gtm-workflow

gtm-workflow is a skill for Claude Code from N-O-P-E/nope-marketplace. It costs 101 tokens per session (1,777 once invoked), scanned A, original, MIT.

A workflow for managing Google Tag Manager, a web service that controls tracking code and events on a website. It lets you inspect the setup, test tracking, make draft changes, and publish them after verification.

In plain words
What is it for?
Use it to review tags and triggers, investigate dataLayer events, check GA4 or Meta Pixel events, test tracking with Tag Assistant, and publish documented changes.
Why use it?
It helps determine whether a tracking problem comes from the website event or from the Tag Manager configuration. Previewing changes before publishing reduces the chance of sending incorrect data live.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the gtm-workflow plugin — 1 skill shipped together

Good fit Use it to review tags and triggers, investigate dataLayer events, check GA4 or Meta Pixel events, test tracking with Tag Assistant, and publish documented changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/n-o-p-e/nope-marketplace/gtm-workflow
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add N-O-P-E/nope-marketplace --skill gtm-workflow
Clone the repo
git clone --depth 1 https://github.com/N-O-P-E/nope-marketplace

Made for: Claude Code.

Or install gtm-workflow, the plugin that ships this one along with the rest of its 1 skill.

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 gtm-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/n-o-p-e/nope-marketplace/gtm-workflow/github.svg)](https://agentmods.dev/skills/n-o-p-e/nope-marketplace/gtm-workflow)
Your own site
<a href="https://agentmods.dev/skills/n-o-p-e/nope-marketplace/gtm-workflow"><img src="https://agentmods.dev/badge/skills/n-o-p-e/nope-marketplace/gtm-workflow/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 gtm-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/n-o-p-e/nope-marketplace/gtm-workflow"><img src="https://agentmods.dev/badge/skills/n-o-p-e/nope-marketplace/gtm-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00101 $0.01777
Opus 5 $0.00051 $0.00889
Sonnet 5 $0.00020 $0.00355
Haiku 4.5 $0.00010 $0.00178

Measured 12d ago against content hash 2de45dfbb7fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gtm-workflow 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 12d 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.

plugins/gtm-workflow/skills/gtm-workflow/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gtm-workflow

Drive Google Tag Manager end-to-end through a real Chrome via chrome-devtools-mcp: inventory, verify, edit, preview, publish.

First principles

  1. Reads before writes. Always inventory the container before proposing changes — tags the user "forgot existed" are common.
  2. Workspaces stage; Publish ships. Work in the GTM draft workspace. Nothing goes live until the explicit Publish step.
  3. Preview before Publish. Use Tag Assistant to confirm tags fire on the real site before pushing to production.
  4. Events come from two places. A tag fires because of (a) a dataLayer push from your site code or (b) an auto-tracked DOM event (click, scroll, visibility). Diagnose which source is missing before assuming the tag is broken.
  5. Every publish gets a version name and description. Future-you needs to roll back.

The loop

Inventory → Instrument → Verify → (optionally) Modify → Preview → Publish

For any GTM task, identify which phase you're starting in:

Phase 1 — Connect

Before any other work:

  1. Confirm the user has chrome-devtools-mcp available. Invoke list_pages. If it errors with browser already running, follow references/troubleshooting.md.
  2. Navigate to https://tagmanager.google.com/#/home.
  3. Check auth: evaluate_script for document.body.innerText. If the page shows account listings, user is signed in. If it redirects to accounts.google.com, the user needs to sign in themselves — show them the tab and wait.
  4. Read the account list. Ask the user which container they want if there's more than one. Each container row is a link to /container/accounts/<account-id>/containers/<container-id> — grab the real IDs from the href, never guess.

Read the full file on GitHub · 135 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 135 lines · 101 tokens per session scan A 2de45dfbb7fc

Subscribe to this mod's changes

gtm-workflow is a skill published in the GitHub repository N-O-P-E/nope-marketplace (9 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 1,777 once invoked, about $0.0005 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.