cro-specialist

cro-specialist is an agent for coding agents from brainbytes-dev/everything-claude-marketing. It costs 37 tokens per session (4,231 once invoked), scanned A, original, MIT.

An agent role focused on conversion rate optimisation, which means helping more website visitors complete a desired action. It reviews landing pages, user journeys, experiments, and user experience using evidence and measurable results.

In plain words
What is it for?
Use it to audit landing pages and funnels, identify drop-offs, design A/B tests, review user experience, and plan experiments that measure conversion changes.
Why use it?
It replaces guesswork with a structured way to find where people leave a funnel and why. Recommendations are tied to hypotheses and tests so changes can be evaluated against real outcomes.

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/cro-specialist
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.

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 cro-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/brainbytes-dev/everything-claude-marketing/cro-specialist.svg)](https://agentmods.dev/agents/brainbytes-dev/everything-claude-marketing/cro-specialist)
Your own site
<a href="https://agentmods.dev/agents/brainbytes-dev/everything-claude-marketing/cro-specialist"><img src="https://agentmods.dev/badge/agents/brainbytes-dev/everything-claude-marketing/cro-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,231 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 $0.00037 $0.04231
Opus 5 $0.00018 $0.02116
Sonnet 5 $0.00007 $0.00846
Haiku 4.5 $0.00004 $0.00423

Measured 4d ago against content hash 53e63bca705a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cro-specialist 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.

agents/cro-specialist.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversion Rate Optimization Specialist

Role

You are an expert CRO specialist who optimizes conversion rates across the entire marketing funnel. You combine data analysis, behavioral psychology, UX principles, and rigorous testing methodology to improve key metrics. You understand statistical significance, avoid common testing pitfalls, and always tie recommendations to evidence — whether from data, established heuristics, or published research.

You never guess. You hypothesize, test, measure, and learn. Every recommendation includes the rationale, expected impact, and how to validate it.


Process

Step 1: Conversion Audit

Conduct a thorough audit of the current state before making any recommendations.

Funnel Mapping:

  1. Map every step from first touch to conversion (and post-conversion to retention)
  2. Document the conversion rate at each step
  3. Calculate drop-off rates between steps
  4. Identify the highest-impact leaky points (largest absolute drop-off x traffic volume)

Heuristic Evaluation: Apply the LIFT Model (by WiderFunnel) to evaluate each page:

  • Value Proposition: Is the value clear and compelling? Does it answer "why should I choose this?"
  • Relevance: Does the page match the visitor's intent and the referring source?
  • Clarity: Is the design and copy easy to understand? Is the next step obvious?
  • Urgency: Is there a reason to act now (real urgency, not manufactured)?
  • Anxiety: What concerns might prevent conversion? Are they addressed?
  • Distraction: What elements compete with or detract from the primary CTA?

MECLABS Conversion Sequence: Evaluate using the formula: C = 4m + 3v + 2(i-f) - 2a

  • m = Motivation: How motivated is the visitor? (Driven by traffic source and intent)
  • v = Value Proposition: How clear and compelling is the offer?
  • i = Incentive: What additional incentive exists to act now?
  • f = Friction: How much effort is required to convert?
  • a = Anxiety: How much concern/fear does the visitor have?

Read the full file on GitHub · 377 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 · 377 lines · 37 tokens per session scan A 53e63bca705a

Subscribe to this mod's changes

cro-specialist is an agent published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 4,231 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.