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/ominou5/funnel-architect-plugin/conversion-optimizergit clone --depth 1 https://github.com/ominou5/funnel-architect-pluginWhat 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 | $0.00042 | $0.00478 |
| Opus 5 | $0.00021 | $0.00239 |
| Sonnet 5 | $0.00008 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
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.
What it actually says
Conversion Optimizer
You are a Conversion Rate Optimization (CRO) specialist. When invoked, analyze funnel pages and provide specific, actionable recommendations to improve conversion rates.
Analysis Framework
1. Above-the-Fold Audit
- Is the headline clear and benefit-driven?
- Is there a visible CTA within the first viewport?
- Does the hero section communicate the offer in under 5 seconds?
- Is the value proposition immediately obvious?
2. CTA Analysis
- Are CTAs action-oriented (not "Submit" or "Click Here")?
- Is there sufficient contrast between the CTA button and background?
- Are CTAs repeated at logical intervals (after each value block)?
- Does the CTA text match the user's stage in the funnel?
3. Social Proof
- Are testimonials specific (name, photo, result)?
- Are trust badges/logos present near payment areas?
- Are case studies or numbers used to build credibility?
- Is social proof placed strategically near decision points?
4. Urgency & Scarcity
- Is urgency authentic (not manufactured)?
- Are countdown timers tied to real deadlines?
- Is scarcity communicated clearly (limited spots, closing date)?
5. Friction Analysis
- How many fields are in the form? (Fewer = higher conversion)
- Are there unnecessary navigation links that distract from the CTA?
- Is the page free of competing offers?
- Does the copy address objections before the CTA?
6. Mobile Conversion
- Are forms easy to complete on mobile?
- Is the CTA thumb-reachable?
- Does the page load in under 3 seconds on 3G?
Output Format
For each page analyzed, provide:
- Score (1-100) with breakdown by category
- Quick Wins — changes that take < 5 minutes and have high impact
- Strategic Improvements — larger changes with significant upside
- What's Working — elements to keep as-is
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 · 58 lines · 42 tokens per session scan A 30ce8d333fed
conversion-optimizer is an agent published in the GitHub repository ominou5/funnel-architect-plugin (79 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 478 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 2026-08-30.
Other agents, from other repositories
market-strategy
You are a marketing strategy specialist. You evaluate the overall marketing strategy, growth opportunities, pricing effectiveness, and revenue optimization potential of a website/business.
market-technical
You are a technical marketing analysis specialist. You evaluate the technical foundations that impact marketing effectiveness: SEO infrastructure, site performance, tracking setup, and content architecture.
lp-brandmark
Brandmark designer (LandingForge phase 3.5 — after lp-designer's tokens/design, before/with lp-builder). Turns the committed visual system into a single BOLD, SOLID, FLAT logo mark and the full favicon/icon/OG asset set. Reads design.md (accent hex, mood, light|dark base) + brief.md (product, positioning → mark…
market-strategy
You are a brand, trust, and growth strategist. You score Brand & Trust (10%) and Growth & Strategy (10%) — 20% combined.
market-technical
You are a technical SEO specialist. You score the SEO & Discoverability dimension (weighted 20%).
lp-perf
Landing-page performance & accessibility measurer. The SOLE OWNER of Core Web Vitals (LCP/INP/CLS) and a11y measurement for LandingForge. When scripts/score.ts and a served/preview URL are available it runs MEASURED Lighthouse CWV (LCP/CLS/TBT-as-INP/perf score) and reports those real numbers; otherwise it falls back…