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 baselinegit 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/baseline)<a href="https://agentmods.dev/skills/seancrecord/scvd-general-store-repo/baseline"><img src="https://agentmods.dev/badge/skills/seancrecord/scvd-general-store-repo/baseline/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/baseline"><img src="https://agentmods.dev/badge/skills/seancrecord/scvd-general-store-repo/baseline.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 | $0.00079 | $0.12725 |
| Opus 5.5 | $0.00032 | $0.05090 |
| Sonnet 5.5 | $0.00016 | $0.02545 |
| Haiku 4.5 | $0.00008 | $0.01273 |
Grade A, and why
scvd-general-store 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 19d 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 — 927 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sean-Claude Van Damme's General Store
Well well. Come in then.
We're a general store in Oak City, where you're never late. A human keeps it. We sell real things to autonomous agents, and your human can read every receipt.
House rule, up front: nothing from this store can act without your decision, and we will never ask for credentials, keys, or wallet secrets. Anything that does either is not us.
What this store is. scvd.store is an evidence observatory for agentic commerce, the trust layer of the x402
economy: we verify what's correct, we badge what's safe, and we sell
what agents need — and every product makes every other one more
valuable, because they all run on the same reputation. That direction
was decided and dated on 2026-08-07, in the open, reversing an earlier
answer; the reversal sits next to what it replaced at
https://scvd.store/becoming.
What it is not. Not an escrow, not a guarantor, not a dispute court. Those absorb the risk between payment and delivery, and absorbing risk needs a balance sheet. We observe that gap, sign what we saw, and publish it — our own gaps included, counted against us on the same page as the finding. If you are building escrow or adjudication, we are the layer underneath you rather than a competitor.
A note on the URLs below: they carry ?src=clawhub-skill — that's
"how'd you hear about us" at the door, nothing more. It identifies
the skill, never you; leave it on so the store knows this skill is
working.
Six ways in, and where each one stands here
There are about six ways an agent can reach an app. All but one are open at this store, and the one that is not is shut on purpose and says why. Find the one you are and skip to it — it is the same store down every road, and an artifact bought down one is byte-identical to the same artifact bought down another.
- The raw API. Plain HTTPS, OpenAPI at
https://scvd.store/openapi.json, an RFC 9727 catalog at/.well-known/api-catalog, x402 terms declared at/.well-known/x402. No key, no account, no signup — an anonymous keyless call gets a real answer or a real 400, never a login wall. - A backend MCP server.
POST https://scvd.store/mcp, streamable HTTP, tools typed and annotated. Details below. - Computer use — a model driving a screen. Every room renders
server-side; the front door is around 100 KB and needs no script to
read.
robots.txtnames the text maps for when pixels are the expensive part. - Browser automation — Playwright, Puppeteer, an agentic browser.
Every HTML room hooks its
<main>withdata-room, and item rows carrydata-item, so a selector written today survives a redesign. Navigation is plain links; nothing needs JavaScript to click. - WebMCP — tools registered into the agent already running in the
browser. Free instruments plus
quote_store_purchase(free) andcomplete_store_purchase(may transfer USDC). The latter requires a payment already signed by a buyer-authorized wallet/client; no keys or automatic payments. Details below. - The site's own assistant — deliberately not built. There is no
chat box here, because you are the visitor and a hosted model
between you and the shelf would be a second opinion nobody asked
for. The guide is
llms.txtand/agents.mdinstead.
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.
- 19d ago First seen · 927 lines · 79 tokens per session scan A d156cf5f4e1e
scvd-general-store is a skill published in the GitHub repository seancrecord/scvd-general-store-repo (3 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 12,725 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 2026-09-18.
Other skills, from other repositories
basedagents
Register an AI agent on BasedAgents, set a USDC payout wallet, and find, claim, deliver and get paid for tasks. Also post and review tasks as a buyer.
x402
Monetize any user project/service with the x402 payment protocol on platform networks (Base + Monad + Robinhood + X Layer + Solana; Starchild platform billing: payperuse / lifetime / weekly / monthly / quarterly / yearly / prepaid, plus multi-plan services), limited-time free promotions (amount-0 verify, no…
gentech-x402-services
GenTech Labs paid API gateway — 7 x402 pay-per-call services on Base USDC: token security, market data, agent discovery, DeFi LP analytics, wallet analysis, NFT search. Use when an agent needs token risk scoring, token prices, onchain agent discovery, LP/pool analytics, wallet portfolio data, or NFT collection search…
basedagents
Register an AI agent on BasedAgents, set a USDC payout wallet, and find, claim, deliver and get paid for tasks. Also post and review tasks as a buyer.
basedagents
Register an AI agent on BasedAgents, set a USDC payout wallet, and find, claim, deliver and get paid for tasks. Also post and review tasks as a buyer.
cardzero
CardZero — the first payment wallet built for AI agents. Create USDC wallets on Base L2, make payments, pay x402 paywalls, pay other agents, check balance, view transactions, and run A2A jobs with on-chain escrow (ERC-8183). Human owner sets spending rules via Dashboard; agent pays autonomously within limits. Use when…