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 joao-aires/agent-skills-public --skill browser-extension-uigit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/browser-extension-ui)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/browser-extension-ui"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-ui/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/joao-aires/agent-skills-public/browser-extension-ui"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-ui.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 | $0.00048 | $0.02205 |
| Opus 5.5 | $0.00019 | $0.00882 |
| Sonnet 5.5 | $0.00010 | $0.00441 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
browser-extension-ui 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 7d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fit the experience to the browser surface
Read the accepted task, visual direction and interaction behavior before selecting layouts or components. Inspect existing tokens, typography, primitives and framework versions. Chrome's surface constraints affect implementation; they do not require a Google-like palette, a new font system or a component-library migration. Use general interface design expertise for shared hierarchy, flow and visual consistency when relevant; contribute browser-surface lifecycle, entry/exit and permission constraints before a layout is settled. A popup's dismissal contract or a host site's focus ownership may require different interaction structures than a full-tab application. This specialist can still design a complete extension experience when no generic interface skill is installed; it must not require another plugin or impose its own visual identity.
Derive the experience from the kind of work
Start with what someone is trying to accomplish, not with a popup template. A bookmark clipper, a searchable vault and a page assistant may all have a toolbar icon while needing different primary experiences. Conversely, a collection browser can work in a popup, a side panel or a full tab. Product type describes the work; surface describes where it happens.
For a new experience or substantial revision:
- Identify the main loop. What brings someone in, what object do they recognize or change, and what tells them they are done? Establish whether the task concerns a page/selection, a site, a collection or a browser session. Include how often people repeat it and how long unfinished work may last.
- Match a reference structure. Read the selector in extension types and UI structures, then the relevant patterns. Combine patterns when the accepted product genuinely contains several loops. A shared header or settings page does not make two extensions the same type.
- Allocate work to surfaces. Use the platform table below to decide which parts need proximity to a page, persistence, comparison space or direct browser entry. Make each additional surface earn its place; a command-only utility may not need a popup at all.
- Adapt the structure. Map the actual product objects, actions, roles and states into the selected arrangement. Account for the accepted component system, appearance policy and accessibility requirements. Resolve mismatches rather than adding features merely because a reference product has them.
- Trace the transitions. Establish entry, location, affected scope, unfinished work, result freshness and return behavior. Read experience patterns for cross-surface contracts and configuration as one of those transitions.
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.
- 7d ago Changed bf909fd55cf9
- 8d ago Changed · +21 lines c34c806266ee
- 9d ago Changed · +20 lines 638d211a5808
- 11d ago First seen · 59 lines · 48 tokens per session scan A d8a1901392d5
browser-extension-ui is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 2,205 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 2026-10-24.
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…