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.
curl -O https://raw.githubusercontent.com/genvjacobc/lightspeed-x-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/genvjacobc/lightspeed-x-mcpWrote 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/instructions/genvjacobc/lightspeed-x-mcp/claude-md)<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.
<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>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 | $0.02247 | $0.02247 |
| Opus 5.5 | $0.00899 | $0.00899 |
| Sonnet 5.5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00225 | $0.00225 |
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.
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 onlytools/writes/apply.tsmay call it. Every other write tool is a preview: it may GET, validate andcreatePlan(), and must returnpreviewResult(). 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_writekeeps_meta["anthropic/requiresUserInteraction"]: trueanddestructiveHint; it is the only flagged tool and previews stayreadOnlyHint. 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_ACCOUNTSunset, register no write tool at all. High-risk tools (sales, registers, store credit, gift cards, loyalty, and raw writes to those paths) also requireLIGHTSPEED_WRITE_HIGH_RISK=true, enforced inwriteClient(). - Every write tool must say what it cannot do. Set
verified: falseuntil the endpoint has been exercised live, give each step anundowhere one exists, back up prior state viabefore, and add a warning for anything permanent. A POST is never retried except on 429. scripts/check-writes.mjspins 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()fromlib/format.ts. - Never
console.log. Stdout carries JSON-RPC frames on stdio transport. Diagnostics go toconsole.error. The only exception isdoctor.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, sodist/is intentionally tracked. A source change that is not rebuilt ships broken. Runnpm run buildbefore committing. - Bump
versionin all four places when releasing:package.json,.claude-plugin/plugin.json,.claude-plugin/marketplace.json, and theVERSIONconstant insrc/index.ts. Plugin users only receive updates when the manifest version changes, andVERSIONis what the server announces to its client, so a missed bump makes the running server lie about which build it is. Check with:
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.
- 18d ago Changed · +24 lines · +434 tokens per session 1743ec870aae
- 1mo ago First seen · 145 lines · 1,813 tokens per session scan A 9f97260ddc30
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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.