agentleFS
Sign inStart free
runxhqrunxhq/runx/skills/marketplace-invoke/SKILL.md

marketplace-invoke

Skill97 starsChanged 33 days agoApache-2.0View on GitHub

Invoke one exact marketplace-listed vendor resource through an approved settlement adapter and return receipt-backed provider readback.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill through a paid endpoint listing after marketplace discovery.

    line 37
  2. Distinctive:

    Stop if the family is unsupported, terms drift, the provider reports terminal failure, or the inner receipt cannot be verified from hosted …

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Marketplace Invoke

The caller supplies only the provider-neutral vendor request body and bounded transport preferences. Paid-listing admission injects the immutable offer and the run idempotency identity. The selected settlement adapter derives its own protocol envelope, authority attenuation, endpoint, amount, and parent binding; neither callers nor product facades may forge those fields.

marketplace-invoke is the buyer-facing marketplace skill called through the existing runx skill surface. Paid listing admission injects the immutable listing, vendor, exact endpoint, vendor price, demand-side fee, settlement family, and expected receipt class into one Runx run before its quote is fingerprinted. Hosted receipt custody verifies the returned inner receipt and seals the outer execution as a mediated composite receipt.

The skill is rail-neutral at its boundary. settlement_family selects an explicit adapter branch; x402 is the first implementation. Stripe and future rails add sibling branches while preserving the listing, vendor, authority, result, and composite-receipt semantics. Provider SDKs, wallets, credentials, settlement recovery, and database state remain in Runx Hosted.

Composes

<!-- Generated from the native execution closure; run pnpm core-skills:composes:generate. -->
  • x402-pay#readback
  • x402-pay#settle

Operator guide

Use this skill through a paid endpoint listing after marketplace discovery. Supply the exact vendor invocation body and optional bounded transport limits. marketplace_offer and idempotency_seed are reserved for hosted admission; caller-supplied values are refused. Keep large inputs behind artifact references.

The x402 branch delegates settlement and each read observation to x402-pay. marketplace-invoke emits the existing current-V1 external-job schedule intent after settlement, then its package-owned vendor-readback runner performs one read per durable claim until the vendor receipt is ready or the bounded deadline ends. This skill adds no wrapper approval: the delegated settlement is the one waiting-resolution gate for vendor spend. The skill never interprets wallet material.

Stop if the family is unsupported, terms drift, the provider reports terminal failure, or the inner receipt cannot be verified from hosted custody. An incomplete readback remains durable waiting state; an uncertain settlement keeps the same hosted run and payment identity.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free