Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/prashishh/seo-geo-report-enginenpx agentmods add skills/prashishh/seo-geo-report-engine/llm-visibilityWrote 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/prashishh/seo-geo-report-engine/llm-visibility)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/llm-visibility"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/llm-visibility/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/prashishh/seo-geo-report-engine/llm-visibility"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/llm-visibility.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 | $0.00192 | $0.01762 |
| Opus 5 | $0.00096 | $0.00881 |
| Sonnet 5 | $0.00038 | $0.00352 |
| Haiku 4.5 | $0.00019 | $0.00176 |
Grade A, and why
llm-visibility 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llm-visibility
The operational core of GEO measurement. For a client's money-query grid it asks all five answer engines the same questions and reports, per query and per engine: is the brand mentioned (named in the answer), is it cited (its domain in the sources), and who is named/cited instead. It rolls up to the durable-visibility bar: present in >=3 of 5 engines. Powered by DataForSEO (Codex-safe, no MCP).
Two distinct signals, because engines behave differently:
- Mention — the model names the brand in prose ("...HubSpot, Zoho..."). This is the primary signal for chat models (ChatGPT, Claude), which name brands from knowledge without linking.
- Citation — the brand's domain appears in the answer's source list. This is the primary signal for Google AI Overview, Perplexity, and Gemini (web-search), which attach sources.
Engines (all through the one DataForSEO account)
google_aio (Google AI Overview, citation-based) · perplexity (sonar, always cites) · chatgpt
(gpt-4o-mini, knowledge-mention) · gemini (2.5-flash, cites) · claude (haiku-4-5, knowledge-mention).
Swap models or force web search on all engines with flags. AIO is keyword/SERP-based; the four LLMs take
the query as a natural-language prompt, so phrase the grid as real questions.
Tool
python3 tools/geo/llm_visibility.py --project <slug> --location <code> \
--brand "Brand Name" alias brand.com \
--prompts "natural question 1" "natural question 2" ... \
--date 2026-07-01 \
--out projects/<slug>/data/raw/dataforseo/llm-visibility-<date>.json
Defaults to client.yml domain + target_keywords + competitors when flags are omitted. Competitors are
pulled from client.yml and matched by name + domain, so the scan reports who the engines name instead.
Every run appends normalized rows to projects/<slug>/data/ai-visibility.csv (date, engine, prompt,
mentioned, cited, competitors, cited_domains) so the dashboard can trend "cited in N of M" over time.
Options: --engines google_aio perplexity chatgpt gemini claude (subset), --web-search-all,
--no-log. Cost: a 6-query x 5-engine scan is roughly $0.25-0.30 (Perplexity + Gemini web search are
the bulk; chat/claude knowledge answers are near-free).
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 · 103 lines · 192 tokens per session scan A d11ff338c8a4
llm-visibility is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 192 tokens to every session and 1,762 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
content-amplifier
Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…
email-sequence-designer
Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound)…
reactivation-specialist
Use when the user asks to "build a win-back campaign", "re-engage lapsed subscribers", "run a re-permission / re-consent sweep", or "sunset my dead list"; produces a closed-loop reactivation program — a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm /…
campaign-planner
Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", "track or close a creator campaign", or "record a late campaign correction"; produces the plan and, when requested, a non-canonical evidence tracker with scoped identity, publication, reconciliation, close, and reopen receipts. Not…
product-feed-optimizer
Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…
attribution-reconciler
Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution…