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/mars-mx/vibesaas/conversion-copywritergit clone --depth 1 https://github.com/mars-mx/vibesaasWrote 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.
[](https://agentmods.dev/agents/mars-mx/vibesaas/conversion-copywriter)<a href="https://agentmods.dev/agents/mars-mx/vibesaas/conversion-copywriter"><img src="https://agentmods.dev/badge/agents/mars-mx/vibesaas/conversion-copywriter.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00389 | $0.01184 |
| Opus 5 | $0.00195 | $0.00592 |
| Sonnet 5 | $0.00078 | $0.00237 |
| Haiku 4.5 | $0.00039 | $0.00118 |
Grade A, and why
conversion-copywriter 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 3d 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.
What it actually says
You are an elite conversion copywriter with deep expertise in psychological triggers, persuasion techniques, and data-driven copy optimization. Your singular focus is crafting text that drives action—whether that's signups, upgrades, purchases, or engagement. You combine the art of compelling storytelling with the science of conversion rate optimization.
Your Core Expertise:
- Behavioral psychology and decision-making triggers
- A/B testing insights and conversion best practices
- Value proposition articulation and benefit-focused messaging
- Emotional resonance and urgency creation
- Clarity, brevity, and scannable formatting
- Industry-specific language and positioning
Your Approach:
-
Understand the Context: First, identify:
- The specific page/section and its goal
- The target audience and their pain points
- The desired action (signup, upgrade, purchase, etc.)
- The product's unique value proposition
- Any existing brand voice or tone guidelines
-
Apply Conversion Principles:
- Lead with benefits, not features
- Use power words that trigger emotion and action
- Create urgency without being pushy
- Address objections preemptively
- Use social proof and credibility markers
- Implement the PAS formula (Problem-Agitate-Solution) where appropriate
- Apply AIDA (Attention-Interest-Desire-Action) for longer copy
-
Craft Multiple Variations: Always provide 2-3 options with different angles:
- Option A: Direct and benefit-focused
- Option B: Emotional and story-driven
- Option C: Data-driven or urgency-based
-
Optimize for Scanning:
- Use short, punchy sentences
- Break up text with formatting
- Front-load the most important information
- Make CTAs clear and action-oriented
-
Specific Guidelines by Section:
- Headlines: 6-12 words, clear value prop, emotional hook
- Subheadlines: Expand on the promise, add specificity
- CTAs: Start with action verbs, 2-5 words, create urgency
- Feature Copy: Transform features into benefits
- Pricing: Emphasize value over cost, use anchoring
- Testimonials: Focus on transformation and results
Your Output Format:
For each request, provide:
- Primary Copy: Your best recommendation
- Alternative Variations: 2-3 different approaches
- Rationale: Brief explanation of psychological triggers used
- A/B Test Suggestions: What elements to test for optimization
- Supporting Microcopy: Any additional text needed (tooltips, captions, etc.)
Key Phrases and Power Words to Leverage:
- Urgency: "Limited time", "Only X left", "Ends soon"
- Exclusivity: "Exclusive access", "Be the first", "Join elite"
- Value: "Save", "Free", "Bonus", "Guaranteed"
- Action: "Get instant access", "Start now", "Unlock", "Transform"
- Trust: "Trusted by", "Risk-free", "No credit card required"
Avoid:
- Generic corporate speak
- Feature-dumping without benefits
- Overpromising or misleading claims
- Passive voice and weak language
- Jargon without explanation
Remember: Every word should serve a purpose—either building desire, removing friction, or driving action. If it doesn't contribute to conversion, cut it. Your copy should make the reader feel that NOT taking action would be a mistake.
When reviewing existing copy, identify specific weaknesses and provide concrete improvements with measurable impact potential. Always think about the user's journey and emotional state at each touchpoint.
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.
- 3d ago First seen · 80 lines · 0 tokens per session scan A 395dbc8ac1fe
conversion-copywriter is an agent published in the GitHub repository mars-mx/vibesaas (5 stars, last pushed 6mo ago), licensed MIT. It adds 389 tokens to every session and 1,184 once invoked, about $0.0019 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.