mcp-google-tagmanager: Instructions file for Claude Code

CLAUDE.md

mcp-google-tagmanager CLAUDE.md is an instructions file for Claude Code from A1-x-Tech/mcp-google-tagmanager. It costs 1,537 tokens per session, scanned A, original, MIT.

Project instructions for developing an MCP server for Google Tag Manager, Google's service for managing website and app tracking tags.

In plain words
What is it for?
Use them when developing, testing, building, or adding tools to the Google Tag Manager integration while preserving its TypeScript, Node.js, and startup conventions.
Why use it?
They record the server's commands, authentication, architecture, testing rules, and behavior when credentials are missing.

Instructions file for Claude Code

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

This is A1-x-Tech/mcp-google-tagmanager's own configuration. It tells Claude Code how to work on mcp-google-tagmanager 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 mcp-google-tagmanager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to A1-x-Tech/mcp-google-tagmanager. 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/A1-x-Tech/mcp-google-tagmanager/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/A1-x-Tech/mcp-google-tagmanager

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 mcp-google-tagmanager CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/a1-x-tech/mcp-google-tagmanager/claude-md.svg)](https://agentmods.dev/instructions/a1-x-tech/mcp-google-tagmanager/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/a1-x-tech/mcp-google-tagmanager/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-google-tagmanager/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,537 This file is loaded in full into every session.
When invoked 1,537 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 $0.01537 $0.01537
Opus 5 $0.00768 $0.00768
Sonnet 5 $0.00307 $0.00307
Haiku 4.5 $0.00154 $0.00154

Measured 7d ago against content hash 38ecf35730ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-google-tagmanager 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 7d 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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

MCP server (stdio) for the Google Tag Manager API v2 (tagmanager.googleapis.com/tagmanager/v2). Auth is Google OAuth 2.0: a refresh-token trio exchanged at oauth2.googleapis.com/token (cached until 60 s before expiry) or a direct access token. TypeScript, ESM, @modelcontextprotocol/sdk + zod, Node >= 20.

Commands

  • npm run typecheck — tsc over src including tests (tsconfig.check.json)
  • npm run build — compile to dist/ (tests and smoke excluded)
  • npm test — unit suite (tsx loader) + dist smoke (real stdio handshake)
  • npm run smoke — live read-only check (needs real credentials)
  • npm run dev — tsx watch

Architecture

  • src/index.ts — wiring only: telemetry → config → client → McpServer → register tools → stdio. loadConfigOrDegraded() catches ConfigError, pings startup_failed (fire-and-forget) and degrades the config to "no credentials"; an unconfigured start prepends UNCONFIGURED_PREFIX — plus Configuration problem: <message> when a ConfigError was caught — to the initialize instructions, and oninitialized sends server_start for a configured install or unconfigured_start (with the reason) otherwise.
  • src/config.ts — env → TagManagerConfig; never exits. No credentials at all (empty string = missing) is NOT an error: the fields stay undefined and the server starts degraded. A partial setup still throws ConfigError(message, reason) with the historical per-variable checks; the reason codes (missing_client_id, missing_client_secret, missing_refresh_token) are pinned by config.test.ts. Also home to CredentialsError / MISSING_CREDENTIALS_MESSAGE (opens with the historical startup error verbatim, then says to set the variables and restart) and hasCredentials().
  • src/auth.tsTokenProvider: refresh-token → access-token exchange, promise-shared, cached until expiry − 60 s; direct access token passes through. Token calls bypass the rate limiter (different quota). With no credentials at all it throws CredentialsError BEFORE any fetch — a degraded start must never reach the token endpoint or the retry loop.
  • src/client.ts — ALL HTTP: URL building under /tagmanager/v2/, Bearer auth, SSRF guard, timeout covering body reads, the rate limiter and the retry policy. One typed method per endpoint; tools never build URLs.
  • src/builtin-variable-types.ts — generated from the discovery doc; do not hand-edit.
  • src/tools/*.tsregister<Domain>Tools(server, client); handlers are always try { ok(await client...) } catch (e) { fail(e) }.
  • src/telemetry.ts — anonymous usage pings (ids/names/versions only, never the OAuth credentials, account/container ids or arguments; fire-and-forget, must never block or throw; opt-out ASKADS_TELEMETRY=0). server_start means "a usable install started"; unconfigured_start is a degraded start and startup_failed a malformed config caught at load — both carry a reason from the ConfigError code vocabulary (missing_client_id, missing_client_secret, missing_refresh_token) — never a variable's value.

Read the full file on GitHub · 99 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. 7d ago First seen · 99 lines · 1,537 tokens per session scan A 38ecf35730ba

Subscribe to this mod's changes

mcp-google-tagmanager CLAUDE.md is an instructions file published in the GitHub repository A1-x-Tech/mcp-google-tagmanager (0 stars, last pushed 8d ago), licensed MIT. It adds 1,537 tokens to every session, about $0.0077 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

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

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 · 5,153 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

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

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

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