design-qa

design-qa is a skill for Claude Code, Codex from agentlas-ai/agentlas-desktop. It costs 29 tokens per session (717 once invoked), scanned A, original, Apache-2.0.

A visual quality check that compares a rendered prototype screenshot with a target design image at matching dimensions.

In plain words
What is it for?
Use it to compare screenshots side by side, inspect five visual areas, and iteratively correct mismatches until the required target comparison is met.
Why use it?
It helps find visual differences in a prototype before delivery instead of relying on an informal inspection.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: $skill-name invocation.

Good fit Use it to compare screenshots side by side, inspect five visual areas, and iteratively correct mismatches until the required target comparison is met.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentlas-ai/agentlas-desktop/design-qa
Install

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.

Any agent
npx skills add agentlas-ai/agentlas-desktop --skill design-qa
Clone the repo
git clone --depth 1 https://github.com/agentlas-ai/agentlas-desktop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for design-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/design-qa.svg)](https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/design-qa)
Your own site
<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/design-qa"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/design-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00717
Opus 5 $0.00015 $0.00358
Sonnet 5 $0.00006 $0.00143
Haiku 4.5 $0.00003 $0.00072

Measured 3d ago against content hash 13e4c63ff7d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

design-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 3d 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.

plugins/design/skills/design-qa/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Purpose

Acts as the mandatory quality gate before prototype delivery by conducting a 1:1 side-by-side visual comparison between the pinned visual target (assets/target-design.png) and the live browser rendering (implementation.png), iterating until pixel-faithful alignment is achieved.

Preconditions

  • The pinned visual target (assets/target-design.png or equivalent source mockup) must exist.
  • A rendered prototype view (implementation.png captured from the local browser runtime) must be available.
  • If either artifact cannot be retrieved or rendered, mark final result: blocked and halt handoff.
  • Adhere to $qa-rubric and $critical-overrides.

Steps

  1. Normalize Viewport & Pixel Density:
    • Align the implementation capture (implementation.png) and assets/target-design.png to the exact same CSS pixel dimensions, aspect ratio, and device scale factor.
    • For mobile apps, evaluate the inner screen content at 1:1 CSS pixels rather than container bezels.
  2. Side-by-Side Comparison & Inspection:
    • Place assets/target-design.png and implementation.png together in a side-by-side comparison view.
    • Systematically inspect the 5 required fidelity surfaces:
      • Typography: Font family, optical weights, sizes, line heights, letter spacing, and wrapping.
      • Spacing & Rhythm: Margins, padding, grid alignment, section gaps, border radii, and elevation.
      • Colors & Tokens: Color palette accuracy, background/foreground contrast, and semantic state styling.
      • Image Quality & Assets: Asset fidelity, resolution, sharpness, and absence of makeshift CSS/SVG approximations.
      • Copy & Content: Accurate matching of headings, labels, metrics, and visible body copy.
  3. Iterative Remediation Loop:
    • Classify observed differences into P0 (blocker), P1 (major), P2 (moderate), and P3 (minor polish).
    • For any P0/P1/P2 findings:
      1. Apply targeted code/CSS fixes to the prototype.
      2. Re-capture the browser screenshot at the identical viewport and state.
      3. Re-compare against assets/target-design.png.
    • Repeat until no actionable P0/P1/P2 differences remain.
  4. Generate QA Report: Document findings, remediation history, and evidence paths in design-qa.md at the project root with final result: passed.

Read the full file on GitHub · 48 lines

Changes

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.

  1. 3d ago Changed · +4 lines 13e4c63ff7d9
  2. 7d ago First seen · 44 lines · 29 tokens per session scan A b1ab0088fb4d

Subscribe to this mod's changes

design-qa is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 717 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

architecture-diagram

How to draw and maintain the architecture diagram Ensemblr keeps for a workspace — ensemblrgetarchitecturediagram to fetch the stored one (it answers with null when nobody has drawn this workspace yet), the IR shape, how to derive it from the codebase, and ensemblrupdatearchitecturediagram to store it. Read this when…

ensemblr-hq/ensemblr · 94 tokens

frame-macos-notification

Realistic macOS notification banner with app icon, title, and body, suited to video overlays or product teasers.

nexu-io/open-design · 30 tokens

frame-macos-notification

A template for realistic macOS Big Sur-style notification banners, with an app icon, title, message, and optional action button.

nexu-io/html-anything · 31 tokens

figma-create-design-system-rules

Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…

warpdotdev/warp · 71 tokens

figma-generate-design

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the…

warpdotdev/warp · 160 tokens

figma-generate-library

Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. This skill teaches WHAT to build and in WHAT ORDER — it…

warpdotdev/warp · 95 tokens