Modern Web Guidance hands-on: Chrome's front-end skill gets small models to use native dialog and popover

Published on November 21, 2026 by Remy

Short answer: If a coding agent writes front-end code for you, and especially if it runs on a cheap or free model, install GoogleChrome’s modern-web-guidance. It does not make the agent smarter. Before the agent writes a dialog, a menu, or a form, the skill makes it look up a guide that the Chrome, Edge, Firefox, and MDN teams maintain. The agent then uses native <dialog>, popover, and CSS anchor positioning instead of hand-rolled divs and key listeners. On one small task, three free models passed all 16 browser checks with the skill. Without it, mimo-v2.6-flash dropped 2 checks and hy4-flash dropped 3. deepseek-v4.1-flash passed everything without the skill, so for that model the skill only changed the implementation. The costs are clear too: each run reads tens of KB of guide text, wall time goes up several times, and search queries go to Google unless you opt out.

Install it in the project root, and turn telemetry off first. Claude Code, Codex, Copilot CLI, and others can also use their own plugin marketplaces. The README lists the commands.[1]

export DISABLE_TELEMETRY=1
npx -y modern-web-guidance@latest install          # interactive: pick the agent and scope
npx -y [email protected] install -a opencode -y   # the non-interactive form used here
Your situationRecommendation
Lots of front-end work on small or free modelsInstall it. These models gained the most in this test
Strong models, mostly back-end or scriptsYou can skip it. The description says it does not trigger for back-end, CI, or scripts
You have your own component library and design rulesPrefer your library. The guides give generic patterns and don’t know your conventions
Your network blocks npm, or you can’t send queries outEvaluate first. Every lookup runs npx online, and telemetry is on until you turn it off
You must support older browsers or specific Firefox versionsTest the fallback paths yourself. This report only verified Chrome 156

This is the first issue of the Hot Skill Hands-on series. For what Agent Skills are and how to install them, see the Agent Skills starter guide. For where a skill like this fits in the whole lifecycle, see the Agent Skills 2026 survey.

Why this skill, this week

Modern Web Guidance is a set of Agent Skills led by the Chrome team and maintained with Edge, Firefox, and MDN. It holds more than 200 front-end implementation guides plus Baseline browser-compatibility data.[1] Version 1.0 shipped on November 10, and the author’s Show HN post reached 449 points and 146 comments.[2] Version 1.0.1 followed on November 16, and that is the version tested here.[3] This week the source repository, GoogleChrome/modern-web-guidance-src, gained 5,224 stars on the GitHub TypeScript weekly chart. That is in the same range as mattpocock/skills (5,337) and anthropics/skills (4,086).[4]

The official numbers are large. In the HN post, the author says Codex, Claude Code, and Antigravity ran 200 tasks with about 1,700 Playwright and AST assertions, and the average pass rate went from 55% without the skill to 92% with it.[2] The November 8 row in the README has Claude Code at 57% to 88% and Codex at 54% to 82%.[1] Those are the project’s own tasks and graders. This report uses a small task the project has not seen, and three free models it did not evaluate, to see how much of the gain remains.

Install: 2.5 MB copied, only SKILL.md used

install -a opencode -y clones the repository and installs only the modern-web-guidance skill. The other skill in the repository, chrome-extensions, is not installed by default. The installer copies the skill to ./.agents/skills/modern-web-guidance and writes a skills-lock.json with the commit.

modern-web-guidance 1.0.1 install output: clones the repository, finds 2 skills, selects modern-web-guidance, copies it to ./.agents/skills/modern-web-guidance. The directory holds SKILL.md and guides, 210 guide files, 2.5M in total. skills-lock.json records commit 64a6d708

The directory has 210 guides, but none of the three runs with the skill read the local guides directory. SKILL.md tells the agent to call npx -y modern-web-guidance@latest search and retrieve every time, and the latest CLI on npm returns the guide text. The local dialog.md matched the CLI output exactly, so nothing went wrong here. Two things still matter:

  • skills-lock.json pins SKILL.md, not the guides. When @latest on npm changes, the guide text the agent reads changes with it.
  • Every lookup needs the network. By default the CLI collects install counts, the calling agent’s name, retrieved guide ids, and the search queries the agent writes. Set DISABLE_TELEMETRY=1 to turn this off.[1]

Five extra steps in the agent’s workflow

The SKILL.md description is forceful. It says HTML, CSS, and client-side JS tasks are “MANDATORY: Execute FIRST”, and it lists a long set of triggers from modals and popovers to passkeys and WebAssembly. The README puts the description at about 205 tokens.[1] The body defines four steps: search with 2 to 5 English words, retrieve guides by id, check the code against the guide, and end the answer with a ### Modern Web Guidance section that names the guides used.

