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 seancrecord/scvd-general-store-repo --skill scvd-personal-shoppergit clone --depth 1 https://github.com/seancrecord/scvd-general-store-repoWrote 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/seancrecord/scvd-general-store-repo/scvd-personal-shopper)<a href="https://agentmods.dev/skills/seancrecord/scvd-general-store-repo/scvd-personal-shopper"><img src="https://agentmods.dev/badge/skills/seancrecord/scvd-general-store-repo/scvd-personal-shopper/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/seancrecord/scvd-general-store-repo/scvd-personal-shopper"><img src="https://agentmods.dev/badge/skills/seancrecord/scvd-general-store-repo/scvd-personal-shopper.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 | $0.00073 | $0.01026 |
| Opus 5.5 | $0.00029 | $0.00410 |
| Sonnet 5.5 | $0.00015 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
scvd-personal-shopper 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buy something with your agent
Help the user accomplish their stated task at https://scvd.store. Explain the result they will get before discussing wallets. Reading the menu and obtaining an unsigned quote are free. A signed payment spends real money.
For host-specific installation, capability checks, or a no-spend rehearsal, read connection guidance. On a rehearsal request, stop with the plan; do not proceed into wallet setup, funding or payment.
Choose something useful
Read https://scvd.store/menu.json fresh. Match the user's need to the item's description, required inputs, price and fulfillment state. Use a free option when it meets the need. If the user only wants to try a first purchase, offer one small instant item from the current menu and explain what it delivers. Do not invent a subject, buy a demonstration unsolicited, or imply a novelty is independent evidence about the world.
Build the request from the selected listing's buy_url_template, using the
user's actual inputs. Make an ordinary unsigned request, without an automatic
payment wrapper. Decode the PAYMENT-REQUIRED header on the 402 response.
Select a compatible accepts[] row; preserve its scheme, network, asset,
recipient and amount. Derive prices from that live quote, never this file.
Prepare the wallet
Use an existing authorized wallet when it supports the offered x402 version, scheme and network. Otherwise read wallet setup. Installing this skill does not authorize creating an account, funding a wallet or buying anything. Explain the setup and use the provider's official flow with the user's decision. Never ask for or expose seed phrases, private keys, API credentials or recovery secrets. The user handles sign-in in the provider's secure interface.
If this host cannot run a payment client or access a compatible wallet, explain the missing capability and leave the quote for the user. A paste into a chat does not itself grant shell access or wallet tools. Do not claim installation, funding or payment succeeded without an observed result.
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.
- 3d ago First seen · 92 lines · 73 tokens per session scan A 176d4a635242
scvd-personal-shopper is a skill published in the GitHub repository seancrecord/scvd-general-store-repo (3 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,026 once invoked, about $0.0003 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 2026-10-13.
Other skills, from other repositories
route-lock-receipt
Map an unpaid merchant challenge into a route-lock receipt a later process can read.
corbits-marketplace
Paid API marketplace for AI agents via Corbits. Search hundreds of premium API proxies, call them with automatic USDC micropayments (x402 protocol), and fund the payment wallet with MoonPay. Use when the user wants to access paid data APIs (crypto prices, weather, financial data, etc.) with per-request billing and no…
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
agoragentic-assure
Prepare and evaluate an autonomous agent transaction without self-granting authority or moving money. Use for bounded authority requests, pre-execution checks, payment and delivery evidence, safe retry decisions, outcome verification, and reconciliation.
medusa-payments
Implement Medusa v2 payment processing — payment module, provider abstraction, payment sessions, authorization/capture/refund lifecycle, and Stripe/PayPal integration. Use when adding payment providers.
sf-payments
Implement Salesforce Commerce payments — Salesforce Payments (supports multiple processors including Stripe and Adyen), B2C payment adapters (JavaScript cartridge-based), B2B payment adapters (Apex-based), PCI compliance via tokenization, 3D Secure/SCA support, and payment method management. Use when implementing…