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/ThisIsSadeghi/KMPilotnpx agentmods add skills/thisissadeghi/kmpilot/verify-uiWrote 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/thisissadeghi/kmpilot/verify-ui)<a href="https://agentmods.dev/skills/thisissadeghi/kmpilot/verify-ui"><img src="https://agentmods.dev/badge/skills/thisissadeghi/kmpilot/verify-ui/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/thisissadeghi/kmpilot/verify-ui"><img src="https://agentmods.dev/badge/skills/thisissadeghi/kmpilot/verify-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 42 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00030 | $0.11530 |
| Opus 5.5 | $0.00012 | $0.04612 |
| Sonnet 5.5 | $0.00006 | $0.02306 |
| Haiku 4.5 | $0.00003 | $0.01153 |
Grade A, and why
verify-ui scanned grade A with 2 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Linux: sudo apt-get install python3 (or your distro's package manager) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Task, Read, Write, Edit, Glob, Grep, Bash(mkdir *), Bash(ls *), Bash(curl *), Bash(rm *), Bash(grep *), Bash(wc *), Bash(./gradlew *), Bash(python3 *), AskUserQuestion, mcp__stitch__get_screen, mcp__stitch How it starts
The opening of the file, as written. The whole thing — 633 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify UI
Verify a feature's UI implementation matches the Stitch design at the token level. Produces a two-source token audit (HTML ↔ Code) overlaid with an X-component default-render trap checklist, plus an X-components compliance check.
Architecture Reference: @../_shared/patterns.md Rationale & edge cases: @RATIONALE.md (read only when an edge case stumps you)
Prerequisites
- Feature implemented (build passes)
.claude/docs/_project/stitch-project.jsonexists with afeatures[{featurename}]entry
Workflow
[USER INVOKES] → Preflight → Acquire HTML (reuse or download) → Token Extraction → Catalog → Token Audit → Trap Checklist → Component Overrides Check → Motion Audit → X-Components Check → Present Results → Handle Mismatches → Cleanup → DONE
Step 1: Preflight
- Parse feature name from
$ARGUMENTSor ask the user. - Verify required tooling — Python 3 (used by Step 3 to run
.claude/skills/_shared/extract_tokens.py):
If the command fails (python3 --versionpython3: command not found, non-zero exit), STOP and tell the user:
Do not retry or work around the failure — wait for the user to install Python 3.Python 3 is not installed (or `python3` is not on PATH). /verify-ui extracts design tokens from Stitch HTML via `.claude/skills/_shared/extract_tokens.py` and cannot proceed without it. Install Python 3, then re-invoke /verify-ui {featurename}: - macOS: brew install python3 - Linux: sudo apt-get install python3 (or your distro's package manager) - Windows: https://www.python.org/downloads/ (or `winget install Python.Python.3`) Verify with: python3 --version - Verify files exist:
.claude/docs/_project/stitch-project.jsonwithfeatures[{featurename}]entryfeature/{featurename}/src/commonMain/kotlin/**/presentation/ui/
- Verify build passes:
./gradlew :feature:{featurename}:assembleAndroidMain.
Read .claude/docs/_project/stitch-project.json to load:
projectIdand shared state screen IDs (sharedStateScreens.loading.screenId,sharedStateScreens.failed.screenId)- Per-feature screen IDs (
features[featurename].successScreenId,.emptyScreenId) - Per-feature state selections (
features[featurename].states = { loading, failed, empty }). False flags mean the state was skipped at design time and is not audited below. - Secondary screens (
features[featurename].secondaryScreens[]— each{ kind, screenId, role, label, htmlPath, tokensPath, dimensions }, written by/design-uiStep 1.13b). Each is an additional audit unit keyed by itsrole;kind: surface= an overlay (bottom sheet / dialog / modal / drawer / panel),kind: screen= a full sibling screen of the same feature (own Route, reached via callback). Empty/absent → the feature has none; audit nothing extra. - Backward compatibility: if
statesis absent on a legacy feature entry, derive it from observable state —{ loading: true, failed: true, empty: (emptyScreenId != null) }. Pre-optional-states features had loading/failed always present and empty only when anemptyScreenIdwas recorded. IfsecondaryScreensis absent, the feature has no secondary screens.
What ships with it
1 file 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 First seen · 633 lines · 30 tokens per session scan A 6e38611dda3b
verify-ui is a skill published in the GitHub repository ThisIsSadeghi/KMPilot (57 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 11,530 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
compose-component-design
Use when designing or reviewing reusable Jetpack Compose component APIs with modifier parameters, root layout placement, caller-provided variable content, primitive content parameters, optional content, or boolean shape flags.
proceed-video
A workflow for analysing short recordings of a single user-interface animation. It creates frame grids and motion-trail comparisons so the interaction can be studied visually.
kotlin-android
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
android-jetpack-compose-expert-v2
Android Jetpack Compose Expert workflow skill. Use this skill when the user needs Expert guidance for building modern Android UIs with Jetpack Compose, covering state management, navigation, performance, and Material Design 3 and the operator should preserve the upstream workflow, copied support files, and provenance…
android-studio
Configure Android Studio Gradle projects, emulators, build variants, and signing; diagnose build and runtime failures with AGP and Logcat.