Chromium is an open-source web browser project and the official GitHub mirror of its source code. It is used to build and maintain software for browsing the web, with documentation and code for products such as Chrome and Android WebView.
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 chromium/chromium --skill figma-design-reviewgit clone --depth 1 https://github.com/chromium/chromiumWrote 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/chromium/chromium/figma-design-review)<a href="https://agentmods.dev/skills/chromium/chromium/figma-design-review"><img src="https://agentmods.dev/badge/skills/chromium/chromium/figma-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/chromium/chromium/figma-design-review"><img src="https://agentmods.dev/badge/skills/chromium/chromium/figma-design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.01305 |
| Opus 5 | $0.00030 | $0.00652 |
| Sonnet 5 | $0.00012 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
figma-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 today.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Design Review
This skill provides a structured workflow for reviewing a Figma design (node or page) and critiquing its alignment with the existing codebase component specifications. It helps bridge the gap between design and implementation by identifying hardcoded values, raw icon usages instead of proper components, and structural mismatches.
Prerequisites
- Figma MCP Server: Must be active and configured in the workspace context to fetch designs and metadata.
- Chromium Repository: This skill should be executed from inside the root
directory of the Chromium repository source code (
//src/).
Review Workflow
When asked to review a Figma design for code alignment, follow these steps sequentially:
1. Fetch the Design Context
Use the get_design_context tool on the provided Figma URL or node ID.
- Pay close attention to the generated React/Tailwind code output as it represents the node's structure.
- Look for generic
<div>wrappers versus named components. - Check for hardcoded
classNamevalues versus design tokens (e.g.,var(--desktop/sys/surface)). - Note any raw image/mask constructions.
2. Identify and Read Component Specifications
Identify the main UI components used in the design (e.g., Buttons, Dialogs, Radio Buttons, Text Fields).
- Look up Chorme Design System component specs using the
chrome-componentsskill. - Read the identified
_Spec.mdfiles usingread_fileto understand how the components are implemented in the target codebase (WebUI and C++ Views). - Crucial Component Mapping Rule:
- The design context from Figma may output complex nested
divs, SVGs, or image masks (imgMask,imgIcon) instead of clean component tags. This happens when Figma Code Connect is missing, causing the API to decompile the visual layers of a component. - Do not assume these are "raw custom-drawn shapes" if the component
instance name, data name, or ID in the design context (e.g.
data-name="RadioButtons",data-name=".base.Buttons") matches an official component defined in the spec files. - Cross-reference the Figma component name/ID with Section 1 of the
component's
_Spec.mdfile to identify the true target components (e.g.,<cr-radio-button>for WebUI,views::RadioButtonfor C++). - Don't report this in the feedback, and don't advise on the use of Figma Code Connect.
- The design context from Figma may output complex nested
- Crucial Information to Extract from Specs:
- Standard tokens used for colors, spacing, outlines, and fonts.
- Handling of interactive states (hover, focus, disabled).
- Use of specific variant classes (e.g.,
.action-button,.tonal-button). - Architectural constraints (e.g., C++ handles shadows natively).
What ships with it
2 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.
- today Changed · +49 lines deefd27999c6
- 12d ago First seen · 74 lines · 59 tokens per session scan A f1da15fb05e6
figma-design-review is a skill published in the GitHub repository chromium/chromium (24,756 stars, last pushed today), licensed BSD-3-Clause. It adds 59 tokens to every session and 1,305 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pagouse
Observe and (with a grant) drive Chromium tabs via the pagouse CLI: snapshot the accessibility tree, click/fill by ref, navigate. Not a seat adapter. Trigger keywords: pagouse, browser tab, fill form, click the button on the page, snapshot page, AX tree.
analyzing-browser-forensics-with-hindsight
Parse Chromium-based browser databases with Hindsight to extract and correlate browsing history, downloads, cookies, cached content, autofill data, saved passwords, and extensions from Chrome, Edge, Brave, Opera, and Vivaldi into a unified timeline (XLSX, JSON, or SQLite output). Use during incident response…
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
stealth-browser-launch
Launch stealth Chromium with C++ fingerprint patches for anti-bot bypass.
separateweb-capture
Capture a URL into a full-page screenshot, cropped UI item PNGs, and a JSON manifest. Use when the user says separateweb capture , asks to capture a website, or wants UI extraction assets without running the SeparateWeb web app.