Five extra steps the agent takes once the skill is installedThe SKILL.md description sits in contextAbout 205 tokens. It says MANDATORY: Execute FIRST for front-end work210 guides are copied locallyNo run read themThe model matches it and loads SKILL.mdAll three models called Skill right after TASK.mdTriggered 3 of 3npx modern-web-guidance@latest searchA 2 to 5 word query returns guide idsFetches @latest every timeQueries go to Google by defaultnpx modern-web-guidance@latest retrieveWrites guides such as dialog and menu to /tmp28 to 53 KB per callThe agent reads it allWrites code from the guide, then checks itshowModal(), popover, position-area, with fallbacks16 of 16 checks, 3 of 3 runsEnds with ### Modern Web GuidanceOne bullet per guide used, with a quoteTwo runs never got hereThey hung in self-testsOpenCode 2.3.1 with modern-web-guidance 1.0.1. Models: deepseek-v4.1-flash, mimo-v2.6-flash, and hy4-flash (free tier).

All three models called the Skill tool before they wrote any code, and their queries were nearly identical. Here is part of the hy4-flash run. Two search calls cover the dialog and the menu, and each returns 10 candidates. One retrieve fetches menu,viewport-aware-dropdowns, and another fetches four dialog guides.

hy4-flash-free terminal: loads the modern-web-guidance skill. search "confirmation modal dialog" and "popover menu dropdown" each return guide ids and descriptions. retrieve outputs 41.1 KB and 28.1 KB, saved to /tmp/mwg-guide-*.md. The agent reads both files and then writes index.html, styles.css, and app.js

When a guide is larger than 9.5 KB, the CLI does not print it. It writes the text to /tmp/mwg-guide-*.md and tells the agent to read the whole file with its file tool. The deepseek run fetched dialog,menu,viewport-aware-dropdowns at once, and that one file was 53.2 KB and 819 lines. This is the main cost of the skill, covered below.

After the code, deepseek ended its answer as step four asks, and each bullet quotes the guide. For example, it did not put role="menu" on the menu, because the guide says not to declare that role without the full arrow-key behavior.

deepseek-v4.1-flash-free final answer: a What changed section lists the delete confirmation and More menu changes. The Modern Web Guidance section has three bullets, dialog, menu, and viewport-aware-dropdowns, each with a quote from the guide

The test: a delete confirmation and a dropdown menu

The task is a static page with a three-row member list and no build step. TASK.md describes behavior only and names no APIs:

  1. Clicking Delete first asks “Remove name from the team?” with Cancel and Remove. While the popup is open, the page behind can’t be clicked. Esc or Cancel closes it without deleting.
  2. Clicking More opens a small menu right under the button with Copy email and Make admin, which can just console.log for now. Clicking anywhere else or pressing Esc closes it.

Each model ran twice: once in a directory with the skill and once without, with everything else identical. Both runs used opencode run --auto with a 15-minute timeout. Afterward, Playwright drove Chrome 156 through 16 checks. Eleven map to the TASK.md requirements. Five cover things the task did not state but users hit: whether focus enters the popup, whether Tab reaches the page behind, whether focus returns to the trigger on close, and whether the menu is cut off at the bottom of the viewport. One check, “the delete confirmation is a <dialog>”, tests the implementation, not visible behavior.

Same task with and without the skill (16 browser checks)With skillchecks passedWithoutchecks passedWith skillwall timeWithoutwall timedeepseek-v4.1-flash16/1616/167 min 07 s1 min 25 smimo-v2.6-flash16/1614/1615 min timeout*8 min 38 shy4-flash16/1613/1615 min timeout*38 s*** The code was done. The run hung in self-tests until timeout 900. ** Hit the free-tier limit after writing the code.Failures without the skill: no <dialog>, Tab reaches the page behind, the bottom menu leaves the viewport.

