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 agentmods add skills/lonniev/tollbooth-sample/bootstrap-dpyc-operatornpx skills add lonniev/tollbooth-sample --skill bootstrap-dpyc-operatorgit clone --depth 1 https://github.com/lonniev/tollbooth-sampleWrote 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/lonniev/tollbooth-sample/bootstrap-dpyc-operator)<a href="https://agentmods.dev/skills/lonniev/tollbooth-sample/bootstrap-dpyc-operator"><img src="https://agentmods.dev/badge/skills/lonniev/tollbooth-sample/bootstrap-dpyc-operator.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.02573 |
| Opus 5 | $0.00051 | $0.01287 |
| Sonnet 5 | $0.00020 | $0.00515 |
| Haiku 4.5 | $0.00010 | $0.00257 |
Grade A, and why
bootstrap-dpyc-operator 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 5d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap a DPYC Tollbooth Operator MCP
This skill scaffolds a new DPYC Operator MCP server that wraps a user's existing
service. The operator sells its tools for Bitcoin Lightning micropayments: patrons pre-fund a
satoshi balance (identified by a Nostr npub, no KYC), and each tool call debits credits at a
price the operator sets dynamically. All the payment, identity, vault, and audit machinery
comes from the tollbooth-dpyc SDK — the user only supplies domain logic.
The canonical template is the tollbooth-sample repo. This skill always fetches it live so it never goes stale, then mirrors its structure into a new project.
The one rule: the template is the source of truth
Do not invent structure, versions, or APIs from memory. Clone tollbooth-sample and copy
what is actually there. The SDK evolves; the live template reflects the current shape.
Procedure
1. Confirm inputs
Gather (ask only for what the user did not already provide):
- Service name / slug — short, lowercase, e.g.
weather,polygon,wiki. Becomes the tool prefix (<slug>_check_balance,<slug>_<your_tool>). - One-line description of what the service does.
- Path to the user's existing code and its shape: a REST API, a stdio MCP, or an
HTTP MCP. Detect the shape yourself if you can see the code (look for
FastMCP, an MCPServer, stdio transport, or plain HTTP handlers vs. a REST client).
If the upstream service needs credentials (API key, OAuth), note that — it affects the
credential template and whether a per-call session module is warranted (see
references/sessions-and-vaults.md).
2. Fetch the live template
git clone --depth 1 https://github.com/lonniev/tollbooth-sample.git /tmp/tollbooth-sample-template
Then read, from the clone:
pyproject.toml— the live wheel pin (e.g.tollbooth-dpyc[nostr]==X.Y.Z). Never hardcode a version; copy whatever the template pins today.src/tollbooth_sample/server.py— the bootstrap anatomy you will mirror.src/tollbooth_sample/weather.py— the domain-module exemplar (pure logic, no billing).src/tollbooth_sample/config.py,fastmcp.json,.fastmcp.yaml,renovate.json,.github/workflows/ci.yml,tests/— copy these with only names/slugs changed.
What ships with it
5 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.
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.
- 5d ago First seen · 164 lines · 101 tokens per session scan A 70d5a84bb2f0
bootstrap-dpyc-operator is a skill published in the GitHub repository lonniev/tollbooth-sample (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 101 tokens to every session and 2,573 once invoked, about $0.0005 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.
Other skills, from other repositories
sparkbtcbot
Give an AI agent a self-custodial Bitcoin wallet on the Spark L2. Covers wallet init from a BIP39 mnemonic, zero-fee Spark and BTKN/LRC20 token transfers, Lightning invoices (create and pay), Spark native invoices, L402 paywall payment, L1 deposits and cooperative withdrawals, and message signing. Make sure to use…
btcpay-mcp
MCP server for BTCPay Server — enables AI agents to manage Bitcoin and Lightning merchant payments. 21 tools, 77 tests, MIT license.
saturnzap
Non-custodial Lightning wallet for AI agents via sz CLI: send/receive sats, pay invoices, auto-pay HTTP 402 (L402), manage channels and liquidity. Use when: (1) paying for API access with Lightning, (2) creating or paying BOLT11 invoices, (3) checking wallet balance or channel health, (4) managing peers and channels.…
satrank-l402
Discover and score L402 endpoints on Bitcoin Lightning before paying. Use when an agent needs to call a paid API and wants a Bayesian trust posterior + offline-verifiable Nostr assertion. Bitcoin-pure, no x402/EVM.
lightning-architecture-review
Review Bitcoin Lightning Network protocol designs, compare channel factory approaches, and analyze Layer 2 scaling tradeoffs. Covers trust models, on-chain footprint, consensus requirements, HTLC/PTLC compatibility, liveness, and watchtower support.
lightning-channel-factories
Technical reference on Lightning Network channel factories, multi-party channels, LSP architectures, and Bitcoin Layer 2 scaling without soft forks. Covers Decker-Wattenhofer, timeout trees, MuSig2 key aggregation, HTLC/PTLC forwarding, and watchtower breach detection.