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 musabekisakov-imj/flutter-design-engineer --skill flutter-visual-qagit clone --depth 1 https://github.com/musabekisakov-imj/flutter-design-engineerWrote 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/musabekisakov-imj/flutter-design-engineer/flutter-visual-qa)<a href="https://agentmods.dev/skills/musabekisakov-imj/flutter-design-engineer/flutter-visual-qa"><img src="https://agentmods.dev/badge/skills/musabekisakov-imj/flutter-design-engineer/flutter-visual-qa.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00364 |
| Opus 5 | $0.00028 | $0.00182 |
| Sonnet 5 | $0.00011 | $0.00073 |
| Haiku 4.5 | $0.00006 | $0.00036 |
Grade A, and why
flutter-visual-qa 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 8d 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.
What it actually says
Flutter Visual QA
Rendered output is the evidence. Source inspection alone cannot establish visual quality.
Build a Matrix
Select the smallest representative matrix covering:
- compact and expanded constraints;
- light and dark themes when supported;
- primary, loading, empty, error, and destructive states as applicable;
- default and enlarged text;
- LTR and RTL for localized products.
Record the exact viewport, device-pixel ratio, theme, locale, and fixture state. Read references/visual-qa.md.
For connected or multi-domain products, also read references/connected-product-workflows.md and include partial-source failure in the matrix.
Inspect
Review hierarchy and scan path first, then layout, type, spacing rhythm, color roles, controls, content realism, edge behavior, and pixel-level defects. Compare related states side by side. Distinguish implementation defects from subjective preference.
Prioritize:
- task-blocking clipping, overlap, invisibility, or unreachable controls;
- broken hierarchy, contrast, state communication, or adaptive composition;
- inconsistency and polish defects;
- optional aesthetic refinements.
Golden Tests
Use golden tests for stable components and deterministic fixtures. Control fonts, animations, time, network content, and pixel ratio. Do not approve broad golden updates without inspecting diffs.
Close the Loop
Require at least one refinement pass for material findings and recapture affected states. Report the matrix inspected, fixes made, unverified combinations, and artifact paths.
What ships with it
3 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.
- 8d ago First seen · 41 lines · 56 tokens per session scan A e2759271c7e8
flutter-visual-qa is a skill published in the GitHub repository musabekisakov-imj/flutter-design-engineer (4 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 364 once invoked, about $0.0003 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 skills, from other repositories
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
flutter-mcp-cli-runtime-validation
Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.
mobile-responsive-qa
Verify phone/tablet input and navigation flows.
visual-qa
Use when a website needs rendered screenshot review, Playwright visual regression, multi-viewport checks, horizontal overflow detection, console-error checks, focus/state inspection, or a repeatable visual QA evidence set.
a11y-performance
Use for release-level accessibility and performance review, including WCAG 2.2 AA, keyboard/focus, target size, reduced motion, semantic controls, Core Web Vitals, images/fonts/JavaScript, and animation or 3D performance budgets.
testing-with-marionette
AI-driven Flutter E2E testing via VM Service CLI. Control running Flutter apps in debug mode for smoke tests, regression checks, exploratory testing, and UI automation. Trigger when user mentions E2E testing, UI automation, smoke tests, integration testing, test automation, controlling Flutter apps, VM Service…