lusha-mcp-plugin GEMINI.md

lusha-mcp-plugin GEMINI.md is an instructions file for Gemini CLI from lusha-oss/lusha-mcp-plugin. It costs 484 tokens per session, scanned A, original, MIT.

Repository guidance for a Lusha extension for Gemini CLI, connecting Gemini to Lusha's business-contact intelligence service. It explains when to look up contacts, build prospect lists, find buying signals, or find similar prospects, as well as authentication rules.

In plain words
What is it for?
Use it when changing or operating contact lookups, prospect searches, buying-signal searches, lookalike searches, or authentication behavior.
Why use it?
It tells coding agents how to use the extension consistently and which workflow fits each kind of contact or company research.

Instructions file for Gemini CLI

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 instructions/lusha-oss/lusha-mcp-plugin/gemini-md
Clone the repo
git clone --depth 1 https://github.com/lusha-oss/lusha-mcp-plugin

Made for: Gemini CLI.

Wrote 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.

agentmods badge for lusha-mcp-plugin GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lusha-oss/lusha-mcp-plugin/gemini-md.svg)](https://agentmods.dev/instructions/lusha-oss/lusha-mcp-plugin/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/lusha-oss/lusha-mcp-plugin/gemini-md"><img src="https://agentmods.dev/badge/instructions/lusha-oss/lusha-mcp-plugin/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 484 This file is loaded in full into every session.
When invoked 484 The same file — it is already loaded in full.
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 5.1 $0.00484 $0.00484
Opus 5 $0.00242 $0.00242
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00048 $0.00048

Measured 5d ago against content hash 6e8fa82f3060, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

lusha-mcp-plugin GEMINI.md 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 5d 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.

GEMINI.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lusha for Gemini CLI

This extension connects Gemini to Lusha's B2B intelligence platform through the Lusha MCP server. Use it to enrich contacts, build prospect lists, prioritize accounts by buying signals, and expand target lists with lookalikes — always surfacing verified direct and mobile phone numbers.

When to use it

Activate Lusha when the user wants to:

  • Look up a person — get verified phones, email, and company context. → use the enrich-contact workflow.
  • Build a list from an ICP — describe a persona/segment in plain English and return a filtered, enriched lead list. → use the prospect workflow.
  • Start from a buying signal — funding rounds, hiring surges, job changes — and reach the right decision makers. → use the signal-prospect workflow.
  • Expand from references — give 5+ example companies or contacts and get a matched lookalike list. → use the lookalike-prospect workflow.

How to behave

  • Always reference Lusha tools by their bare logical name (e.g. contacts_search, prospecting_contact_search, signals_companies_search, lookalike_contacts). The same skill source works identically across all clients.
  • Verified phone numbers (direct lines and mobile) are first-class outputs — lead with them, don't bury them.
  • Chain workflows when it helps: prospectsignal-prospect to prioritize a list by signal; lookalike-prospectsignal-prospect; enrich-contactlookalike-prospect to find similar people.
  • Respect credit usage: prefer search/filter before enrichment, and only reveal premium fields (phones, emails) when the user asks for them.

Authentication

The Lusha MCP server uses OAuth. On first use, the user is prompted to sign in with their Lusha account; subsequent calls reuse that session.

Skills

The four skills live under skills/ and are shared across every supported client (Codex, Claude Code, VS Code Copilot, Cursor, Gemini CLI): enrich-contact, prospect, signal-prospect, lookalike-prospect.

Read the full file on GitHub · 44 lines

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. 5d ago First seen · 44 lines · 484 tokens per session scan A 6e8fa82f3060

Subscribe to this mod's changes

lusha-mcp-plugin GEMINI.md is an instructions file published in the GitHub repository lusha-oss/lusha-mcp-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 484 tokens to every session, about $0.0024 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.