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 unifapi-agent/agents --skill llm-mention-trackinggit clone --depth 1 https://github.com/unifapi-agent/agentsWrote 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/unifapi-agent/agents/llm-mention-tracking)<a href="https://agentmods.dev/skills/unifapi-agent/agents/llm-mention-tracking"><img src="https://agentmods.dev/badge/skills/unifapi-agent/agents/llm-mention-tracking.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00120 | $0.02253 |
| Opus 5 | $0.00060 | $0.01126 |
| Sonnet 5 | $0.00024 | $0.00451 |
| Haiku 4.5 | $0.00012 | $0.00225 |
Grade A, and why
llm-mention-tracking 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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Mention Tracking
Track how often a brand and its domain are mentioned across ChatGPT and AI search engines over a fixed prompt set — and how that share of voice compares to named competitors and moves over time. Where an audit is a snapshot, this is the recurring read: the panel and competitor list stay frozen so each run is comparable to the last.
This is an enhanced skill: it reads live public data through UnifAPI. The deliverable is a trend, not a single number, so the value comes from running it on a cadence against an unchanging panel.
Use UnifAPI for live evidence
This is an enhanced skill: it reads live public data through UnifAPI. Use the unifapi skill to connect (OAuth MCP), then discover these GEO operations. All are POST; pass engine (google / chatgpt), location, and language identically on every run so the trend is real movement, not config drift.
- Share of voice across labeled groups — the core read —
geo/mentions/cross-aggregated-metricscompares mentions across labeled groups: put the brand in one group and each named competitor in its own group, and the call returns the head-to-head share directly. This is the engine of the tracker — run it identically every cadence and the output diff is the SoV trend. - Panel-level mentions —
geo/mentions/search(target= array of up to 10 entities: brand domain + each competitor) captures, per prompt, whether each entity is mentioned and in which answers — the granular backing for the aggregated share. - Roll-up —
geo/mentions/aggregated-metricsrolls mentions up across the whole target set in one call (counts, AI search volume, cited domains), cheaper than per-prompt SERP when you only need the totals. - Citation vs name-drop —
geo/serp(target= brand domain,is_targetflag) confirms whether a mention is an actual cited source (a link) or just an in-text name-drop. Citations are the stronger signal; track them on a separate line. - Who's climbing —
geo/mentions/top-domainsranks the most-cited domains for the set; diffing this list run-to-run is the fastest "which competitor is gaining" read. - Weight by demand —
geo/keywords/search-volumeweights each prompt by AI-search demand so SoV reflects the prompts that carry traffic. Pull once at panel creation and reuse across runs (re-pull quarterly).
What ships with it
1 file 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.
- 8d ago First seen · 101 lines · 120 tokens per session scan A 5d59f85d3300
llm-mention-tracking is a skill published in the GitHub repository unifapi-agent/agents (559 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 2,253 once invoked, about $0.0006 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
orangeo-ai-visibility-skill
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…
ai-visibility
Measure and improve whether AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) recommend a brand, and fix the reasons they do not. Use this skill whenever someone asks about AI visibility, AEO, GEO, answer engine optimization, generative engine optimization, "AI SEO", brand mentions or share of voice in AI…
ansvisor-aeo-coach-standalone
Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution. For clients that support…
ansvisor-aeo-coach
Acts as an Answer Engine Optimization (AEO) analyst for users running Ansvisor. Activates when the user asks how their brand is doing across AI search engines (ChatGPT, Gemini, Perplexity, Claude, Copilot, AI Overview, AI Mode), why visibility changed, or how they compare to competitors. Uses the Ansvisor MCP server…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
geo-report
Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions.