried the same MAUI DevFlow workflow several times, tried multiple
workarounds, or are ending a long DevFlow-assisted debugging session, ask
whether the user wants to run maui-devflow-session-review to summarize friction
for MAUI DevFlow product feedback. Do not run it automatically.
Core Loop
-
Confirm the app is already integrated:
grep -rl "Microsoft.Maui.DevFlow" --include="*.csproj" .If no project has DevFlow package references, stop and switch to
maui-devflow-onboard. -
Pick the target framework and launch target. Do not assume
net10.0; inspect the project first.grep -i "TargetFramework" *.csproj Directory.Build.props 2>/dev/null -
Start or select the device/emulator. For Android and iOS, avoid reusing a simulator/emulator that is already running another app under investigation.
-
Launch the app and keep the launch process alive when required.
- iOS, Android, and Mac Catalyst
dotnet build -t:Runusually block for the app lifetime. - GTK
dotnet runblocks for the app lifetime. - macOS AppKit builds can exit after compiling; launch the
.appseparately.
- iOS, Android, and Mac Catalyst
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +20 lines · -29 tokens per session 73adb0522143
- 2mo ago Changed · -15 lines · +56 tokens per session 98ffb81242cc
- 2mo ago First seen · 112 lines · 85 tokens per session scan A baea4c116044
maui-devflow-debug is a skill published in the GitHub repository dotnet/maui-labs (235 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,311 once invoked, about $0.0004 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.
maui-devflow-debug compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maui-devflow-debugdotnet/maui-labs | Skill | 235 | yesterday | MIT | A | 112 | Claude Code, Codex |
| argent-metro-debuggersoftware-mansion/argent | Skill | 3.2k | yesterday | Apache-2.0 | A | 104 | Claude Code, Codex |
| argent-react-native-optimizationsoftware-mansion/argent | Skill | 3.2k | yesterday | Apache-2.0 | A | 71 | Claude Code, Codex |
| argent-native-profilersoftware-mansion/argent | Skill | 3.2k | yesterday | Apache-2.0 | A | 37 | Claude Code, Codex |
| argent-react-native-app-workflowsoftware-mansion/argent | Skill | 3.2k | yesterday | Apache-2.0 | C | 46 | Claude Code, Codex |
| symbolication-setupnexus-labs-automation/mobile-observability | Skill | 116 | 2mo ago | MIT | A | 40 | Claude Code |
| network-tracingnexus-labs-automation/mobile-observability | Skill | 116 | 2mo ago | MIT | A | 31 | Claude Code |