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 RadOrigin-LLC/RAD-Claude-Skills --skill chrome-ext-service-workergit clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/radorigin-llc/rad-claude-skills/chrome-ext-service-worker)<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/chrome-ext-service-worker"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/chrome-ext-service-worker/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/radorigin-llc/rad-claude-skills/chrome-ext-service-worker"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/chrome-ext-service-worker.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 | $0.00111 | $0.00932 |
| Opus 5 | $0.00056 | $0.00466 |
| Sonnet 5 | $0.00022 | $0.00186 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
chrome-ext-service-worker 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 11d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome Extension Service Workers
MV3 replaced persistent background pages with ephemeral, event-driven service workers. They wake to process events and terminate after ~30 seconds of inactivity. All in-memory state is lost on termination. Code must be structured around this fundamental constraint.
The Ephemeral Lifecycle
[Event occurs] → [Worker starts] → [Script executes top-to-bottom]
→ [Registered listeners fire] → [~30s idle] → [Worker terminates]
→ [All global variables lost]
Every handler must assume zero prior state. Rehydrate from storage at the start of every event.
Hard Rules
1. Register Listeners Synchronously at Top Level
The browser scans for listeners on the first turn of the event loop. Listeners inside promises, callbacks, setTimeout, or async functions will NOT be registered in time.
// CORRECT — synchronous, top-level
export default defineBackground(() => {
chrome.runtime.onMessage.addListener(handleMessage);
chrome.alarms.onAlarm.addListener(handleAlarm);
chrome.runtime.onInstalled.addListener(handleInstall);
});
// WRONG — async, buried inside callback
export default defineBackground(async () => {
await someSetup();
// TOO LATE — worker may have already handled the event
chrome.runtime.onMessage.addListener(handleMessage);
});
2. Never Use setTimeout/setInterval
Standard timers are canceled on termination. Replace with chrome.alarms:
// WRONG — unreliable
setTimeout(() => checkForUpdates(), 60000);
// CORRECT — survives worker restarts
chrome.alarms.create('check-updates', { periodInMinutes: 1 });
chrome.alarms.onAlarm.addListener((alarm) => {
if (alarm.name === 'check-updates') checkForUpdates();
});
3. Never Store State in Global Variables
// WRONG — lost on restart
let userPrefs = {};
// CORRECT — persist to storage
async function getPrefs() {
const { prefs } = await chrome.storage.local.get('prefs');
return prefs ?? DEFAULT_PREFS;
}
What ships with it
1 file 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.
- 11d ago First seen · 128 lines · 111 tokens per session scan A 7121df06316b
chrome-ext-service-worker is a skill published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 111 tokens to every session and 932 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
web-quality-audit
Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
ui-test
Runs UI tests described in plain English by driving real Chrome via the Claude-in-Chrome extension. Covers end-to-end flows (clicks, forms, assertions), visual checks (screenshot + optional baseline diff), accessibility (axe-core), performance (Web Vitals + light Lighthouse-style metrics), and an interactive --debug…
audit-ui-e2e
Runs a beginner-mind end-to-end UI audit of any running app — local dev server, staging, production, or a specific URL. Drives Chrome through every interactive element on the target surface, collects structured findings (severity, category, where, symptom, impact, repro, triage), and hands the result off to…
capture-screens
Automatically navigates a web app using Playwright MCP and captures context-aware named screenshots at each product feature state. Names each file semantically based on context (e.g., checkout-payment-form-filled.png). Outputs a manifest.json mapping filenames to descriptions and a summary report. Use when documenting…
bug-reporting
Load this skill whenever you are filing, reviewing, or generating accessibility bug reports — whether from automated tool output, manual testing, user reports, or testing with disabled people. The purpose of this skill is to make accessibility findings easier to report accurately, connect them to real people and…
audio-video
Load this skill whenever the project contains audio or video content, media players, podcasts, video embeds, or any / elements. Under no circumstances publish audio or video without captions, transcripts, and audio descriptions where required. Absolutely always apply WCAG 1.2 criteria for time-based media.