customer-icp-agent

customer-icp-agent is an agent for Claude Code from Andytoizer/gtm-brain-builder. It costs 36 tokens per session (138 once invoked), scanned A, original, MIT.

A research agent that builds customer, ideal-customer-profile, persona, segment, and proof context from business data and customer language.

In plain words
What is it for?
Use it to organize revenue, CRM, product-use, support, and customer-language evidence, while separating approvals for names, logos, quotes, metrics, screenshots, and case studies.
Why use it?
It reduces the risk of choosing target customers or using customer evidence from a single incomplete source.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: $skill-name invocation.

Part of the gtm-brain-builder plugin — 11 skills, 9 agents shipped together

Good fit Use it to organize revenue, CRM, product-use, support, and customer-language evidence, while separating approvals for names, logos, quotes, metrics, screenshots, and case studies.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/andytoizer/gtm-brain-builder/customer-icp-agent
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.

Clone the repo
git clone --depth 1 https://github.com/Andytoizer/gtm-brain-builder

Made for: Claude Code.

Or install gtm-brain-builder, the plugin that ships this one along with the rest of its 11 skills, 9 agents.

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 customer-icp-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/andytoizer/gtm-brain-builder/customer-icp-agent.svg)](https://agentmods.dev/agents/andytoizer/gtm-brain-builder/customer-icp-agent)
Your own site
<a href="https://agentmods.dev/agents/andytoizer/gtm-brain-builder/customer-icp-agent"><img src="https://agentmods.dev/badge/agents/andytoizer/gtm-brain-builder/customer-icp-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00036 $0.00138
Opus 5 $0.00018 $0.00069
Sonnet 5 $0.00007 $0.00028
Haiku 4.5 $0.00004 $0.00014

Measured 7d ago against content hash 08b10eac4244, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

customer-icp-agent 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 7d 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.

agents/customer-icp-agent.md · 21 lines

What it actually says

You are the customer ICP agent.

Use the $customer-icp-agent skill as your playbook.

Owns

  • customers/
  • icp/

Output Standard

  • Clean billing/company/product aliases before using names as proof.
  • Keep name, logo, use case, outcome, metric, quote, screenshot, and case study approvals separate.
  • Do not derive ICP from one source alone.
  • Ask Grill-me before promoting best-customer patterns.
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. 7d ago First seen · 21 lines · 36 tokens per session scan A 08b10eac4244

Subscribe to this mod's changes

customer-icp-agent is an agent published in the GitHub repository Andytoizer/gtm-brain-builder (8 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 138 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

hormozi-persona

Alex Hormozi persona, always in first person, never breaking character. Use as the base voice in every hormozi-gtm command. Runs Value Equation + Core Four + Money Models analysis before executing any request. Brutal, constructive feedback.

henriquecaner/hormozi-gtm · 58 tokens

ad-architect

Video script specialist — long-form VSL (8-15min) and short-form (15-60s for Reels/Shorts/TikTok). Masters the hook framework, the VSL 7-step arc, and ad copy formula. Use to write new scripts, refine existing ones, or generate batches of variants.

henriquecaner/hormozi-gtm · 70 tokens

offer-architect

Grand Slam Offer and Value Equation specialist. Use when you need to diagnose, rebuild, or create an offer from scratch. Prerequisite for LPs and ads — copy written on top of a weak offer is money out the window.

henriquecaner/hormozi-gtm · 51 tokens

humanizer

Final step of the pipeline. Takes a finished draft and strips AI writing patterns (em-dash overuse, rule of three, AI vocab, promotional language, vague attributions) in both EN and PT-BR. Always run before saving external output (LP, ad, hooks, plan, etc).

henriquecaner/hormozi-gtm · 64 tokens

money-model-architect

Money Model specialist — Attraction Offer, Core Offer, Upsell, Downsell, Continuity. Use to design the revenue model, calculate LTV:CAC, set the ascension ladder, and lock in Client-Financed Acquisition.

henriquecaner/hormozi-gtm · 52 tokens

pricing-strategist

Pricing specialist built on the 5 laws of the LEAKED Pricing Playbook + Value Equation + LTV:CAC. Use to analyze current price, recommend ranges, structure tiers and anchoring, and validate margin.

henriquecaner/hormozi-gtm · 49 tokens