lob-mcp: Instructions file for Claude Code

CLAUDE.md

lob-mcp CLAUDE.md is an instructions file for Claude Code from optimize-overseas/lob-mcp. It costs 5,288 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Claude Code, an AI coding assistant, explaining how to work on a public MCP server that connects to the Lob.com mailing API.

In plain words
What is it for?
Following project conventions, maintaining the lob-mcp server, and checking that public changes do not reveal private Lob usage.
Why use it?
It keeps code, package contents, releases, and history generic and free of private customer or account details.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is optimize-overseas/lob-mcp's own configuration. It tells Claude Code how to work on lob-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 lob-mcp configures →

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/optimize-overseas/lob-mcp/claude-md.svg)](https://agentmods.dev/instructions/optimize-overseas/lob-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/optimize-overseas/lob-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/optimize-overseas/lob-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,288 This file is loaded in full into every session.
When invoked 5,288 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 $0.05288 $0.05288
Opus 5 $0.02644 $0.02644
Sonnet 5 $0.01058 $0.01058
Haiku 4.5 $0.00529 $0.00529

Measured 6d ago against content hash 753fe45e5cb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lob-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 6d 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 · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

lob-mcp is an MCP (Model Context Protocol) server that wraps the Lob.com API, exposing 78 tools + 23 design-spec resources across 12 resource groups — address verification, address book CRUD, mail-piece preview/create/lifecycle (postcards, letters, self-mailers, checks), templates + template versions + template search, campaigns + creatives, buckslips/cards + print orders, QR-code analytics, resource proofs, bank accounts, webhook subscriptions, and design specifications.

Distributed on npm as lob-mcp; runs as a local stdio server via npx lob-mcp. The package and repo are public.

Public-repository discipline

This rule is permanent and non-negotiable. This repository, the npm package, the GitHub release page, and the git history are all public. The codebase must be completely generic and applicable to any Lob user — exposing nothing about who maintains or uses it, what use cases it gets pointed at, or what specific Lob resources live in any private account.

Scope — applies to every public surface, not just code:

  • Source files (src/), build output (build/), schemas, tool descriptions, error messages, log lines, banner text.
  • Docs: README.md, CHANGELOG.md, CLAUDE.md, anything under docs/.
  • Tests that ship in the repo (currently tests/ is gitignored, but if any test ever becomes tracked it falls under this rule).
  • Examples in any of the above.
  • Git metadata: commit messages, tag messages, GitHub release notes, PR descriptions, issue titles/bodies. These are public artifacts of the repo.
  • npm metadata: package.json description / keywords / author, the published tarball.

Forbidden content:

  • Business or customer names (real or thinly anonymized).
  • Specific use-case framing (industries, workflows, campaigns, vertical references).
  • Real Lob resource identifiers from any private account: tmpl_…, adr_…, bnk_…, cmp_…, crv_…, psc_…, ltr_…, chk_…, bck_…, crd_…, vrf_…, ep_…, whk_…, etc. Even in a "the live verification used X" sentence in a commit message. Use generic placeholders instead.
  • Real template descriptions / campaign names / metadata values from any private account, even if they sound innocuous.
  • Account-specific quantities, prices, or volumes that imply who the account belongs to.
  • Personal identifiers: maintainer email beyond the package.json author block, anyone's name, addresses other than Lob's HQ at 210 King St used as an explicit placeholder.
  • Secrets: any API key, credential, internal URL, or live Lob test data.

Read the full file on GitHub · 188 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. 6d ago First seen · 188 lines · 5,288 tokens per session scan A 753fe45e5cb1

Subscribe to this mod's changes

lob-mcp CLAUDE.md is an instructions file published in the GitHub repository optimize-overseas/lob-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 5,288 tokens to every session, about $0.0264 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens