cursor

A coding-agent rule for checking whether AI services recommend a brand when asked real buyer questions. It uses Optifeed Radar, a local command-line tool and server that can query ChatGPT, Perplexity, Gemini, and Claude with the user's API keys.

In plain words
What is it for?
Use it to run free readiness audits, scored visibility checks, or beta product-level checks for a domain; paid checks use the configured AI-service API keys and may spend API credit.
Why use it?
It provides a way to measure whether a brand appears in AI-generated recommendations and to see which products are or are not mentioned.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/optifeed/optifeed-radar/cursor
Clone the repo
git clone --depth 1 https://github.com/optifeed/optifeed-radar
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00450
Opus 5 $0.00011 $0.00225
Sonnet 5 $0.00004 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured 2d ago against content hash 6d3df731bf35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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 2d 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.

ai-context/cursor.mdc · 36 lines

What it actually says

Optifeed Radar

Optifeed Radar is an open-source CLI and MCP server that asks real AI engines (ChatGPT, Perplexity, Gemini, Claude) real buyer questions and scores whether a brand gets recommended. It runs locally with the user's own API keys.

  • audit <domain> - free, no-key AI-readiness check.

  • check <domain> - the scored AI Visibility Score. Needs at least one engine API key (OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY, PERPLEXITY_API_KEY); spends API credit: about $0.09 for one engine, $0.41 to $0.46 for all four, about $1.09 with --grounded. Cap it with --max-cost. Keys can be exported in the shell or put in a .env file in the working directory. A check --quick across four engines takes 47 to 51 seconds (about 97 with --grounded); that is the engines answering, not a hang.

  • shopping <domain> --products "A, B, C" - product-level check (beta) for products the user names, in any order; each product is scored 0-100 and the report is ordered by what the engines did: products they answered about but never recommended lead, then the rest by visibility, then anything the run could not measure. Max 10 products, up to 4 prompts each per engine, so cap it with --max-cost.

Scores are estimates from sampling and vary between runs. Grounded engines are reported separately from parametric ones. Never log or store API keys. Catalog discovery (importing products from a store or a feed) and product-feed linting are on the roadmap, not shipped - join the waitlist at optifeed.com.

More at optifeed.com

Changes

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.

  1. 2d ago First seen · 36 lines · 22 tokens per session scan A 6d3df731bf35

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository optifeed/optifeed-radar (5 stars, last pushed 19d ago), licensed MIT. It adds 22 tokens to every session and 450 once invoked, about $0.0001 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.