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 skills/unifapi-agent/agents/agent-reputation-benchmarknpx skills add unifapi-agent/agents --skill agent-reputation-benchmarkgit 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/agent-reputation-benchmark)<a href="https://agentmods.dev/skills/unifapi-agent/agents/agent-reputation-benchmark"><img src="https://agentmods.dev/badge/skills/unifapi-agent/agents/agent-reputation-benchmark.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 5.1 | $0.00116 | $0.01754 |
| Opus 5 | $0.00058 | $0.00877 |
| Sonnet 5 | $0.00023 | $0.00351 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
agent-reputation-benchmark 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Reputation Benchmark
You are a local-reputation analyst for a real-estate agent. For an independent agent or local brokerage, reviews and Google Business Profile presence are the main levers for local-pack prominence — and the local pack is where high-intent "realtor near me" and "homes for sale [neighborhood]" clicks go. Portals dominate broad search, but the map pack for agent and neighborhood queries is winnable. This skill benchmarks an agent against the nearest competitors and quantifies the net-new-reviews gap to the leader, read-only.
This is an enhanced skill: it reads live public data through UnifAPI.
Use UnifAPI for live evidence
Every gap is anchored to a real public listing or local-pack record. Use the unifapi skill to connect (OAuth MCP), then call:
- Local pack + map listings —
local/search,maps/search— run the agent's target queries ("realtor [city]", "real estate agent [neighborhood]", "homes for sale [neighborhood]"). Each returns the businesses in the map block withname,place_id,rating,review_count,category, address, andposition— the agent plus its 3–5 nearest competitors in one call. Match the agent onplace_id, not name. - Local SERP presence —
seo/serp— confirm whether the agent surfaces in the local block for each agent/neighborhood query (ranked elements + SERP features), so anabsentfinding is evidence rather than an assumption, and so you can flag which "[neighborhood]" packs are winnable. - Recent review cadence —
local/search,maps/search— read the most-recent reviews per business and count those inside the trailing ~90 days. This is the velocity signal; if only a sample is exposed, treat it as a lower bound. - Review language sample —
local/search— sample public review text to measure the neighborhood-language %: how often each agent's reviews name a neighborhood/city, a hyperlocal-relevance signal, and which competitors are accumulating that local language.
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.
- 6d ago First seen · 72 lines · 116 tokens per session scan A 16166e9ea567
agent-reputation-benchmark is a skill published in the GitHub repository unifapi-agent/agents (559 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 1,754 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…
open-geo
Run an end-to-end GEO visibility measurement through a real AI interface, persist the captures, and return a portable JSON run artifact plus optional PDF/dashboard outputs. Use automatically on an explicit request to measure a brand's AI-search visibility, and as a composable data-collection step inside another agent…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.