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 porcupine-md/jonggrang --skill validating-visual-designgit clone --depth 1 https://github.com/porcupine-md/jonggrangWrote 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/porcupine-md/jonggrang/validating-visual-design)<a href="https://agentmods.dev/skills/porcupine-md/jonggrang/validating-visual-design"><img src="https://agentmods.dev/badge/skills/porcupine-md/jonggrang/validating-visual-design/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/porcupine-md/jonggrang/validating-visual-design"><img src="https://agentmods.dev/badge/skills/porcupine-md/jonggrang/validating-visual-design.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 | $0.00032 | $0.01227 |
| Opus 5.5 | $0.00013 | $0.00491 |
| Sonnet 5.5 | $0.00006 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade C, and why
validating-visual-design scanned grade C 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/porcupine-md/anoa-browser/master/scripts/install-linux.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/porcupine-md/anoa-browser/master/scripts/install-linux.sh | bash How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validating Visual Design with anoa
Frontend code that typechecks and passes unit tests can still render broken.
This skill uses anoa — the browser CLI preinstalled in the Jonggrang sandbox
— to open the running app in a real headless browser and verify the design
actually works.
anoa is available to every agent backend (claude, opencode, codex, jonggrang).
Call it via Bash. In the sandbox it is already there — start with the session
step below.
On a bare host, install the binary once:
curl -fsSL https://raw.githubusercontent.com/porcupine-md/anoa-browser/master/scripts/install-linux.sh | bash
That is one binary carrying its own browser, so there is no second download
for a browser — but the binary itself does have to exist. If anoa is not on
PATH, install it rather than reaching for another tool.
The browser is a session
This is the one thing to get right. Start the browser once; every command after that attaches to the running browser and leaves it running, so the page, cookies and scroll position survive between commands.
anoa --headless --port 9222 & # start once, in the background
anoa status # exit code 3 = nothing listening
A command that seems to do nothing almost always means no browser is running —
check anoa status before assuming the command is wrong.
When to use
- After implementing or changing any UI (component, page, layout, styling).
- Before signalling completion on a task that touches the frontend.
- During Phase 10 design verification / interface-quality audits.
Core commands
anoa open http://localhost:3000 # go to a url (scheme optional)
anoa wait --load # or --text/--url/<css>: name what you expect
anoa screenshot design.png # PNG of the viewport
anoa snapshot -i # interactive elements, each with an @ref
anoa get text # all visible text (cheaper than get html)
anoa click @e2 # act by ref — or by any CSS selector
anoa fill @e3 "value" # fires input/change, so React sees it
anoa set viewport 375 812 # resize the page
anoa set media dark # emulate prefers-color-scheme
anoa console # what the page logged
anoa errors # uncaught exceptions
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 · 120 lines · 32 tokens per session scan C d2f78f62aee1
validating-visual-design is a skill published in the GitHub repository porcupine-md/jonggrang (16 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,227 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
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 $ultragoal 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.
open-design-setup
Prepare or repair a project's prototyping environment so open-design can build prototypes with the project's own component library and render them through the project's toolchain. Use when the library target is needed and docs/design/prototyping.md is missing, stale, or failing; excludes HTML-only design work and…
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…