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.
npx skills add Ad-Superpowers/ad-superpowers-plugin --skill gtm-consent-mode-guidegit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote 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/skills/ad-superpowers/ad-superpowers-plugin/gtm-consent-mode-guide)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/gtm-consent-mode-guide"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/gtm-consent-mode-guide/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/skills/ad-superpowers/ad-superpowers-plugin/gtm-consent-mode-guide"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/gtm-consent-mode-guide.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 | $0.00117 | $0.05903 |
| Opus 5.5 | $0.00047 | $0.02361 |
| Sonnet 5.5 | $0.00023 | $0.01181 |
| Haiku 4.5 | $0.00012 | $0.00590 |
Grade A, and why
gtm-consent-mode-guide 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 1mo 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 — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTM Consent Mode v2 Guide
Since March 2024, Google requires Consent Mode v2 for any advertiser serving users in the European Economic Area (EEA). Without it, Google Ads, GA4, and other Google products cannot use remarketing or behavioral modeling for those users. This skill covers everything you need to implement consent correctly, integrate a CMP, and recover the data you lose to cookie consent refusals.
Why Consent Mode v2 Exists
Regulatory Background
| Regulation | Scope | Key Requirement |
|---|---|---|
| GDPR (2018) | EU/EEA residents | Explicit consent before storing cookies or processing personal data |
| ePrivacy Directive | EU/EEA | Consent before setting non-essential cookies |
| Digital Markets Act (2024) | Large platforms (Google, Meta, etc.) | Platforms must verify consent before using data for ads |
| TDDDG (Germany) | Germany | Stricter interpretation of ePrivacy |
| nFADP (Switzerland) | Switzerland | GDPR-equivalent since Sept 2023 |
What Changed in v2 (March 2024)
Consent Mode v1 had two consent types: ad_storage and analytics_storage. v2 adds two more:
| Consent Type | Purpose | Required Since |
|---|---|---|
ad_storage |
Cookies for advertising (Google Ads, remarketing) | v1 (2020) |
analytics_storage |
Cookies for analytics (GA4, GA) | v1 (2020) |
ad_user_data |
NEW in v2. Sending user data to Google for advertising | March 2024 |
ad_personalization |
NEW in v2. Using data for ad personalization/remarketing | March 2024 |
If you do not implement v2: Google Ads cannot use remarketing audiences, conversion modeling is disabled, and your campaigns lose optimization signal for EEA users.
How Consent Mode Works
The Two-Step Consent Flow
Step 1: consent_default (on page load, BEFORE any tags fire)
|
Set all consent types to 'denied' for EEA users
|
GTM loads tags in RESTRICTED mode:
- GA4: sends cookieless pings (no user identification)
- Google Ads: no conversion tracking, no remarketing
- Meta: pixel does not fire
|
Step 2: consent_update (when user interacts with consent banner)
|
+-- User ACCEPTS all --> Update all to 'granted'
| GTM reloads tags in FULL mode
| Cookies are set, full tracking resumes
|
+-- User ACCEPTS analytics only --> Update analytics_storage to 'granted'
| GA4 sets cookies, ads remain restricted
|
+-- User REJECTS all --> No update (stays 'denied')
Cookieless pings continue, no cookies set
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.
- 1mo ago First seen · 571 lines · 117 tokens per session scan A 39d944795d58
gtm-consent-mode-guide is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 117 tokens to every session and 5,903 once invoked, about $0.0005 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 2026-09-11.
Other skills, from other repositories
ai-hive-administrative-review-materials
A document-preparation workflow for organising materials for an administrative appeal, which challenges a government decision or action through an official review process.
ai-hive-after-death-official-checklist
A checklist assistant for handling administrative tasks after a family member dies, such as identifying procedures, organisations, accounts, and required documents. It works from authorised source materials and treats local official rules as the final authority.
ai-gaochao-cn-migration-ai-hive
A migration-review workflow for moving AI API workloads between providers. It examines data retention, training use, data location, deletion, contracts and operational tests before any traffic is moved.
sealeap-pixiu-amazon-account-compliance
An Amazon account-risk and compliance workflow covering brand registration, intellectual property, customer service, and support cases. It organizes notices, evidence, deadlines, affected accounts, and corrective materials without inventing missing facts.
sealeap-amazon-compliance-led-growth
Build an Amazon growth strategy that treats tax, product safety, account, IP, and logistics compliance as non-negotiable constraints, then compares niches, price bands, operating models, and marketplaces using weighted economics. Use when the user asks how to find opportunities as compliance costs rise or whether to…
sealeap-amazon-negative-review-response
Triage negative Amazon reviews into policy violations, suspected abuse, and genuine product feedback, then prepare factual official reports and product-remediation actions. Use when the user asks whether a review can be removed, how to report abusive content, or how to respond to a rating decline. Never fabricate…