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 Thibaultbm/claude-seo-geo --skill seo-traffic-dropgit clone --depth 1 https://github.com/Thibaultbm/claude-seo-geoWrote 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/thibaultbm/claude-seo-geo/seo-traffic-drop)<a href="https://agentmods.dev/skills/thibaultbm/claude-seo-geo/seo-traffic-drop"><img src="https://agentmods.dev/badge/skills/thibaultbm/claude-seo-geo/seo-traffic-drop/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/thibaultbm/claude-seo-geo/seo-traffic-drop"><img src="https://agentmods.dev/badge/skills/thibaultbm/claude-seo-geo/seo-traffic-drop.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 | $0.00147 | $0.04670 |
| Opus 5 | $0.00073 | $0.02335 |
| Sonnet 5 | $0.00029 | $0.00934 |
| Haiku 4.5 | $0.00015 | $0.00467 |
Grade A, and why
seo-traffic-drop 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 12d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Traffic drop: find what changed before changing anything
A drop is a diagnostic problem, not a content problem. The failure mode of this work is not missing the cause, it is acting on the first plausible one: a core update landed near the date, so the team rewrites 40 articles, while the actual cause was a noindex shipped in a template on the same week. The rewrite then hides the evidence.
So the order is fixed. Confirm the loss is real, date it, shape it, name the candidate causes, confirm one with a test that could have failed, and only then fix. Every step below produces evidence someone else can check.
Company knowledge first (Obsidian)
If the working environment contains an Obsidian vault or any local knowledge base (a folder of .md notes, often with a .obsidian directory), read the relevant notes before acting: the SEO action log (what was shipped and when), past incidents, the site's seasonality, migrations, and known technical debt. The action log is the highest-value note in a drop investigation, because it answers "what changed" without waiting for the client. At the end of the session, append the diagnosis, the evidence and the remediation to that log so the next incident starts with a history. Vault structure and protocols: the obsidian-brain skill.
When to use this skill
Use it for:
- "Our traffic dropped", "we lost rankings", "clicks fell off a cliff"
- Impressions or clicks collapsing in Search Console, on the whole site or one section
- Pages disappearing from the index, or a sudden coverage change
- A suspected core update, a manual action, or a penalty
- Traffic loss after a migration, a redesign, a replatform or a big deploy
- Sessions falling in GA4 while Search Console looks fine, or the reverse
- AI referral traffic falling, or the brand losing its citations in AI answers
Hand off once the cause is named:
| Confirmed cause | Skill that fixes it |
|---|---|
| Indexation, robots, rendering, speed, migration, hack | seo-technical |
| Client-rendered site built by an AI generator | seo-ai-site-builders |
| Thin, stale or outranked content | seo-content-blog and the page-type content skills |
| Blocks missing from a page that competitors have | seo-page-sections |
| Cannibalization, orphaned pages, weak internal links | seo-internal-linking |
| Lost or toxic backlinks | seo-backlinks |
| Local pack or Business Profile loss | seo-local |
| Lost AI citations, AI Overview displacement | geo-visibility |
| No measurement to detect the next one | geo-tracking |
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.
- 12d ago First seen · 241 lines · 147 tokens per session scan A 9c14e00a9584
seo-traffic-drop is a skill published in the GitHub repository Thibaultbm/claude-seo-geo (16 stars, last pushed yesterday), licensed MIT. It adds 147 tokens to every session and 4,670 once invoked, about $0.0007 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
geo-audit
Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.
geo
GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GEO audits, citability scoring, AI crawler analysis, llms.txt generation, brand mention scanning, platform-specific…
geo-brand-mentions
Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.
geo-llmstxt
Analyzes and generates llms.txt files -- the emerging standard for helping AI systems understand website structure and content. Can validate existing llms.txt files or generate new ones from scratch by crawling the site.
agent-readiness-scan
Use when a client audit, GEO/AI-visibility snapshot, or remediation re-scan needs the Cloudflare agent-readiness score from isitagentready.com — e.g. Theo client audits, "is the site agent-ready", markdown negotiation / MCP / llms.txt / Content-Signal checks, or tracking score deltas after Tier 0/1 fixes.
found-by-ai
Measure whether AI engines actually recommend a business when buyers ask. Runs the free live scan at areyoufoundbyai.com (no auth, 60s), reads the verdict and the rivals AI names instead, hands back the fix plan, and wires monitored sites into a fix-and-re-measure loop over MCP.