The same model, hy4-flash-free, both outputs, same checks: with the skill all 16 PASS. Without it, Delete opens a modal dialog, Tab never reaches the page behind, and Menu stays inside a short viewport FAIL

Which platform features each output used:

Delete confirmationMore menuMenu positionPage behind
deepseek with<dialog> + showModal() + form method="dialog"popover + popovertargetposition-area + position-try-fallbacks, JS fallbackMade inert by the browser
deepseek without<dialog> + showModal()div toggled by JSJS coordinates, flipsMade inert by the browser
mimo with<dialog> + form method="dialog"popover + commandfor, plus the experimental focusgroupposition-area, JS fallbackMade inert by the browser
mimo withoutdiv overlay + aria-modaldiv created at runtimeJS coordinates, no flipManual main.inert = true
hy4 with<dialog> + form method="dialog"popover + popovertargetposition-area, JS fallback that flipsMade inert by the browser
hy4 withoutdiv overlay + role="alertdialog"<ul> created at runtimeJS coordinates, no flipNothing. The overlay only blocks the mouse

One result needs its own note. Without the skill, deepseek-v4.1-flash still chose <dialog>, passed all 16 checks, and took 1 minute 25 seconds. For a capable model, the skill changes how the code is written, with popover and anchor positioning for the menu, but not whether it is correct. On HN, one commenter said legacy-scan found only two issues in their code and that the skill seems more useful “with weaker models”.[2]

The differences show up with the keyboard and at the edges

The two dialog screenshots look almost the same. Both have a gray backdrop, a centered card, and two buttons, and in both the page behind can’t be clicked.

Delete confirmation from both hy4-flash-free outputs: left uses dialog with showModal, right uses a div overlay. They look nearly identical

Press Tab a few times and they differ. When showModal() opens a <dialog>, the browser makes the rest of the page inert. Tab moves between the dialog’s buttons and the browser UI and never lands on a button behind it. The div overlay that hy4 wrote without the skill blocks only the mouse. After two presses of Tab, focus is on More and then Delete in the first row behind the overlay. A keyboard or screen-reader user who presses Enter at that point activates a button on the page behind.

After pressing Tab four times: on the left, with the skill, focus is still on the dialog's Remove button. On the right, without the skill, the focus ring is on the first row's Delete button behind the overlay

The menu differs at the bottom of the viewport. With the window at 250 pixels tall, scrolled to the end, click More on the last row. All three outputs with the skill use position-try-fallbacks: flip-block, so the menu flips above the button when there is no room below. Without the skill, mimo and hy4 compute coordinates in JS and always place the menu below, so half of it is cut off and you must scroll to see the second item. deepseek wrote its own flip logic without the skill and passed this check.

With a 250-pixel-tall window, clicking More on the last row: on the left, with the skill, the menu flips above the button and shows in full. On the right, without the skill, the menu runs past the bottom of the viewport and only Copy email shows

Code size is similar. The hy4 output with the skill has 52 non-empty lines of JS and the one without has 71, because focus, Esc, and outside clicks are left to the browser. The deepseek output with the skill has 109 lines. The extra lines are fallback branches for browsers without the Popover API or anchor positioning. The guides require a fallback for any feature that is not Baseline Widely available, and the model followed that rule.

The cost: time, context, and network

Runs with the skill were much slower. deepseek went from 1 minute 25 seconds to 7 minutes 7 seconds. Neither mimo nor hy4 finished normally with the skill. hy4 had the code written 1 minute 12 seconds after start, and mimo after about 8 and a half minutes, and that code passed every check. Then both wrote their own Chrome DevTools Protocol scripts to self-test, hung, and ran into the 15-minute timeout. mimo’s first attempt stopped while it was still reading a guide file, and only the second attempt wrote code. mimo also self-tested without the skill and finished normally in 8 minutes 38 seconds. So the timeouts are not all the skill’s fault. Still, step three of SKILL.md asks the agent to check its code against the guide, and that seems to push these two models to verify every behavior from the guide in a browser.

