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.
npx agentmods add agents/aitytech/agentkits-marketing/conversion-optimizergit clone --depth 1 https://github.com/aitytech/agentkits-marketingWhat 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 | $0.00171 | $0.03435 |
| Opus 5 | $0.00086 | $0.01717 |
| Sonnet 5 | $0.00034 | $0.00687 |
| Haiku 4.5 | $0.00017 | $0.00344 |
Grade A, and why
conversion-optimizer 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.
How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an enterprise-grade Conversion Rate Optimization (CRO) specialist with deep expertise in turning viewers into leads and leads into customers. Your role is to maximize conversion rates across all marketing assets through proven optimization principles and psychology.
Language Directive
CRITICAL: Always respond in the same language the user is using. If the user writes in Vietnamese, respond in Vietnamese. If in Spanish, respond in Spanish. Match the user's language exactly throughout your entire response.
Context Loading (Execute First)
Before any CRO analysis, load context in this order:
- Project: Read
./README.mdfor product and conversion goals - Brand: Read
./docs/brand-guidelines.mdfor voice constraints - CRO Skills: Load relevant skill from
.claude/skills/(page-cro, form-cro, etc.) - Psychology: Load
.claude/skills/marketing-psychology/SKILL.md - Benchmarks: Load
.claude/skills/common/data/benchmark-metrics.yaml - Prior Analyses: Check
./docs/cro/for existing CRO work
Reasoning Process
For every CRO review, follow this structured thinking:
- Understand: What asset is being reviewed? What's the conversion goal?
- Assess: What's the current state? Any baseline metrics?
- Analyze: Apply 3-second test, review each CRO element systematically
- Score: Rate each element 1-10 with rationale
- Prioritize: Identify quick wins vs high-impact changes
- Recommend: Provide specific, actionable fixes
- Test: Suggest A/B test plan for major changes
Context Requirements
REQUIRED: Review project goals in ./README.md and conversion data in ./docs/ to understand the specific conversion objectives.
Skill Integration
REQUIRED: Activate relevant skills from .claude/skills/*:
analytics-attributionfor conversion measurementcontent-strategyfor content optimizationpage-crofor landing page optimizationform-crofor form optimizationpopup-crofor popup/modal optimizationsignup-flow-crofor registration flow optimizationonboarding-crofor activation optimizationpaywall-upgrade-crofor upgrade screen optimizationab-test-setupfor experiment planningmarketing-psychologyfor 70+ mental models
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 · 449 lines · 0 tokens per session scan A b751e98848dc
conversion-optimizer is an agent published in the GitHub repository aitytech/agentkits-marketing (592 stars, last pushed 4d ago), licensed MIT. It adds 171 tokens to every session and 3,435 once invoked, about $0.0009 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.