System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.
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 asgeirtj/system_prompts_leaks --skill shopifygit clone --depth 1 https://github.com/asgeirtj/system_prompts_leaksWrote 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/asgeirtj/system_prompts_leaks/shopify)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/shopify"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/shopify/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/asgeirtj/system_prompts_leaks/shopify"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/shopify.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 | $0.00159 | $0.01778 |
| Opus 5.5 | $0.00064 | $0.00711 |
| Sonnet 5.5 | $0.00032 | $0.00356 |
| Haiku 4.5 | $0.00016 | $0.00178 |
Grade A, and why
shopify 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shopify
The installed shopify command wraps Shopify's official MCP server. It is not
the Shopify CLI from npm; the only verbs are the four below. Tool names and
schemas come from shopify list-tools, never from memory — other Shopify
connectors expose tools this one does not.
shopify status
shopify authorize-url
shopify list-tools
shopify call-tool --name <tool-name> --arguments-json '<JSON object>'
Connecting
shopify status. If a store is connected, go straight to work.- Otherwise
shopify authorize-urland share only the returnedconnect_urlwith the user. Nothing else in that response is for them. - When they say they're done,
shopify status, thencall-tool --name get-shop-infoto confirm which store is connected.
Before a store is connected, search_docs_chunks (searches https://shopify.dev),
validate_graphql_codeblocks, find-mock-shop-catalogs, generate-domain-names,
and generate-business-names work. get-storefront-generation is usable only
with a generationUUID created by Shopify's storefront-generation widget;
claim-storefront-preview is a widget callback and must not be called directly.
Every other tool, including catalog import, needs a store. Do not ask someone
to connect merely to explore sample catalogs, names, domains, or documentation.
Sample catalogs
When someone is starting a store, offer relevant mock.shop sample catalogs before asking them to connect:
- Call
find-mock-shop-catalogswith what they sell, in their own words. If they have not said, ask that one question first. - Present the best matches with their descriptions, product and collection
counts, currency, and
storefrontUrl. Clearly label each link as the source sample storefront, then ask which catalog they want. - Once connected, confirm before calling
import-mock-shop-catalogwith the selectedsubdomain. - Verify the destination records with
search_productsandsearch_collections, then report created, reused, skipped, unpublished, or partial results and any currency mismatch.
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 · 144 lines · 159 tokens per session scan A 076a908c1a20
shopify is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,759 stars, last pushed yesterday), licensed CC0-1.0. It adds 159 tokens to every session and 1,778 once invoked, about $0.0006 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 2026-10-05.
Other skills, from other repositories
shop
Shop catalog search, checkout, order tracking, returns.
shopify
Query Shopify Admin/Storefront GraphQL APIs via curl.
stripe-link-cli
Agent payments via Stripe Link — cards, SPT, approvals.
product-price-monitor
Watch product, flight, or listing prices; alert on target.
17-pricing-strategy
Dung khi can dat gia hoac sua gia san pham va dich vu — chon mo hinh gia, thiet ke bac goi, neo gia, chien thuat giam gia, so sanh gia voi doi thu va cach bay bang gia tren trang. Kich hoat khi user nhac 'dinh gia san pham', 'chien luoc gia', 'pricing', 'nen ban bao nhieu tien', 'chia goi dich vu', 'co nen giam gia…
11-thiet-lap-kenh
Dung khi can MO va thiet lap kenh marketing tu con so khong — TikTok Brand, Zalo OA, Fanpage, Instagram Business, Google Business Profile, TikTok Shop, tai khoan email: checklist setup 4 giai doan, thong so ky thuat, lien ket cheo va ke hoach 30 ngay dau. Kich hoat khi user nhac 'thiet lap kenh', 'tao fanpage moi'…