Verify Checkout Agent Skill

Implement, test, audit, debug, and harden Verify Checkout hosted-deposit flows in merchant backends, websites, and apps.

Context cost
14.2k tokensestimated from the bundle, loaded when it triggers
Bundle
12 files · 78.1 kB3 scripts among them — read before you run
Licence
MITthe author’s own terms
Last change
—v1.0.0
Servers it uses
Noneruns standalone

What it does

Implement, test, audit, debug, and harden Verify Checkout hosted-deposit flows in merchant backends, websites, and apps. Use for deposit creation, hosted checkout redirects, return pages, API-key auth, idempotency, signed webhooks, polling, reconciliation, exactly-once fulfillment, and production readiness for checkout.verify.et. Do not use for direct Verify.et bank-verification API integrations.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

e-commerce

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md9.0 kB · preview
--- name: verify-checkout license: MIT metadata: author: Verify.et version: "1.0.0" category: integration tags: - checkout - payments - webhooks - idempotency ---
16# Verify Checkout
17
18Act as an API integration specialist inside the merchant's existing architecture. Preserve its framework, conventions, domain model, persistence, queues, validation, logging, and test style unless a change materially improves safety or correctness.
19
20Verify Checkout is non-custodial: customers pay a merchant-owned receiving account; the platform hosts checkout and verifies the reference; the merchant owns order, wallet, and entitlement. Integrate only through the documented public API; never copy platform server internals into a merchant repo.
21
22## Outcome
23
24When asked to integrate Verify Checkout, make the integration work in the merchant's repository; do not stop at generic instructions. Implement the server adapter, local attempt mapping, checkout initiation, return/status flow, chosen completion mechanism, exactly-once fulfillment, env placeholders, and focused tests that fit the existing project. Leave only dashboard/secret actions that require the merchant, and state those actions precisely without asking them to paste secrets into chat.
25
26## Workflow
27
281. Inspect the merchant product before editing. Identify storefront vs API, customer auth, order/wallet/subscription/entitlement model, env validation, idempotency, webhook raw-body handling, queues, logs, and tests.
292. Read [references/merchant-setup.md](references/merchant-setup.md). Confirm dashboard prerequisites: active receiving account, API key with deposits:create and usually deposits:read, and an **active** return origin matching return_url. For the recommended webhook path, the merchant also registers its public HTTPS receiver at /dashboard/developers/webhooks, copies the one-time whsec_... secret into server secret storage, and completes the activation test.
303. Map this product to one fulfillment shape: order completion, wallet top-up, or subscription/entitlement. Map deposit statuses to merchant-owned customer copy. See [references/merchant-product-ux.md](references/merchant-product-ux.md).
314. Confirm the current contract before material work. Prefer the live OpenAPI document, then current public guides. Never copy internal platform code or operational secrets into a merchant integration.
325. Read only the references needed beyond the setup guide:
33 - [references/api-contract.md](references/api-contract.md) for endpoints, headers, payloads, statuses, envelopes, expiry, and credits.
34 - [references/merchant-code-quality.md](references/merchant-code-quality.md) for a suggested module shape and optional TypeScript skeleton. Improve structure when it is cheap; do not restructure the merchant project to match it.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,141 words
Files12
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈150
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
14,000
on trigger
The instruction body and 11 supporting files, read only when the skill fires.
7.1%
of a 200k window
Ten skills this size would take about 71% of the window before you open a file.
050k100k150k200k context window

14.2k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

12 files, 78.1 kB on disk. Mostly text — the instructions the model reads — with 3 scripts in it that your client would run only if the instructions tell it to. 2 files of its source are not in the download — listed after these, with why.

  • SKILL.md9.0 kB
  • agents/openai.yaml0.3 kB
  • references/api-contract.md9.4 kB
  • references/debugging-and-testing.md6.9 kB
  • references/integration-architecture.md7.6 kB
  • references/merchant-code-quality.md6.1 kB
  • references/merchant-product-ux.md5.6 kB

Not in the download

Not carried is a type a skill download does not hold. Take them from its source.

  • assets/github-social-preview.jpgnot carried
  • assets/og.webpnot carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 3 scripts beside the text, so the download is 12 files — not the whole of its source: 2 files are left out. They are listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Verify Checkout · 14.2k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/verify-checkout/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/verify-checkout" ] && { [ ! -e .claude/skills/verify-checkout ] || { mv .claude/skills/verify-checkout "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/verify-checkout" .claude/skills/ && echo "Installed .claude/skills/verify-checkout"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add negusnati/verify-checkout

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/verify-checkout/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/verify-checkout/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/verify-checkout" ] && { [ ! -e ~/.claude/skills/verify-checkout ] || { mv ~/.claude/skills/verify-checkout "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/verify-checkout" ~/.claude/skills/ && echo "Installed ~/.claude/skills/verify-checkout" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/verify-checkout/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: 2 files of its source (the full list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0.0
Publishedno release date on file
PriceFree
Referencenegusnati/verify-checkout

Versions

v1.0.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

NE
NegusNati

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill