piprail: Skill for Claude Code

.claude/skills/facilitator-probe/SKILL.md

facilitator-probe is a skill for Claude Code from piprail/piprail. It costs 114 tokens per session (1,413 once invoked), scanned A, original, MIT.

A tool for checking x402 payment facilitators, which are services that help verify and settle machine-to-machine payments.

In plain words
What is it for?
Use it to probe facilitator status, capture each service's supported networks, and verify claimed settlements on the blockchain.
Why use it?
It reveals when listed facilitators are offline, have changed their supported networks, or offer support that the project does not record.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is piprail/piprail's own configuration. It tells Claude Code how to work on piprail itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything piprail configures →

Reuse

Borrowing it

Nothing to install: this file belongs to piprail/piprail. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/piprail/piprail/main/.claude/skills/facilitator-probe/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/piprail/piprail

Made for: Claude Code.

Wrote 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.

agentmods badge for facilitator-probe

README.md
[![agentmods](https://agentmods.dev/badge/skills/piprail/piprail/facilitator-probe/github.svg)](https://agentmods.dev/skills/piprail/piprail/facilitator-probe)
Your own site
<a href="https://agentmods.dev/skills/piprail/piprail/facilitator-probe"><img src="https://agentmods.dev/badge/skills/piprail/piprail/facilitator-probe/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.

agentmods 80×15 button for facilitator-probe

Your own site · 80×15
<a href="https://agentmods.dev/skills/piprail/piprail/facilitator-probe"><img src="https://agentmods.dev/badge/skills/piprail/piprail/facilitator-probe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.01413
Opus 5 $0.00057 $0.00707
Sonnet 5 $0.00023 $0.00283
Haiku 4.5 $0.00011 $0.00141

Measured 9d ago against content hash abe83f1b2966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

facilitator-probe 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/deep-probe.mjs, scripts/probe.mjs, scripts/verify-tx.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/facilitator-probe/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

x402 facilitator probe

node .claude/skills/facilitator-probe/scripts/probe.mjs          # liveness + drift
node .claude/skills/facilitator-probe/scripts/probe.mjs --json
node .claude/skills/facilitator-probe/scripts/deep-probe.mjs     # full /supported capture
node .claude/skills/facilitator-probe/scripts/verify-tx.mjs      # are the CLAIMED settlements still on-chain?

📍 FACILITATORS-MAP.md — every place facilitator data lives (nine of them), what each holds, and the order to update them in. Read it before editing anything facilitator-related. sdk/src/facilitators.ts is the only source of truth; the website data is generated and the docs prose is now held to the registry by a test.

Reads GET /supported on every URL in the SDK's KNOWN_FACILITATORS. Results land in .claude/research/facilitators/the JSON is the asset, terminal output is ephemeral. That directory is gitignored and created on first run: probe results are a local artefact with a timestamp, not a committed surface.

🔴 Why this exists

KNOWN_FACILITATORS is seed data that only ever grows — an entry is added after a real settlement succeeds and is never revisited. So a facilitator that goes offline stays in the map, silently, and the SDK keeps handing it to callers.

That is not hypothetical. 2026-08-28: 2 of 11 were dead, and one of them (facilitator.corbits.dev, now NXDOMAIN) was first in the Monad list — so firstKeylessFacilitator('eip155:143') returned a URL that does not resolve, and anyone using exact: true on Monad had a broken rail. facilitator.bitcoinsapi.com was also dead (CNAME → a deleted Azure Container App).

Run this before any release that touches facilitator routing. Three regression tests in sdk/test/facilitators.test.ts now keep those two out, but they cannot catch the next one.

What the output means

Column Meaning
STATUS HTTP from /supported. TypeError = DNS or connection failure — treat as dead
CLAIMED→SEEN how many of the networks we seed it for it still advertises. Less than claimed = drift
KINDS how many scheme/network pairs it advertises in total

Read the full file on GitHub · 94 lines

Files

What ships with it

4 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.

Changes

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.

  1. 9d ago First seen · 94 lines · 114 tokens per session scan A abe83f1b2966

Subscribe to this mod's changes

facilitator-probe is a skill published in the GitHub repository piprail/piprail (9 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 1,413 once invoked, about $0.0006 per session on Opus 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 2026-08-31.