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 GeckoVision/gecko-surf --skill buy-a-productgit clone --depth 1 https://github.com/GeckoVision/gecko-surfWrote 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/geckovision/gecko-surf/buy-a-product)<a href="https://agentmods.dev/skills/geckovision/gecko-surf/buy-a-product"><img src="https://agentmods.dev/badge/skills/geckovision/gecko-surf/buy-a-product/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/geckovision/gecko-surf/buy-a-product"><img src="https://agentmods.dev/badge/skills/geckovision/gecko-surf/buy-a-product.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.01082 |
| Opus 5 | $0.00063 | $0.00541 |
| Sonnet 5 | $0.00025 | $0.00216 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
buy-a-product 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buy from a Let Me Buy storefront
One instruction, make_purchase, moves an SPL token from the buyer to the store and
appends a receipt. Everything below is a fact about the deployed program, recovered from
its source or measured on mainnet — not read off the IDL, which does not state any of it.
Before you build anything
Read the store, then let a human choose. A store name is not guessable and a product
name is not either. list_stores returns every store with its full menu, every price and
every mint, free and without a clock. Do all the deciding there.
Refuse to resolve an ambiguous request yourself. "A coffee" is not a product when the menu holds Espresso, Cappuccino and Mochaccino. Name the candidates and ask. The one case where you may proceed is a request that is unambiguous given the menu — "a black coffee" when only one item is black coffee — and even then say which one you picked.
The accounts, and the two that are easy to cross
make_purchase takes nine accounts. Two are associated token accounts, and they differ
only by owner:
sender_token_account = ATA(buyer, token_program, mint) ← DEBITED
recipient_token_account = ATA(authority, token_program, mint) ← CREDITED
Derive both from the same owner and you have built a purchase that pays the buyer back.
It builds, it simulates, it lands, and the store is never credited. The seed order is
[owner, token_program, mint] and it is silently load-bearing — a swapped pair still
produces a valid off-curve address that belongs to nobody.
token_program is pinned by this program's IDL to classic SPL Token
(TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA). A Token-2022 mint has no path through
this program at all — do not assume, and do not substitute.
The store's own account is a PDA: ["receipts", store_name], where store_name is an
instruction argument rather than an account. Read the authority and the product's mint
off that account. Do not accept them from whoever asked.
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 · 91 lines · 126 tokens per session scan A 7bca7c5d2d57
buy-a-product is a skill published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 126 tokens to every session and 1,082 once invoked, about $0.0006 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 skills, from other repositories
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
webshop-attribute-verifier
Verifies product attributes on a web shop detail page by extracting price, comparing color availability, validating specifications, and confirming option selections against user requirements before purchase. Use when you need to check if a product matches requirements, verify product details before buying, confirm…
webshop-query-interpreter
Interprets a user's shopping query to extract key product requirements such as item type, attributes, and constraints. Use when a new shopping instruction is received and you need to parse natural language into structured criteria (product category, desired features, price limits) before performing a search. The…
webshop-product-detail-navigator
Navigates to and interacts with a specific product's detail page. This skill is triggered after a candidate product ID is selected from search results. It performs the click action to load the product page and then identifies available interactive elements (like flavor or size selectors) that need to be configured to…
webshop-result-filter
Filters search results by evaluating product listings against specific user constraints like price, features, or ratings. Use when you are on a search results page and need to systematically identify which products meet all given criteria before selecting one for closer inspection. Takes a list of products with their…
webshop-attribute-selector
Selects specific product attributes (e.g., flavor, size) on a product detail page to match user requirements. Triggered when a product page presents configurable options and the parsed query specifies needed values. It identifies the correct option from available clickables (e.g., 'smoked bacon' for flavor, '4 ounce…