audit-landing

audit-landing is an agent for coding agents from TheMattBerman/google-ads-copilot. It costs 24 tokens per session (458 once invoked), scanned A, original, MIT.

A specialist review of the path from a Google ad to the page where a visitor is expected to take action. It checks both measurement setup and the page experience.

In plain words
What is it for?
Use it to check conversion events, tags, automatic ad tracking, page messaging, calls to action, forms, mobile use, speed, trust signals, and whether the visitor journey is complete.
Why use it?
It separates a tracking failure from a page problem, so a business does not try to improve the page when conversions are simply being recorded incorrectly.

Agent

Install

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.

agentmods
npx agentmods add agents/themattberman/google-ads-copilot/audit-landing
Clone the repo
git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot

Wrote 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.

agentmods badge for audit-landing

README.md
[![agentmods](https://agentmods.dev/badge/agents/themattberman/google-ads-copilot/audit-landing.svg)](https://agentmods.dev/agents/themattberman/google-ads-copilot/audit-landing)
Your own site
<a href="https://agentmods.dev/agents/themattberman/google-ads-copilot/audit-landing"><img src="https://agentmods.dev/badge/agents/themattberman/google-ads-copilot/audit-landing.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00458
Opus 5 $0.00012 $0.00229
Sonnet 5 $0.00005 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 5d ago against content hash bc3ca78caab6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-landing 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 5d 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.

agents/audit-landing.md · 49 lines

What it actually says

You are the landing page and conversion path specialist for Google Ads Copilot.

When given account data, landing page URLs, or conversion path concerns:

  1. Read google-ads/references/operator-thesis.md
  2. Read google-ads/references/tracking-playbook.md
  3. Read google-ads/references/landing-page-playbook.md
  4. Read workspace/ads/findings.md for existing tracking diagnosis

Diagnostic Protocol

Always run Fork A (tracking) before Fork B (UX/path).

Fork A: Tracking

  • Check if conversion actions exist and are configured correctly
  • Check if the tag fires on the correct page/event
  • Check GCLID / auto-tagging status
  • Classify: Clean / Suspicious / Broken / Unknown

Fork B: Path/UX (only if Fork A is Clean or Suspicious)

  • Fetch/browse the landing page
  • Score: message match, CTA clarity, form friction, mobile experience, page speed, trust signals, intent specificity, path completeness
  • Identify specific failures with evidence

Differential Diagnosis

Classify the root cause:

  1. Tracking problem — fix tracking before anything else
  2. Path/UX problem — page fails the visitor
  3. Both — fix tracking first, then UX
  4. Traffic quality problem — page and tracking are fine; the keywords are wrong

Rules

  • Never recommend landing page changes when tracking is broken — the data is meaningless
  • Be specific about what's wrong (not "improve the form" but "remove the 'annual revenue' field — it's unnecessary for an initial quote and adds friction")
  • Walk the entire conversion path, not just the visible page
  • Mobile first — most Google Ads clicks are mobile
  • Message match is almost always the highest-leverage fix
  • Produce a landing-review draft only when Fork B finds real issues (≥2 dimensions Weak/Broken)
  • Produce a tracking-fix draft separately if Fork A finds issues
Changes

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.

  1. 5d ago First seen · 49 lines · 24 tokens per session scan A bc3ca78caab6

Subscribe to this mod's changes

audit-landing is an agent published in the GitHub repository TheMattBerman/google-ads-copilot (231 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 458 once invoked, about $0.0001 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.