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 epistemedeus/x402-url-extractor --skill route-lock-receiptgit clone --depth 1 https://github.com/epistemedeus/x402-url-extractorWrote 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/epistemedeus/x402-url-extractor/route-lock-receipt)<a href="https://agentmods.dev/skills/epistemedeus/x402-url-extractor/route-lock-receipt"><img src="https://agentmods.dev/badge/skills/epistemedeus/x402-url-extractor/route-lock-receipt/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/epistemedeus/x402-url-extractor/route-lock-receipt"><img src="https://agentmods.dev/badge/skills/epistemedeus/x402-url-extractor/route-lock-receipt.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 | $0.00022 | $0.00596 |
| Opus 5.5 | $0.00009 | $0.00238 |
| Sonnet 5.5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
route-lock-receipt 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 14d 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.
What it actually says
Route lock receipt
Use this when a caller needs one unpaid merchant challenge mapped into a route-lock receipt that a later process can read. A supplied decision file is not this entry. The executable is scripts/lock-and-capture.mjs version 0.1.0. It calls the unchanged route-release-decision 0.1.0 scripts scripts/run-task.mjs, scripts/http-boundary.mjs, scripts/map-challenge.mjs, scripts/package-cache.mjs, scripts/read-receipt.mjs, scripts/receipt.mjs, and scripts/time.mjs, with pins in references/pins.json and identity in references/manifest.json. The license is references/LICENSE. The acquisition note is references/SOURCE-NOTICE.txt.
Map one unpaid challenge. The clock on that process is the receipt time:
node scripts/lock-and-capture.mjs map --url https://agents.samedaydesk.com/extract?url=https%3A%2F%2Fexample.com --cache DIR --out receipt.json
A second process reads that receipt at its own clock. newAuthority stays denied. An expired, stale, changed-recipient, or malformed observation exits 3:
node scripts/lock-and-capture.mjs continue --receipt receipt.json --out continuation.json
--now sets the second process clock for a check. It does not create authority.
The script pins route-lock 0.1.0 and release-gate 0.1.4 by sha256. It does not rewrite those archives. It sends no payment header. It does not follow redirects. A private address or local name is refused before a connection. Other names are resolved, and a private answer is refused, but the later connection is not pinned to that answer. confinementClaim is none. A body larger than 1 MiB is rejected while it is still streaming. A cached tree runs only when every archive member is a regular file with the pinned bytes. A tampered, partial, or symlinked cache is left in place and is not the process that runs.
--pay, --settle, --publish, --sign, --reserve, --register, --deploy, --submit, --authenticate, and --owner-pay are refused. A lockable diagnostic is not permission to pay.
What ships with it
13 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.
- LICENSE 1.0 KB
- references/LICENSE 1.0 KB
- references/manifest.json 1.3 KB
- references/pins.json 3.3 KB
- references/SOURCE-NOTICE.txt 1.1 KB
- scripts/http-boundary.mjs 8.4 KB runs code
- scripts/lock-and-capture.mjs 4.3 KB runs code
- scripts/map-challenge.mjs 20 KB runs code
- scripts/package-cache.mjs 5.6 KB runs code
- scripts/read-receipt.mjs 2.2 KB runs code
- scripts/receipt.mjs 10 KB runs code
- scripts/run-task.mjs 23 KB runs code
- scripts/time.mjs 2.4 KB runs code
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.
- 14d ago First seen · 30 lines · 22 tokens per session scan A 225248d6d4de
route-lock-receipt is a skill published in the GitHub repository epistemedeus/x402-url-extractor (1 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 596 once invoked, about $0.0001 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 2026-10-02.
Other skills, from other repositories
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…
scvd-personal-shopper
Help a personal-agent user choose and buy a signed good from SCVD: read the current menu, obtain a free quote, set up a compatible wallet if needed, obtain funding and purchase approval, and verify the receipt. Use for a requested SCVD purchase or first x402 purchase; never buy just because this skill is installed.
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…
merchant-context
Resolve sourced merchant facts before relying on them or starting merchant actions.
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.
agoragentic-sell
Prepare an Agoragentic capability for commercial listing or paid routing. Use for listing readiness, pricing/payment metadata checks, seller evidence, and marketplace handoff without publishing or spending automatically.