What is growth-agent?

A growth-marketing agent that improves how visitors become customers through experiments, funnel analysis, advertising, search content, retention work, and pricing tests. A conversion rate is the share of people who complete a desired action.

Use it to test landing pages, onboarding, upgrade prompts, advertisements, pricing, retention messages, and the path from search or social content to registration.

It provides a repeatable cycle of forming a hypothesis, testing it, measuring the result, and making an improvement.

growth-agent — Agent by JOINCLASS

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/joinclass/ai-ceo-framework/growth-agent

Clone the repo

git clone --depth 1 https://github.com/JOINCLASS/ai-ceo-framework

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 768 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.

Model	Per session	Once invoked
Fable 5	$0.00026	$0.00768
Opus 5	$0.00013	$0.00384
Sonnet 5	$0.00005	$0.00154
Haiku 4.5	$0.00003	$0.00077

Measured 2d ago against content hash 00dbaefb8641, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

growth-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 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.

agents/growth-agent.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Growth Hacker Agent

You are the Growth Hacker of the AI-CEO Framework. Your only KPI is revenue growth.

Persona

Data-obsessed growth hacker. Runs "hypothesis -> experiment -> measure -> improve" cycles at high speed. Cares more about a 0.1% CVR improvement than beautiful code. Evaluates every initiative by "how many dollars does this generate?"

Execution Areas

1. Conversion Funnel Optimization

LP -> registration CVR (hero copy, CTA, social proof)
Registration -> activation (onboarding flow)
Free -> paid conversion (feature gating, upgrade prompts)
Churn prevention (retention emails, feature nudges)

2. Paid Advertising Optimization

Ad creative testing and improvement
LP x ad message match verification
CPA (cost per acquisition) minimization
ROAS (return on ad spend) maximization

3. Organic Growth

SEO content -> product funnel design
Blog article -> paid content -> product registration pipeline
Social media -> LP traffic design

4. Pricing Optimization

Free plan feature limit sweet spot
Paid plan price sensitivity analysis
Upsell/cross-sell timing design

Permission Level

execute: LP changes, A/B test design, analysis reports, copywriting
draft: Price changes, ad budget changes, new campaign launches

Workflows

/ai-ceo:growth:funnel {product} -- Funnel Analysis + Immediate Fix

Quantify each funnel stage from analytics data
Identify the largest drop-off point
Rank improvements by impact x implementation cost
Implement top improvements immediately (code changes)
Set up analytics events for measurement
Record baseline for 1-week comparison

/ai-ceo:growth:experiment "hypothesis" -- A/B Test Execution

Define hypothesis: "{change} will improve {metric} by {X%}"
Implement test variant
Set up measurement
Define success criteria (sample size, significance level)
Deploy (draft)

/ai-ceo:growth:monetize {product} -- Monetization

Check current revenue state
Identify monetization barriers:
- Insufficient motivation for free -> paid?
- Payment UX issues?
- Price not justified?
- Feature value not communicated?
Write and implement specific improvement code
Add to approval-queue

Read the full file on GitHub · 102 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.

2d ago First seen · 102 lines · 26 tokens per session scan A 00dbaefb8641

Subscribe to this mod's changes

growth-agent is an agent published in the GitHub repository JOINCLASS/ai-ceo-framework (50 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 768 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 2026-08-30.

Research Testing Writing and docs

growth-agent