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 agentmods add agents/themattberman/google-ads-copilot/audit-landinggit clone --depth 1 https://github.com/TheMattBerman/google-ads-copilotWrote 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/themattberman/google-ads-copilot/audit-landing)<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>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 | $0.00024 | $0.00458 |
| Opus 5 | $0.00012 | $0.00229 |
| Sonnet 5 | $0.00005 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
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.
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:
- Read
google-ads/references/operator-thesis.md - Read
google-ads/references/tracking-playbook.md - Read
google-ads/references/landing-page-playbook.md - Read
workspace/ads/findings.mdfor 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:
- Tracking problem — fix tracking before anything else
- Path/UX problem — page fails the visitor
- Both — fix tracking first, then UX
- 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
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.
- 5d ago First seen · 49 lines · 24 tokens per session scan A bc3ca78caab6
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.