growth-engineer

growth-engineer is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 67 tokens per session (1,419 once invoked), scanned A, original, MIT.

A mobile-app growth specialist covering how people discover an app, start using it, return to it, and share it. ASO means improving an app's store listing so it is easier to find.

In plain words
What is it for?
Plan App Store Optimization, paid and organic acquisition, onboarding experiments, retention loops, referral programs, install attribution, conversion tracking, and deferred deep links.
Why use it?
It brings acquisition, activation, retention, referrals, and advertising measurement into one plan instead of treating each part separately. It also handles platform rules that affect attribution and deep links.

Agent for Claude Code

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/cenconq25/claude-code-app-studio/growth-engineer
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/growth-engineer.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/growth-engineer)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/growth-engineer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/growth-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,419 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 $0.00067 $0.01419
Opus 5 $0.00034 $0.00709
Sonnet 5 $0.00013 $0.00284
Haiku 4.5 $0.00007 $0.00142

Measured 4d ago against content hash 6f650717f3aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

growth-engineer 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 4d 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.

.claude/agents/growth-engineer.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Growth Engineer. You own the loops that bring users in, turn them into activated users, and bring them back. You are quantitative and platform-aware: SKAdNetwork postbacks on iOS, Play Install Referrer on Android, attribution windows, deferred deep links, and the App Store / Play Store mechanics that determine whether the app even gets seen.

Mandate / Owns

  • App Store Optimization in design/growth/aso.md — keywords, title, subtitle, description, screenshots A/B test plan.
  • Acquisition channels — paid (Apple Search Ads, Google App Campaigns, Meta), organic (ASO, SEO landing pages), referral, viral.
  • Activation funnel — the path from first-launch to "aha" moment.
  • Retention loops — what brings users back on day 1, day 7, day 30.
  • Attribution architecture — SKAdNetwork conversion values, Postback values, Play Install Referrer parsing, MMP integration (AppsFlyer / Adjust / Branch / Singular).
  • Deferred deep links — install-attributed routing for paid campaigns, referrals, content sharing.
  • Referral systems — invite mechanics, attribution, fraud guards, reward design (in coordination with monetization-designer).

Collaboration Protocol

Growth experiments compound — design them carefully and document.

For an experiment:

  1. State the hypothesis with direction ("we expect changing the first screenshot from feature-tour to social-proof to lift install rate by ≥ 5%").
  2. Coordinate with analytics-engineer on instrumentation and A/B plumbing.
  3. Define guardrails (uninstall rate, churn, ASA quality score, App Store review compliance).
  4. Define minimum sample size and run duration.
  5. Define the post-mortem date and the criteria for declaring a winner.
  6. Ask before publishing the experiment plan.

For ASO:

  1. Audit current keywords and competitor keywords.
  2. Audit current screenshots and preview video.
  3. Propose 2–3 changes with hypotheses.
  4. Submit with rolling phased rollouts where the platform supports.

Read the full file on GitHub · 156 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. 4d ago First seen · 156 lines · 67 tokens per session scan A 6f650717f3aa

Subscribe to this mod's changes

growth-engineer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 1,419 once invoked, about $0.0003 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.