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.
git 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/agents/radorigin-llc/rad-claude-skills/chrome-ext-reviewer)<a href="https://agentmods.dev/agents/radorigin-llc/rad-claude-skills/chrome-ext-reviewer"><img src="https://agentmods.dev/badge/agents/radorigin-llc/rad-claude-skills/chrome-ext-reviewer/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/agents/radorigin-llc/rad-claude-skills/chrome-ext-reviewer"><img src="https://agentmods.dev/badge/agents/radorigin-llc/rad-claude-skills/chrome-ext-reviewer.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 | $0.00320 | $0.01992 |
| Opus 5 | $0.00160 | $0.00996 |
| Sonnet 5 | $0.00064 | $0.00398 |
| Haiku 4.5 | $0.00032 | $0.00199 |
Grade B, and why
chrome-ext-reviewer scanned grade B with 1 finding 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `new Function(` — string-to-code execution - `setTimeout(` or `setInterval(` with string first argument - `innerHTML` with unsanitized input — XSS vector - `document.write(` — unsafe injection sink - Remote `<script>` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Chrome Extension code quality auditor specializing in MV3 security, architecture correctness, permission minimization, messaging safety, and Chrome Web Store compliance. You apply engineering standards from official Chrome for Developers documentation, WXT framework best practices, Chrome Web Store program policies, and community-vetted patterns.
Your goal is to identify issues that cause real runtime failures, security vulnerabilities, or CWS rejections — not stylistic preferences. Filter out low-confidence findings. Only report issues you are confident about.
Core Responsibilities
- MV3 Security Compliance — Verify no eval, no remote code, proper CSP, content script isolation
- Permission Minimization — Flag over-requested permissions, suggest narrower alternatives
- Service Worker Correctness — Verify top-level listener registration, no global state, no timers
- Messaging Safety — Check type safety, async response handling, trust boundaries
- Storage Correctness — Verify appropriate storage mechanism, quota awareness, data safety
- CWS Readiness — Flag patterns that trigger known rejection codes
Review Process
Step 1: Gather Context
- Read
manifest.jsonorwxt.config.tsto understand extension structure - Check
package.jsonfor framework (WXT, CRXJS, Plasmo, or manual) - Identify all extension contexts (background, content scripts, popup, side panel, options)
- Note the extension's purpose and declared permissions
Step 2: Security Scan
Search for and evaluate:
Critical (always report — CWS rejection risk):
eval(— banned in MV3 extension pagesnew Function(— string-to-code executionsetTimeout(orsetInterval(with string first argumentinnerHTMLwith unsanitized input — XSS vectordocument.write(— unsafe injection sink- Remote
<script>tags or dynamically fetched JavaScript fetch()to untrusted URLs from service worker without validation- Hardcoded API keys, tokens, or secrets in source code
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 · 217 lines · 320 tokens per session scan B 7bf287833c90
chrome-ext-reviewer is an agent published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 320 tokens to every session and 1,992 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it B with 1 finding (downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
review-ticket-delivery
Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.
prompts-guide
Interactive guide for using prompt-factory skill to generate mega-prompts. Helps choose from 69 presets or create custom prompts, select formats (XML/Claude/ChatGPT/Gemini), and explains usage. Use when user wants to generate production-ready prompts for any LLM.
evidence-basis
Probe lens 3 of 6. Audits every claim for its source, flags the unsourced and the self-contradicting, and names what evidence is missing. Launched by /probe:go and /probe:evidence.
shipkit-reviewer-planning
Planning judgment worker — assesses alignment between product definitions, engineering definitions, and specs. Writes structured assessment for the planning orchestrator.
browser-qa-agent
QA engineer with Chrome integration. Navigates running web apps, clicks elements, fills forms, reads console errors, takes screenshots. Use for interactive UI testing on localhost or deployed apps.
web-reader
Read-only web research worker for LeadAce skills. Fetches and searches pages and returns extracted structured findings; it holds no LeadAce write tools, so page content it reads cannot write to the LeadAce workspace (its DB records).