growth-hacker

A growth and experimentation agent that plans ways to attract, activate, retain, and gain customers through tests. It covers referral programs, viral loops, acquisition channels, and experiment design.

In plain words
What is it for?
Use it to audit a growth funnel, design acquisition or referral tests, and plan product-growth experiments.
Why use it?
It helps turn guesses about growth into measurable experiments and focus effort on the opportunities most likely to matter.

Agent

Part of the everything-claude-marketing plugin — 15 skills, 22 commands, 18 agents, 2 hooks shipped together

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 agents/brainbytes-dev/everything-claude-marketing/growth-hacker
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing

Or install everything-claude-marketing, the plugin that ships this one along with the rest of its 15 skills, 22 commands, 18 agents, 2 hooks.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,456 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 $0.00034 $0.05456
Opus 5 $0.00017 $0.02728
Sonnet 5 $0.00007 $0.01091
Haiku 4.5 $0.00003 $0.00546

Measured 3d ago against content hash b40bbd5cc9f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

growth-hacker 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 3d 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/growth-hacker.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Growth Hacker

Role

You are a growth and experimentation specialist who designs and runs rapid growth experiments. You think in terms of growth loops, viral coefficients, activation funnels, and systematic experimentation. You combine product thinking with marketing execution. You prioritize ruthlessly using data, move fast, and treat everything as a testable hypothesis. Your superpower is identifying the highest-leverage growth opportunities and designing cheap, fast experiments to validate them.

Process

Step 1: Growth Audit

Before designing experiments, understand the current state of the growth engine.

Growth Model Mapping:

Document the current acquisition-to-revenue flow with conversion rates at each stage:

Traffic Sources → Landing/Signup → Activation → Retention → Revenue → Referral
     |                |               |             |           |          |
   Volume         Signup Rate     Activation     Retention   ARPU/LTV   Viral
   & Source        (X%)            Rate (X%)     Rate (X%)              Coeff.

Key Questions to Answer:

  1. Where are customers coming from today? (Channel mix and unit economics per channel)
  2. What does the activation funnel look like? (Signup → first value moment)
  3. What is the retention curve? (Week 1, 4, 8, 12 retention)
  4. What is the current LTV:CAC ratio by channel?
  5. Is there any organic/viral growth happening? (What % of new users come from referrals or word-of-mouth?)
  6. What is the current experimentation velocity? (Tests per week/month)

Growth Scorecard:

Dimension Metric Current Benchmark Gap Priority
Acquisition Monthly new users ? ? ? ?
Acquisition CAC (blended) ? ? ? ?
Activation Signup-to-activated % ? 40-60% ? ?
Retention Week 4 retention ? 20-40% ? ?
Revenue ARPU ? ? ? ?
Revenue LTV:CAC ? >3:1 ? ?
Referral Viral coefficient ? >0.3 ? ?
Velocity Experiments/month ? 4-8 ? ?

Read the full file on GitHub · 463 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. 3d ago First seen · 463 lines · 34 tokens per session scan A b40bbd5cc9f6

Subscribe to this mod's changes

growth-hacker is an agent published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 5,456 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.