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 quangpl/browser-extension-skills --skill extension-analyzegit clone --depth 1 https://github.com/quangpl/browser-extension-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/quangpl/browser-extension-skills/extension-analyze)<a href="https://agentmods.dev/skills/quangpl/browser-extension-skills/extension-analyze"><img src="https://agentmods.dev/badge/skills/quangpl/browser-extension-skills/extension-analyze/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/quangpl/browser-extension-skills/extension-analyze"><img src="https://agentmods.dev/badge/skills/quangpl/browser-extension-skills/extension-analyze.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 | $0.00039 | $0.01140 |
| Opus 5 | $0.00019 | $0.00570 |
| Sonnet 5 | $0.00008 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
extension-analyze 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extension Analyze (Security & Compliance Auditor)
Audit an existing Chrome extension. Do NOT just explain — execute the workflow.
Workflow (Execute This)
Step 1: Locate extension root and detect framework
Ask user for path if not provided. Detect framework:
ls wxt.config.ts plasmo.config.ts vite.config.ts manifest.json 2>/dev/null
- Plasmo: manifest auto-generated; check
package.jsonandplasmo.config.tsinstead - WXT: check
wxt.config.tsmanifest section - Vanilla/CRXJS: check
manifest.jsondirectly
Step 2: Scan manifest.json (or equivalent config)
# Check MV version, permissions, host_permissions, CSP, web_accessible_resources
cat <ext>/manifest.json | jq '{manifest_version, permissions, host_permissions, content_security_policy, web_accessible_resources}'
Step 3: Quick grep scans
# XSS vectors
grep -rn "innerHTML\|outerHTML\|document\.write\|insertAdjacentHTML" <ext>/src --include="*.ts" --include="*.js"
# Unsafe patterns
grep -rn "eval(\|new Function(\|setTimeout.*string\|setInterval.*string" <ext>/src
# Hardcoded secrets
grep -rn "api_key\|apiKey\|secret\|password\|token" <ext>/src --include="*.ts" --include="*.js" | grep -v "\.test\." | grep -v "node_modules"
# HTTP (non-HTTPS) calls
grep -rn "http://" <ext>/src --include="*.ts" --include="*.js"
# Message handler sender validation
grep -rn "onMessage\|addListener" <ext>/src | grep -v "node_modules"
# Remote code loading
grep -rn "importScripts\|fetch.*\.js\|eval\|chrome\.scripting\.executeScript" <ext>/src
Step 4: Check CSP configuration
- MV3 default CSP:
script-src 'self'; object-src 'self' - Flag any
unsafe-inline,unsafe-eval, orhttp:sources - Verify no remote script sources
Step 5: Dependency audit
cd <ext> && npm audit --json | jq '.vulnerabilities | to_entries[] | {pkg: .key, severity: .value.severity}'
Step 6: Generate report
Output findings grouped by severity. See Output Format below.
What ships with it
4 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.
- 11d ago First seen · 135 lines · 39 tokens per session scan A 2ffdb61fac3c
extension-analyze is a skill published in the GitHub repository quangpl/browser-extension-skills (49 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,140 once invoked, about $0.0002 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
chrome-extension
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is nextjs), NOT a desktop shell (that is…
browser-qa
Drive a real headless browser against a locally-served web UI and capture screenshot evidence, reporting step-level PASS/FAIL/BLOCKED with extracted DOM text and console errors. Use when a phase on the docker QA image must exercise a rendered UI and attach screenshots — it complements the text-evidence verify/qa-test…
demo
Record a short demo VIDEO of a PR or feature — drive the repo's web UI in a real headless browser, capture the session, and composite a titled, size-capped mp4 with ffmpeg. Use on the docker QA image when the deliverable is a playable demo clip (single walkthrough or before/after comparison), not a text/screenshot…
website-explorer
Discover website capabilities from user behaviors. Learn APIs and automate workflows.
codex-browser
Control Chrome via Codex Desktop's browser bridge. 52 MCP tools for tabs, navigation, DOM, input, CDP, network, file upload, dialog handling, and diagnostics.
browser-extension-patterns
Build browser extensions with Manifest V3 for Chrome, Firefox, and cross-browser compatibility. Covers content scripts, background workers, popup UI, storage APIs, and extension messaging. Triggers on browser extension development, Manifest V3, or Chrome extension requests.