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 coupler-io/skills --skill ai-traffic-vs-organic-search-reportgit clone --depth 1 https://github.com/coupler-io/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/coupler-io/skills/ai-traffic-vs-organic-search-report)<a href="https://agentmods.dev/skills/coupler-io/skills/ai-traffic-vs-organic-search-report"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/ai-traffic-vs-organic-search-report/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/coupler-io/skills/ai-traffic-vs-organic-search-report"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/ai-traffic-vs-organic-search-report.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 | $0.00196 | $0.03870 |
| Opus 5.5 | $0.00078 | $0.01548 |
| Sonnet 5.5 | $0.00039 | $0.00774 |
| Haiku 4.5 | $0.00020 | $0.00387 |
Grade A, and why
ai-traffic-vs-organic-search-report 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 6d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Traffic vs Organic Search Report
Shows how much traffic ChatGPT, Perplexity and Gemini send your site and how it compares with Google organic search. AI Traffic vs Organic Search Report is a Coupler.io AI agent skill that works with live data from Google Analytics 4 (GA4).
Shows how much traffic answer engines send your site, how it compares to normal search, and whether it's growing.
More people are asking ChatGPT, Perplexity, Gemini and Claude instead of searching Google, and when one of those tools mentions your site, some of those people click through. That traffic shows up in GA4 as referrals — but scattered across source names, easy to miss, and never compared against your organic search on the same terms. Put them side by side and you can see whether AI is bringing real, engaged visitors or just curiosity clicks, whether it's growing month over month, and whether it's adding to your search traffic or starting to replace it.
One thing this does not do, said up front: it measures the traffic answer engines send you. It does not tell you whether you're cited in their answers — whether ChatGPT recommends you when someone asks. That's what most people mean by "ranking in AI answers". Search Console now reports impressions in Google's AI Overviews and AI Mode, but Coupler's connector doesn't expose that report, and ChatGPT or Perplexity citations are in no Google source at all. This skill is the honest half: what actually arrives, not what gets said about you. If you need citation tracking, that's a different source entirely.
What you get back
- AI referral traffic sized — sessions and their share of total, from each answer engine (ChatGPT, Perplexity, Gemini, Claude and others), over time.
- AI vs organic search, side by side — engagement rate, key events and revenue for each, so you can see which traffic is worth more per visit.
- The trend — is AI traffic growing, and is it adding to organic search or coincident with organic falling. Growing-alongside and replacing look different and mean different things.
- Which pages AI sends people to — the content answer engines actually surface, if landing page is available.
- A coverage statement — which AI sources GA4 could separate cleanly, which got lumped into "referral" or "unassigned", and the hard limit that none of this is citation data.
Read-only. It reads GA4 and reports back. It changes nothing.
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.
- 6d ago First seen · 275 lines · 196 tokens per session scan A 07cb619f9605
ai-traffic-vs-organic-search-report is a skill published in the GitHub repository coupler-io/skills (41 stars, last pushed 4d ago), licensed MIT. It adds 196 tokens to every session and 3,870 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-11-15.
ai-traffic-vs-organic-search-report compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-traffic-vs-organic-search-reportcoupler-io/skills | Skill | 41 | 4d ago | MIT | A | 196 | Claude Code |
| jobs-to-be-donewondelai/skills | Skill | 2.8k | today | MIT | A | 137 | Claude Code |
| remotion-best-practicesguanyang/open-agent-hub | Skill | 1.0k | yesterday | MIT | A | 116 | Claude Code |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | 6d ago | MIT | A | 60 | Claude Code |
| etsy-social-media-marketingnexscope-ai/eCommerce-Skills | Skill | 1.5k | 11d ago | MIT | A | 23 | Claude Code, Codex |
| walmart-price-trackernexscope-ai/eCommerce-Skills | Skill | 1.5k | 11d ago | MIT | A | 0 | Claude Code, Codex |
| happiness-skillkangarooking/cangjie-skill | Skill | 13k | 1mo ago | MIT | A | 136 | Claude Code, Codex |