Borrowing it
Nothing to install: this file belongs to layoutit/polycss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/layoutit/polycss/main/.agents/skills/chrome-trace/SKILL.mdgit clone --depth 1 https://github.com/layoutit/polycssWrote 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/layoutit/polycss/chrome-trace)<a href="https://agentmods.dev/skills/layoutit/polycss/chrome-trace"><img src="https://agentmods.dev/badge/skills/layoutit/polycss/chrome-trace/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/layoutit/polycss/chrome-trace"><img src="https://agentmods.dev/badge/skills/layoutit/polycss/chrome-trace.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 | $0.00082 | $0.01921 |
| Opus 5.5 | $0.00033 | $0.00768 |
| Sonnet 5.5 | $0.00016 | $0.00384 |
| Haiku 4.5 | $0.00008 | $0.00192 |
Grade A, and why
chrome-trace 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 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.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome Trace
Core Workflow
Use Playwright with Chromium and the Chrome DevTools Protocol Tracing domain to capture the exact interaction under investigation.
- Start from a reproducible page and action.
- Warm up the page until app-specific readiness is true.
- Start Chrome tracing and a
requestAnimationFramesampler immediately before the action. - Mark the action window with
performance.mark()andconsole.timeStamp(). - Perform the action with real Playwright input when the user is asking about input-driven behavior.
- Stop tracing after a short settle window.
- Align trace event timestamps to
performance.now()using the start/end marks. - Report where time went:
Scripting,Style,Layout,PrePaint,Paint, compositor main-thread work, compositor impl-thread work, raster, GPU/viz events, and the slowest frame windows.
Do not draw conclusions from FPS alone. Use FPS/frame-time summaries only as the symptom; use trace groups and top events as the explanation.
PolyCSS Trace Runners
Use scripts/trace.mjs as the front door:
pnpm bench:build
node .agents/skills/chrome-trace/scripts/trace.mjs motion --page nonvoxel --mesh glb:Elephant.glb --variant baseline --dom-samples --label elephant-baseline
node .agents/skills/chrome-trace/scripts/trace.mjs motion --page nonvoxel --mesh teapot --variant baseline --dom-samples --frame-details --layer-details --gpu-details --trace-out bench/results/teapot.trace.json --label teapot-enriched --report
node .agents/skills/chrome-trace/scripts/trace.mjs motion --page nonvoxel --mesh teapot --variant baseline --gpu-details full --trace-out bench/results/teapot-full-gpu.trace.json --label teapot-full-gpu
node .agents/skills/chrome-trace/scripts/trace.mjs drag --mesh teapot --mode baked --frame-details --label teapot-drag
node .agents/skills/chrome-trace/scripts/trace.mjs motion --mesh garden --report --markdown-out bench/results/garden-trace.md
node .agents/skills/chrome-trace/scripts/trace.mjs compare bench/results/before.json bench/results/after.json --markdown-out bench/results/trace-compare.md
What ships with it
5 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.
- 1mo ago First seen · 117 lines · 82 tokens per session scan A 511dcc78c1b0
chrome-trace is a skill published in the GitHub repository layoutit/polycss (771 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,921 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…