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 confirm-a-deliverygit 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/confirm-a-delivery)<a href="https://agentmods.dev/skills/geckovision/gecko-surf/confirm-a-delivery"><img src="https://agentmods.dev/badge/skills/geckovision/gecko-surf/confirm-a-delivery/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/confirm-a-delivery"><img src="https://agentmods.dev/badge/skills/geckovision/gecko-surf/confirm-a-delivery.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 | $0.00112 | $0.00904 |
| Opus 5 | $0.00056 | $0.00452 |
| Sonnet 5 | $0.00022 | $0.00181 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
confirm-a-delivery 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confirm a delivery on a Let Me Buy storefront
mark_as_delivered takes two accounts — the store's receipts PDA and the authority — plus
a receipt id. It is signed by the store, never the buyer.
The argument-name trap
The receipts PDA derives from ["receipts", store_name]. But this instruction's own
arguments are named _store_name and receipt_id — with a leading underscore, because
Rust marks an unused parameter that way and Anchor copies the name straight into the IDL.
So the seed points at an argument name that does not exist in the instruction that uses
it. Bind the store name to _store_name on the wire and to store_name in the seed. A
tool that passes the IDL's seed path through verbatim derives nothing; a tool that renames
the argument to match the seed sends a field the program does not have.
This is the join an IDL loses, and it is why the recipe is carried separately.
The trap that loses orders, and it is silent
The receipts vec is capped at 20 and the account never reallocs — it is fixed at 3,681
bytes. At the cap, make_purchase calls receipts.remove(0): the oldest receipt is
evicted with no error, no event and no log.
One measured store has 125 purchases and holds 20. 105 receipts are gone from chain.
The consequence for this instruction is the part to plan around:
mark_as_deliveredon an evicted id SUCCEEDS AND DOES NOTHING. It scans the vec, finds nothing, and returnsOk.
So a venue with more than 20 open orders loses them from the delivery queue invisibly, and
the program will keep telling you the delivery worked. Never treat a successful
mark_as_delivered as proof the order was closed — read the receipt back and check
was_delivered actually flipped.
If you are building a delivery queue on this program, the queue depth is 20. Hold your own record of anything beyond it; the chain will not.
Finding the receipt
Read the store's receipts account and match on the buyer, the product and the table number. The vec is sequential and there is no index, so a walk reads every row — every other row belongs to a real customer of a real storefront. Compare and discard; do not carry other people's rows anywhere.
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 · 78 lines · 112 tokens per session scan A 4bae86879303
confirm-a-delivery is a skill published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 112 tokens to every session and 904 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…