What is ln-agent-poc-v2 CLAUDE.md?

Repository instructions for a TypeScript project that uses Bitcoin Lightning payments to buy products through an MCP agent. They describe the project layout, commands, architecture, and spending safeguards.

Use them when installing, developing, linting, testing, or changing the purchasing agent and its Lightning, Cashu, browser-automation, or configuration code.

They give coding agents the project-specific rules needed to work safely in the repository. This includes where payment logic belongs, how to run tests, and which settings must stay documented.

How cachet-jp/ln-agent-poc-v2 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cachet-jp/ln-agent-poc-v2. 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/cachet-jp/ln-agent-poc-v2/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cachet-jp/ln-agent-poc-v2

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cachet-jp/ln-agent-poc-v2/claude-md/github.svg)](https://agentmods.dev/instructions/cachet-jp/ln-agent-poc-v2/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cachet-jp/ln-agent-poc-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/cachet-jp/ln-agent-poc-v2/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cachet-jp/ln-agent-poc-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/cachet-jp/ln-agent-poc-v2/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 740 This file is loaded in full into every session.

When invoked 740 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00740	$0.00740
Opus 5.5	$0.00296	$0.00296
Sonnet 5.5	$0.00148	$0.00148
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash b197dd63d481, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ln-agent-poc-v2 CLAUDE.md 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 2mo 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.

CLAUDE.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

Project

Bitcoin Lightning 決済で商品を購入する MCP エージェント。主要コンポーネントは purchasing-agent/ ディレクトリに全て入っています。

Stack: TypeScript (Node 20+), pnpm, MCP SDK (@modelcontextprotocol/sdk), @cashu/cashu-ts, Playwright (V-Preca inquiry のみ), zod, vitest.

Layout

purchasing-agent/ — MCP サーバー本体。ツール実装・ウォレット連携・V-Preca 照会のブラウザ自動化すべて。
.claude/commands/ — Claude Code の slash-command SKILL。/cashu-purchase /auto-purchase /cashu-manage /bitrefill-purchase /vpreca-inquiry。

Common Commands

cd purchasing-agent
pnpm install
pnpm run lint     # tsc --noEmit
pnpm test         # vitest run
pnpm dev          # tsx src/server.ts (MCP stdio server)

Architecture Notes

All Lightning payments go through Cashu melt — payBolt11(bolt11) in src/lib/payment-strategy.ts is the single dispatch point; tools must never call Cashu directly.
Tool files (src/tools/*.ts) only register MCP tools and delegate to lib/ helpers.
Config (src/lib/config.ts) uses zod; all env vars documented in .env.example. Add new vars both places.
Spend guardrails: MAX_SPEND_JPY for gift-card purchases, CASHU_MAX_BALANCE_SATS for ecash top-ups. Never bypass these.
UseBitcoin uses the REST API (src/lib/usebitcoin-api.ts), not browser automation.
V-Preca inquiry is the only flow that drives Playwright (against Lifecard's card-inquiry page).
Top up Cashu via cashu_create_invoice + cashu_claim_invoice (any LN wallet pays the invoice).

Key Constraints

Secrets live in .env, never committed. .env.example is the canonical list.
MCP responses: use src/lib/tool-helpers.ts helpers (jsonResponse, errorResponse, withErrorHandler) when feasible; existing UseBitcoin tools keep per-tool prefixes so they don't use the helper.
Playwright sessions are saved under purchasing-agent/storage-state/ and are user-private — never commit.
On a fulfilled purchase, do not log the gift code or redeem URL. Errors should not JSON.stringify(order) when the payload can contain a code.

Read the full file on GitHub · 54 lines

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.

2mo ago First seen · 54 lines · 740 tokens per session scan A b197dd63d481

Subscribe to this mod's changes

ln-agent-poc-v2 CLAUDE.md is an instructions file published in the GitHub repository cachet-jp/ln-agent-poc-v2 (4 stars, last pushed 11d ago), licensed MIT. It adds 740 tokens to every session, about $0.0030 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 2026-08-31.

Finance and fintech Web3 and blockchain bitcoin bitrefill cashu claude ecash gift-cards

ln-agent-poc-v2 CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ln-agent-poc-v2 CLAUDE.mdcachet-jp/ln-agent-poc-v2	Instructions file	4	11d ago	MIT	A	740	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

ln-agent-poc-v2: Instructions file for Claude Code