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 Lab2A/metalworks --skill design-reviewgit clone --depth 1 https://github.com/Lab2A/metalworksWrote 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/lab2a/metalworks/design-review)<a href="https://agentmods.dev/skills/lab2a/metalworks/design-review"><img src="https://agentmods.dev/badge/skills/lab2a/metalworks/design-review/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/lab2a/metalworks/design-review"><img src="https://agentmods.dev/badge/skills/lab2a/metalworks/design-review.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 | $0.00109 | $0.00817 |
| Opus 5 | $0.00055 | $0.00409 |
| Sonnet 5 | $0.00022 | $0.00163 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
design-review 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
Before any other tool, run the preflight MCP tool (or metalworks preflight on
the CLI). If it reports setup issues or that an update is available, surface that
to the user in one line and help them resolve it (install the missing extra/key,
or pip install -U metalworks) before continuing. Skip only if the user has
already passed preflight this session.
Read the reference; never reverse-engineer the source. The moment you need to know how
metalworks behaves — provider/model resolution, which source/reader runs, config precedence,
an error you hit, or the async run loop — STOP and read docs/operating-metalworks.md
(bundled with this plugin) before opening any file under src/. It is the source of truth;
do not derive behavior from source. (Full docs: https://metalworks.lab2a.ai/docs.) For a
long-running run, poll status with the Monitor tool or a bounded loop — never a blind sleep.
You are auditing a rendered page's design — what's actually on screen, not
what a DESIGN.md says it should be. The review is deterministic: every
finding is a pure function of the page's computed styles plus, when supplied, the
brand's design system. The model writes nothing here; don't invent findings.
Steps
-
Get the page URL (a live site, a preview, or a
file://path). The page must be reachable by the browser. Optionally get areport_idto grade against that report's design system, not just the generic hard-rules. -
Call the
design_reviewMCP tool with theurl(andreport_idto grade against a system). On the CLI:metalworks research design-review <url>(--report <id>to grade against a system). It reads the page's actual fonts, heading scale, and colors and returns aDesignReviewwith ascore, apassedflag, and per-categoryfindings. -
If it errors that no browser / a screenshot-only renderer is available, relay the fix: design review needs the browser —
metalworks browser install. It cannot run on Firecrawl (which can't read computed styles).
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.
- 9d ago First seen · 56 lines · 109 tokens per session scan A 8e2d0ae79e8a
design-review is a skill published in the GitHub repository Lab2A/metalworks (6 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 817 once invoked, about $0.0005 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.