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 skills add rajitsaha/100xprism --skill popup-crogit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/skills/rajitsaha/100xprism/popup-cro)<a href="https://agentmods.dev/skills/rajitsaha/100xprism/popup-cro"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/popup-cro/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rajitsaha/100xprism/popup-cro"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/popup-cro.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00081 | $0.02407 |
| Opus 5 | $0.00041 | $0.01203 |
| Sonnet 5 | $0.00016 | $0.00481 |
| Haiku 4.5 | $0.00008 | $0.00241 |
Grade A, and why
popup-cro 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 12d 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.
This is a copy
89% identical to popups — 309 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Popup CRO
Create popups that convert without annoying users or damaging brand perception.
Initial Assessment
Product context: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it first and tailor output to it; only ask for what it doesn't cover.
Before recommending, understand:
- Popup Purpose — email/newsletter capture, lead magnet delivery, discount/promotion, announcement, exit intent save, feature promotion, feedback/survey
- Current State — existing popup performance? triggers used? user complaints or feedback? mobile experience?
- Traffic Context — traffic sources (paid, organic, direct); new vs. returning visitors; page types where shown
Core Principles
- Timing is everything — too early = annoying interruption; too late = missed opportunity; right time = helpful offer at the moment of need.
- Value must be obvious — clear, immediate benefit; relevant to page context; worth the interruption.
- Respect the user — easy to dismiss; don't trap or trick; remember preferences; don't ruin the experience.
Trigger Strategies
Time-Based
"Show after 5 seconds" is not recommended; "after 30-60 seconds" (proven engagement) is better. Best for general site visitors.
Scroll-Based
Typically 25-50% scroll depth — indicates content engagement. Best for blog posts and long-form content. Example: "You're halfway through—get more like this."
Exit Intent
Detects cursor moving to close/leave — last chance to capture value. Best for e-commerce and lead gen. Mobile alternative: back button or scroll up.
Click-Triggered
User initiates (clicks button/link), so zero annoyance. Best for lead magnets, gated content, demos. Example: "Download PDF" → popup form.
Page Count / Session-Based
After visiting X pages — indicates research/comparison behavior. Best for multi-page journeys. Example: "Been comparing? Here's a summary..."
Behavior-Based
Add-to-cart abandonment, pricing page visitors, repeat page visits. Best for high-intent segments.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 264 lines · 81 tokens per session scan A ba29377f24cd
popup-cro is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 12d ago), licensed MIT. It adds 81 tokens to every session and 2,407 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to popups, differing in 309 lines, and is treated as a copy.
Other skills, from other repositories
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
google-analytics
Skill "google-analytics" from VKirill/claude-lane-stack, covering version requirements (may 2026), usage, use this skill when, do not use this skill when and purpose.
google-tag-manager
Skill "google-tag-manager" from VKirill/claude-lane-stack, covering 🎯 version requirements (june 2026), usage, use this skill when, do not use this skill when and purpose.
agent-injection-boundary-test
Test an authorized AI agent's handling of instructions embedded in retrieved documents or tool outputs using harmless canaries.
ai-citation-verification
Check whether an AI answer's citations actually support its factual claims, with source-location evidence and explicit uncertainty.
ai-evaluation-dataset
Build a versioned JSONL evaluation dataset for an AI workflow, with acceptance criteria, held-out cases, and leakage checks.