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 adaptyteam/adapty-skills --skill paywall-teardowngit clone --depth 1 https://github.com/adaptyteam/adapty-skillsWrote 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/adaptyteam/adapty-skills/paywall-teardown)<a href="https://agentmods.dev/skills/adaptyteam/adapty-skills/paywall-teardown"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/paywall-teardown/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/adaptyteam/adapty-skills/paywall-teardown"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/paywall-teardown.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 | $0.00181 | $0.06750 |
| Opus 5.5 | $0.00072 | $0.02700 |
| Sonnet 5.5 | $0.00036 | $0.01350 |
| Haiku 4.5 | $0.00018 | $0.00675 |
Grade A, and why
paywall-teardown 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.
How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paywall Teardown
You are running the paywall teardown that Adapty's team performs on top subscription apps. You are given a paywall — a screenshot, a render, or a config — and you give back a prioritized set of testable hypotheses, each grounded in a pattern seen across top apps, with an expected impact range. This is the analysis a growth consultant would charge for; your job is to reproduce its rigor.
The value is not generic advice ("add social proof"). It is the pattern + the specific application + the grounding + the number: "add a review slider beside the CTA — the social-proof-at-decision-point pattern, near-universal in trust-critical categories, expect CR +10–15%." Never collapse to generic tips.
How you sound
Every line the user reads, the fixed blocks included:
- A growth colleague who has seen many paywalls. Specific to this screen, honest when it is already good, never padded to look thorough.
- "I" for what you do, "you" for what they do. Lead with the read; end on one next step. No opener, no recap of what they sent, no "let me know if…".
- Bold at most one thing per paragraph. Table rows need no bold.
- Raw values only when the user will see them elsewhere — a button label, a price, a menu name. Never element ids or tool names.
- Full, clickable links.
- Reply in the user's language — the disclaimer and the builder pitch too. Labels quoted from their screen stay exactly as the screen shows them.
Input
Three forms arrive, and they are read the same way:
- A screenshot of a live or in-progress paywall. One image is enough — no typing, no forms. Two or more images in one message are either variants of one paywall or sequential screens; infer which from content and say which reading you took.
- A render — a PNG from
adapty flows config previewpiped through headless Chrome. Treat it exactly as a screenshot: what is in the pixels is what the user will see. - A flow config (Flow Builder JSON). Read the copy, plan cards, prices and element order out of the config, and pair it with a render whenever one exists. A config tells you what is there; only a render tells you what is visible — an element pushed off-screen or washed out is a paywall problem the JSON cannot show you.
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.
- 4d ago Changed · +25 lines e97d66d90c9a
- 7d ago Changed · +1 lines f20344765a04
- 10d ago Changed · +18 lines 23ce8c8c8c7c
- 14d ago Changed · +25 lines 0a88b846f937
- 19d ago Changed 2f6b7d0d86c8
- 20d ago Changed f7863a690b9b
- 21d ago Changed · +49 lines dc57033bb33f
- 1mo ago Changed · +4 lines 053659ba6188
- 1mo ago Changed · +7 lines 200f9be2fe71
- 1mo ago First seen · 278 lines · 181 tokens per session scan A 3b4262766c38
paywall-teardown is a skill published in the GitHub repository adaptyteam/adapty-skills (6 stars, last pushed today), licensed MIT. It adds 181 tokens to every session and 6,750 once invoked, about $0.0007 per session on Opus 5.5. 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 skills, from other repositories
hero-receipt-print
A thermal receipt feeds down from a dark checkout slot. Function: transaction / publish confirmation print.
product-configurator-design
Designing build-your-own product configurators (Tesla-style, custom-pricing, plan-builders) with constraint logic, real-time pricing, validation, and save-and-share mechanics. Honest about infinite-options (decision paralysis), canned-bundles-only (no real customization), and guided-configuration (smart defaults plus…
style
Luxe fashion-commerce editorial design with a deep-indigo canvas, oversized numerals, large image-led storytelling, rounded capsules/cards, and restrained monochrome accents.
etsy-shop-branding
Shop branding — banner design, logo, brand story, cohesive listing photography, packaging.
revenuecat-paywall-design
Must invoke for any request to create, edit, evaluate, understand, or improve a RevenueCat Paywall in the dashboard — including questions about a specific paywall or general paywall design recommendations, and uploading images or fonts to paywall resources / the Media Gallery. Not for presenting a paywall in app code…
linkfox-multimodal-product-similarity
An image-comparison tool that groups products whose main photos look alike, using features such as appearance, colour, composition, and material.