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 damianvtran/local-operator --skill design-qagit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/design-qa)<a href="https://agentmods.dev/skills/damianvtran/local-operator/design-qa"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/design-qa/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/damianvtran/local-operator/design-qa"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/design-qa.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.00663 |
| Opus 5.5 | $0.00020 | $0.00265 |
| Sonnet 5.5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design QA
A quality gate for user-visible interfaces, web or terminal. Two lanes, in order: measure, then judge. Every claim carries evidence.
Lane 1: measure
Run the deterministic checks for the surface before forming any opinion, and cite each number's actual source (computed style, bounding box, log line). Never report an unmeasured number; if you cannot measure it, say so.
- Web:
references/checks-web.md - Terminal:
references/checks-tui.md - Copy:
references/checks-copy.md
Lane 2: judge
Judge only what measurement cannot decide: hierarchy (does the eye land in the right place), flow (is the next step obvious), does the screen answer its own question, do the states tell the truth. Judgement stands on the lane 1 numbers. Where you must eyeball, say that you did.
Matrix: states x viewports
Cover every state the surface has, at narrow, standard, and wide. Themes and personalization axes the product supports (dark mode, display sizes) are extra columns.
| narrow | standard | wide | |
|---|---|---|---|
| loading | |||
| empty | |||
| error | |||
| populated |
For terminal UIs, "viewports" are terminal sizes; include the smallest width the product promises. A single happy-path screenshot is not coverage.
Procedure
- Get rendered frames, never source alone. Web: drive the harness
browsertool (background tab, logins intact; never install or script a browser engine). Terminal: drive the real app that loads the shipped styles, not a bare test host, and export with the app's own capture facility. - Run the deterministic checks for the surface; keep each check's real output.
- Capture a frame per matrix cell. Where anything animates, compare consecutive frames: a first frame that differs from the settled frame is motion the user sees.
- Form judgements against the brief and the states, not against taste.
- Report findings with severity and evidence. Where the round format uses D-prefixed ids (D1, D2, ...), keep them stable across rounds and verify fixes only on changed surfaces.
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.
- 5d ago First seen · 54 lines · 50 tokens per session scan A ee2cd3df797f
design-qa is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 663 once invoked, about $0.0002 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 2026-10-11.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
excalidraw
Create hand-drawn style diagrams using Excalidraw JSON format. Generate .excalidraw files for architecture diagrams, flowcharts, sequence diagrams, concept maps, and more. Files can be opened at excalidraw.com or uploaded for shareable links.
better-ui
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, choosing or reviewing icons, or any visual detail work. Triggers on UI polish, design details…
theme-pack-authoring
Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.
a2ui
Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a callout, a Mermaid diagram, a weather card, a live clock or countdown, and a dashboard of gauges for a system snapshot, a…