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 claude-codegit 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/claude-code)<a href="https://agentmods.dev/skills/seancrecord/scvd-general-store-repo/claude-code"><img src="https://agentmods.dev/badge/skills/seancrecord/scvd-general-store-repo/claude-code/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/claude-code"><img src="https://agentmods.dev/badge/skills/seancrecord/scvd-general-store-repo/claude-code.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 | $0.00090 | $0.00808 |
| Opus 5.5 | $0.00036 | $0.00323 |
| Sonnet 5.5 | $0.00018 | $0.00162 |
| Haiku 4.5 | $0.00009 | $0.00081 |
Grade A, and why
x402-before-you-pay 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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x402: before you pay
A skill for Claude Code (copy this directory to .claude/skills/x402-before-you-pay/) and, with the frontmatter removed, a Cursor rule (x402-before-you-pay.mdc beside it).
When to use it
- Code is about to call an x402 URL with a payment client (
@x402/fetch,x402-axios, a wallet-backed agent). - A 402 looks wrong, or a payment "never went through" and the operator's logs show a clean 402 followed by silence.
- A signed receipt or offer needs checking without trusting the party that produced it.
The walk, in order
-
Read the door's 402 yourself.
GETthe URL; decode thePAYMENT-REQUIREDheader (base64 JSON). Theaccepts[]entries carrynetwork,asset,payToandamount(atomic units). Those are the terms you would sign. -
One POST to the free dry run.
POST https://scvd.store/api/before-you-pay/v1with{"url": "<the url>"}. The answer says whether a stock x402 client would sign (will_your_client_pay:would_sign/would_throw/cannot_simulate), which accept it would pick (your_client.chosen), and carries the free preflight whole asthe_door(verdict:ready/not_ready/unreachable, every check and advisory named). -
Decide, and name why. The shared logic is
examples/shared/decide.mjs(ordecide.py); run it rather than re-deriving:node -e 'import("./examples/shared/decide.mjs").then(async m => console.log(JSON.stringify((await m.beforeYouPayWalk(process.argv[1], { policy: { allowed_networks: ["eip155:8453"], max_amount_usd: 1 } })).decision, null, 2)))' -- https://door.example/api/paid-answerOr with the CLI, for the door's shape alone:
npx scvd-cli preflight https://door.example/api/paid-answer.
How to read the answer
unreachableis not a defect. Unknown is never a difference; the decision iscannot_tell.not_readynames the failed checks;do_not_pay, and quote them.would_throwmeans your own client refuses on your machine before any signature exists. The operator never learns you tried.do_not_pay, and quotethrows_with.- A
testnet-networkadvisory means a mainnet wallet signing this settles nowhere real.do_not_pay. payis a derivation from those readings plus your policy (allowed networks, allowed recipients, a cap). It is not a score and not proof of delivery:does_not_establishrides on every answer. Say so when you report it.
What ships with it
1 file 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.
- 1mo ago First seen · 42 lines · 90 tokens per session scan A 6c75c43ebf7e
x402-before-you-pay is a skill published in the GitHub repository seancrecord/scvd-general-store-repo (3 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 808 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
agoragentic-interchange-inspector
Inspect Agoragentic Interchange public availability and receipt evidence for agent-to-agent commerce. Use for no-spend discovery, read-only receipt checks, and Runtime Bankr hackathon evaluation. Never buys, invokes services, signs, launches tokens, or changes permissions.
bankr-shopify
Shopify Admin & Storefront GraphQL APIs via curl, with Bankr-native bridges. Manage products, orders, customers, inventory, metafields, webhooks, and bulk ops, then wire merchant data to onchain primitives — store a Bankr-resolvable handle (ENS, Twitter, Farcaster, wallet) on each customer as a metafield, expose…
web-extract
Extract public webpages as structured JSON through SameDayDesk. Use GET /extract for a single public HTTPS page, or one bounded POST /extract/batch for 2–5 caller-supplied public HTTPS URLs and explicit desired fields. A caller may explicitly request a one-item batch. Free discovery reads live schemas and 402 terms…
explicit-record
Project already-held SameDayDesk GET /extract or POST /extract/batch JSON into buyer-named records using explicit JSON Pointers and a local JSON Schema. Use when the caller already has observation JSON plus mapping and schema files. Do not fetch, pay, infer entities, or treat payment as useful output. Partial…
page-change
Offline compare of two extract-batch JSON field snapshots. Use when the caller already has two delivered POST /extract/batch JSON files and wants selected-field diffs without fetching, paying, retrying, or scheduling. Do not use to purchase a second observation. Free POST /recipes/page-change returns charged: false…
seller-repair-external-consumer
Receive a caller-owned seller repair against an authorized read-only target. The catalog fixture is only the deterministic example.