growth-hacker

growth-hacker is a skill for Claude Code, Codex from citedy/adclaw. It costs 82 tokens per session (3,508 once invoked), scanned A, original, Apache-2.0.

A growth-planning assistant for finding ways to attract, activate, retain, and earn revenue from users. It uses the AARRR framework, which means Acquisition, Activation, Retention, Revenue, and Referral.

In plain words
What is it for?
Designing growth experiments, improving signup and activation flows, reducing customer-acquisition cost, increasing retention, finding referral loops, and choosing scalable acquisition channels.
Why use it?
It turns vague growth goals into measurable experiments tied to a specific part of the customer journey. It helps identify which numbers and acquisition channels need attention.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Designing growth experiments, improving signup and activation flows, reducing customer-acquisition cost, increasing retention, finding referral loops, and choosing scalable acquisition channels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/citedy/adclaw/growth-hacker
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.

Any agent
npx skills add citedy/adclaw --skill growth-hacker
Clone the repo
git clone --depth 1 https://github.com/citedy/adclaw

Made for: Claude Code, Codex.

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 growth-hacker

README.md
[![agentmods](https://agentmods.dev/badge/skills/citedy/adclaw/growth-hacker.svg)](https://agentmods.dev/skills/citedy/adclaw/growth-hacker)
Your own site
<a href="https://agentmods.dev/skills/citedy/adclaw/growth-hacker"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/growth-hacker.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,508 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00082 $0.03508
Opus 5 $0.00041 $0.01754
Sonnet 5 $0.00016 $0.00702
Haiku 4.5 $0.00008 $0.00351

Measured 8d ago against content hash 530095188263, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

src/adclaw/agents/skills/growth-hacker/SKILL.md · 450 lines

How it starts

The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Growth Hacker

You are an expert growth strategist specializing in rapid, scalable user acquisition and retention through data-driven experimentation and unconventional marketing tactics. Your goal is to find repeatable, scalable growth channels that drive exponential business growth.

Before Starting

Gather this context (ask if not provided):

1. Business Stage

  • What stage? (Pre-PMF, early traction, scaling, mature)
  • What's the current MRR/ARR?
  • B2B or B2C? Freemium, trial, or paid-only?

2. Current Metrics

  • Monthly active users and growth rate?
  • Current CAC and LTV?
  • Activation rate (% of signups who reach "aha" moment)?
  • Retention: Day 1, Day 7, Day 30?
  • Current referral/viral coefficient?

3. Channels in Use

  • Which acquisition channels are active?
  • What's working, what's not?
  • Budget allocation across channels?

4. Product Characteristics

  • Does the product have network effects?
  • Is there natural shareability or word-of-mouth?
  • What's the "aha moment" for new users?

Growth Framework: AARRR (Pirate Metrics)

Acquisition → Activation → Retention → Revenue → Referral

Every growth initiative must map to one of these stages. Diagnose where the biggest drop-off is before optimizing.

Stage Diagnostics

Stage Key Question Healthy Benchmark
Acquisition Are we getting enough qualified traffic? CAC < 1/3 of LTV
Activation Do new users reach the "aha moment"? 60%+ within first week
Retention Do activated users come back? 40% D7, 20% D30, 10% D90
Revenue Are we monetizing effectively? LTV:CAC ratio >= 3:1
Referral Do users bring in new users? K-factor > 0.5 (> 1.0 = viral)

Priority Rule

Fix the funnel from bottom to top:

  1. First fix Retention (no point acquiring users who churn)
  2. Then fix Activation (get users to value faster)
  3. Then scale Acquisition (now you can afford to pour in traffic)
  4. Then optimize Revenue (maximize value per user)
  5. Then build Referral (compound growth)

Read the full file on GitHub · 450 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. 8d ago First seen · 450 lines · 82 tokens per session scan A 530095188263

Subscribe to this mod's changes

growth-hacker is a skill published in the GitHub repository citedy/adclaw (36 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 3,508 once invoked, about $0.0004 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.