Token use went up as well. In the deepseek pair, the run with the skill had 58,574 input tokens, 10,892 output tokens, and 1.27 million cache-read tokens. Without the skill the numbers were 15,218, 4,144, and 112,000. Once a 53 KB guide file is in the context, every later turn carries it.

There were two side effects:

  • The hy4 run with the skill left a __test.html file in the project root for its self-test and did not delete it.
  • Each search and retrieve is an npx call. hy4 added NPM_CONFIG_CACHE=/tmp/npm-cache by itself, as SKILL.md suggests for sandboxes. In a harness that approves commands one by one, SKILL.md says to allowlist only npx -y modern-web-guidance@latest *, never all of npx *.

Pitfalls and limits

A guide is not guaranteed to be used. In May, accessibility specialist Adrian Roselli tested an early version. Antigravity with Modern Web Guidance built an accordion whose animation did not work in Firefox and that had several WCAG errors, even though the guides already had the relevant rules. A domain expert who consults for Google replied that models are non-deterministic and that a retrieved guide may not be read in full.[5] In this test all three runs read the guides in full, but the sample is one task.

Only Chrome was tested. All three outputs with the skill include a JS fallback for anchor positioning, but the checks ran only in Chrome 156, so the fallback branches never ran. If you support older Safari or Firefox versions, test the fallback paths yourself.

The MANDATORY description competes with other skills. It tells the agent to run first on every front-end task. If you also install your team’s front-end rules or a design-system skill, both will claim to go first. For how skills with overlapping jobs displace each other, see co-installed Agent Skills conflicts.

The local guides are unused. The 2.5 MB guides directory is not part of the default workflow. When the network is down, SKILL.md only suggests retrying with npx --offline from the cache. It does not fall back to the local files. For the trade-offs of reading only from the skill directory and expanding on demand, see Progressive Disclosure.

What was tested and what was not

Tested (OpenCode 2.3.1, Linux x64, OpenCode Zen free models, DISABLE_TELEMETRY=1 on every run):

  • Two installs with npx -y [email protected] install -a opencode -y. Both were commit 64a6d708, and the two directories were identical.
  • Three models, deepseek-v4.1-flash, mimo-v2.6-flash, and hy4-flash, each with and without the skill on the same task. That gives six outputs, and each went through the same 16 Playwright checks.
  • All three runs with the skill triggered it, called search and retrieve, and did not read the local guides directory.
  • The local guide files matched the CLI output, apart from one title line that the CLI adds.

Not tested:

  • big-pickle finished only the run without the skill (14 of 16, again no <dialog> and the bottom menu left the viewport). Its run with the skill hit the free-tier limit, so there is no pair. The hy4 run without the skill also hit the limit after it wrote the code, before it could self-test.
  • Strong models (the flagship Claude, GPT, and Gemini models) with and without the skill. Those are the models the official evals use.[1]
  • The legacy-scan mode, which scans old code and modernizes it.
  • Firefox, Safari, and the JS fallback branches in the outputs with the skill.
  • Repeated runs. Each model ran once.

References

  1. GoogleChrome/modern-web-guidance README (installation, Telemetry & Privacy, Recent eval results): https://github.com/GoogleChrome/modern-web-guidance ↩
  2. Show HN: Get your coding agent off ~2019 JavaScript, onto modern web primitives (2026-11-10): https://news.ycombinator.com/item?id=50443812 ↩
  3. npm package modern-web-guidance 1.0.1 and GitHub release v1.0.1: https://www.npmjs.com/package/modern-web-guidance, https://github.com/GoogleChrome/modern-web-guidance/releases/tag/v1.0.1 ↩
  4. GitHub Trending, TypeScript, Shell, and Python weekly charts (2026-11-21, UTC+8): https://github.com/trending/typescript?since=weekly ↩
  5. Adrian Roselli, Maybe Don’t Rely on Google’s “Modern Web Guidance” (2026-05-25, updated June 24): https://adrianroselli.com/2026/05/maybe-dont-rely-on-googles-modern-web-guidance.html ↩
  6. Modern Web Guidance docs and guide browser: https://developer.chrome.com/docs/modern-web-guidance. Eval dashboard: https://googlechrome.github.io/modern-web-guidance-src/