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 skills add dotnet/maui-labs --skill verification-protocolgit 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/verification-protocol)<a href="https://agentmods.dev/skills/dotnet/maui-labs/verification-protocol"><img src="https://agentmods.dev/badge/skills/dotnet/maui-labs/verification-protocol/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/verification-protocol"><img src="https://agentmods.dev/badge/skills/dotnet/maui-labs/verification-protocol.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 | $0.00105 | $0.01376 |
| Opus 5.5 | $0.00042 | $0.00550 |
| Sonnet 5.5 | $0.00021 | $0.00275 |
| Haiku 4.5 | $0.00011 | $0.00138 |
Grade A, and why
verification-protocol 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Protocol
Verification means proving that code changes produce the intended result on a real device, against reference material, through interactive exercise — not just proving they compile. A fresh binary is built and deployed, the UI is inspected via DevFlow visual tree, navigation is exercised interactively, features are tested with real inputs, and results are compared against the original BaristaNotes app code and reference screenshots. A broken tool in this chain is a problem to solve, not a reason to skip a step.
No task is done until verified on device. "It builds" is not done. A screenshot of a stale binary is not done.
Rule 1: Own Your Dependencies
When a tool or dependency is broken, fix it. The solution is in the repo, the reference code, or the documentation you were given.
| Problem | Wrong | Right |
|---|---|---|
| DevFlow won't connect | "⚠️ Skipped — agent didn't connect" | Diagnose: maui-devflow diagnose. Check csproj integration, broker status, entitlements, ports. Fix the issue. DevFlow source is in this repo — build a custom version if needed. |
| API key missing | "⚠️ Needs API key" | Read the reference app's code. It shows exactly how to source the key (IConfiguration, appsettings.json, env vars). Do what it does. |
| Simulator issue | "⚠️ No simulator available" | xcrun simctl create "Verify" "iPhone 16 Pro" then boot it. |
| Build fails on iOS TFM | "✅ Builds on Release" | Fix the iOS Debug build. That's the one that deploys. |
If you report "blocked" and the answer is in the repo — that is a failure.
Rule 2: Verify Against Reference
When reference material exists (original app code at ~/work/BaristaNotes, screenshots at
~/Downloads/baristanotes-screenshots/), compare your result against it. Do not check if
"it looks reasonable."
Rule 3: Verify the Specific Change
Generic verification is not verification. After completing all levels, explicitly test the exact behavior your task was supposed to produce or fix:
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 First seen · 110 lines · 105 tokens per session scan A 054a48adf811
verification-protocol is a skill published in the GitHub repository dotnet/maui-labs (229 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 1,376 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 2026-09-03.
Other skills, from other repositories
argent-test-ui-flow
Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running UI test scenarios, manual QA steps, visible UI changes, or visual behavior.
mobile-automation
Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.
argent-qa-e2e
Write repeatable QA regression e2e tests from test cases, tickets, or acceptance criteria. Use when the user asks to write, automate, or generate an e2e test or preserve an automated regression scenario, with deterministic setup, stable targets, executable structural or visual evidence, and two consecutive full…
argent-create-e2e
Create, record, edit, replay, or repair reusable Argent e2e test YAML files. Use when the user asks to record, replay, or run an e2e test or a repeatable device path, set up profiling or an A/B comparison, or invoke the authoring engine behind argent-qa-e2e. Also use before repeating three or more interactions. For…
mobilewright-cli
Automate iOS and Android apps on simulators, emulators and real devices, explore screens and write Mobilewright tests.
Appium Mobile Testing
Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.