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 Topman-14/mobius-mcp --skill mobius-page-auditgit clone --depth 1 https://github.com/Topman-14/mobius-mcpWrote 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/topman-14/mobius-mcp/mobius-page-audit)<a href="https://agentmods.dev/skills/topman-14/mobius-mcp/mobius-page-audit"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-page-audit/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/topman-14/mobius-mcp/mobius-page-audit"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-page-audit.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 | $0.00082 | $0.00923 |
| Opus 5 | $0.00041 | $0.00462 |
| Sonnet 5 | $0.00016 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
mobius-page-audit 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mobius-page-audit
A page's source tells you what it was written to do. This tells you what it does — including the requests fired by analytics tags, embedded widgets and third-party scripts that no one on the team wrote, and the controls that look fine but can't actually be operated.
When to use this
- Reviewing a page before it ships.
- "What is this page sending to third parties?" — analytics, pixels, session recorders, chat widgets.
- Checking whether anything sensitive is leaving in a request body.
- Verifying that a page's interactive elements are actually reachable.
Workflow
mobius_diagnose. If it isn'tready, relay the remediation and stop.clear_logs, then load the page fresh —navigate_tofollowed bywait_for_navigation, so you capture the full load, not the tail of it.get_capture_settingsbefore drawing any conclusion from a quiet result. An empty network list because the category is off is not a clean page.
Third-party traffic
get_network_requestsand group by origin. Anything not on the app's own domain is third-party — analytics, tag managers, ad/marketing pixels, session recorders, embedded chat, font and CDN hosts.- For each third-party destination, read the actual
requestBodyrather than assuming what a vendor collects. Look specifically for: full page URLs including query strings, referrer chains, user or account identifiers, email addresses, form field values, and anything that looks like a session token. - Note the ones that fire before any consent interaction — a tag that loads before the banner is answered is usually a compliance problem, not a preference.
export_harif the finding needs to be shared or attached.
What the page reports about itself
get_recent_errorsfor uncaught errors and unhandled rejections during load, andget_recent_logsfor warnings worth surfacing — deprecations, CSP violations, failed resource loads, noisy debug output that shipped by accident.- Distinguish errors thrown by the app from errors thrown inside a third-party script. The second kind is still your problem if it breaks the page, but the fix is different.
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 · 48 lines · 82 tokens per session scan A 638b76b94be6
mobius-page-audit is a skill published in the GitHub repository Topman-14/mobius-mcp (18 stars, last pushed 22d ago), licensed MIT. It adds 82 tokens to every session and 923 once invoked, about $0.0004 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
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
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
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.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…