lightspeed-x-mcp: Instructions file for Claude Code

CLAUDE.md

lightspeed-x-mcp CLAUDE.md is an instructions file for Claude Code from genvjacobc/lightspeed-x-mcp. It costs 2,247 tokens per session, scanned A, original, MIT.

Repository instructions for a read-only connector to Lightspeed X, a retail point-of-sale system formerly called Vend. They guide Claude Code when setting up or editing the connector.

In plain words
What is it for?
Maintaining the Lightspeed X connector, setting it up, checking credentials, and handling user preferences safely.
Why use it?
They keep changes within the connector’s safety rules, especially the rule that it must never change a retailer’s data. They also provide the approved setup and connection checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is genvjacobc/lightspeed-x-mcp's own configuration. It tells Claude Code how to work on lightspeed-x-mcp 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 lightspeed-x-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to genvjacobc/lightspeed-x-mcp. 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/genvjacobc/lightspeed-x-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/genvjacobc/lightspeed-x-mcp

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 lightspeed-x-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/genvjacobc/lightspeed-x-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/genvjacobc/lightspeed-x-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/genvjacobc/lightspeed-x-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/genvjacobc/lightspeed-x-mcp/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.

agentmods 80×15 button for lightspeed-x-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/genvjacobc/lightspeed-x-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/genvjacobc/lightspeed-x-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,247 This file is loaded in full into every session.
When invoked 2,247 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02247 $0.02247
Opus 5.5 $0.00899 $0.00899
Sonnet 5.5 $0.00449 $0.00449
Haiku 4.5 $0.00225 $0.00225

Measured 18d ago against content hash 1743ec870aae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lightspeed-x-mcp 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 18d 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 · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 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.

What this is

lightspeed-x-mcp: an MCP server for Lightspeed X (Retail POS, the platform formerly called Vend), shipped both as a standalone MCP server and as a Claude Code plugin. Read-only by default; since 2.0 it has opt-in writes behind a human approval gate.

If a user asks you to set this up for them

Use the setup skill in skills/setup/SKILL.md. It has the full walkthrough: where the credential file goes, how to get a token, and how to verify. Do not improvise a setup procedure from this file.

The one-command check is:

node dist/index.js --doctor

It validates credentials, calls the live API, and explains any failure. Never tell a user they are connected until the doctor reports every account reachable.

Non-negotiables when editing the server

  • Writes go through the gate, always. LightspeedClient.send() is the only mutating call, and only tools/writes/apply.ts may call it. Every other write tool is a preview: it may GET, validate and createPlan(), and must return previewResult(). Never add a tool or parameter that sends a POST, PUT, PATCH or DELETE directly. The approval gate is the reason this is safe to point at a live business.
  • The gate's properties are not negotiable. lightspeed_apply_write keeps _meta["anthropic/requiresUserInteraction"]: true and destructiveHint; it is the only flagged tool and previews stay readOnlyHint. Plans stay single use, expiring, bound to a server-written confirm phrase, and re-checked against the write-enabled accounts at apply time. No env var, parameter or config key may skip the per-call approval.
  • Off unless asked for. With LIGHTSPEED_WRITE_ACCOUNTS unset, register no write tool at all. High-risk tools (sales, registers, store credit, gift cards, loyalty, and raw writes to those paths) also require LIGHTSPEED_WRITE_HIGH_RISK=true, enforced in writeClient().
  • Every write tool must say what it cannot do. Set verified: false until the endpoint has been exercised live, give each step an undo where one exists, back up prior state via before, and add a warning for anything permanent. A POST is never retried except on 429.
  • scripts/check-writes.mjs pins all of the above. Extend it when you add a write tool; it must keep passing with no credentials.
  • Never throw from a tool handler. MCP requires failures to come back as results, not protocol errors. Wrap every handler in guard() from lib/format.ts.
  • Never console.log. Stdout carries JSON-RPC frames on stdio transport. Diagnostics go to console.error. The only exception is doctor.ts, which runs outside the protocol.
  • No retailer-specific values in code. Accounts, domains, and tokens come from the environment. This repo is public and generic.
  • Rebuild and commit dist/. Plugin installs do not run a build step, so dist/ is intentionally tracked. A source change that is not rebuilt ships broken. Run npm run build before committing.
  • Bump version in all four places when releasing: package.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json, and the VERSION constant in src/index.ts. Plugin users only receive updates when the manifest version changes, and VERSION is what the server announces to its client, so a missed bump makes the running server lie about which build it is. Check with:

Read the full file on GitHub · 169 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.

  1. 18d ago Changed · +24 lines · +434 tokens per session 1743ec870aae
  2. 1mo ago First seen · 145 lines · 1,813 tokens per session scan A 9f97260ddc30

Subscribe to this mod's changes

lightspeed-x-mcp CLAUDE.md is an instructions file published in the GitHub repository genvjacobc/lightspeed-x-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 2,247 tokens to every session, about $0.0090 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.

Related

Other instructions, from other repositories