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 ga4-audience-exclusionsgit 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/ga4-audience-exclusions)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/ga4-audience-exclusions"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/ga4-audience-exclusions/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/ga4-audience-exclusions"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/ga4-audience-exclusions.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 | $0.00097 | $0.04673 |
| Opus 5 | $0.00048 | $0.02337 |
| Sonnet 5 | $0.00019 | $0.00935 |
| Haiku 4.5 | $0.00010 | $0.00467 |
Grade A, and why
ga4-audience-exclusions 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 10d 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 — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GA4 Audience Exclusions Guide
Complete guide for effectively excluding audiences and frequency capping to maximize advertising budget.
Exclusion Types Overview
EXCLUSION STRATEGIES
=====================
┌─────────────────────┬────────────────────────────────────────────────────┐
│ Type │ Description │
├─────────────────────┼────────────────────────────────────────────────────┤
│ GA4 Built-in │ "Exclude users when" in audience builder │
│ Exclusion │ Makes audience pre-filtered │
│ │ └─► Best for: Remarketing audiences │
├─────────────────────┼────────────────────────────────────────────────────┤
│ Google Ads │ Separate exclusion audience added to │
│ Campaign Exclusion │ campaign settings │
│ │ └─► Best for: Prospecting campaigns │
├─────────────────────┼────────────────────────────────────────────────────┤
│ Negative Audience │ "Do not show ads to this audience" │
│ Targeting │ Campaign-level or account-level │
│ │ └─► Best for: Account-wide exclusions │
├─────────────────────┼────────────────────────────────────────────────────┤
│ Frequency Capping │ Soft exclusion via impression limits │
│ │ User sees max X ads per day/week │
│ │ └─► Best for: Display/YouTube │
└─────────────────────┴────────────────────────────────────────────────────┘
Core Exclusion Audiences
ESSENTIAL EXCLUSION AUDIENCES
===============================
1. RECENT PURCHASERS (MUST-HAVE)
─────────────────────────────────
Name: "Purchasers - Last 30 Days"
Condition: event_name = purchase (in last 30 days)
Duration: 30 days
Why exclude:
├── Prevent waste on recently converted users
├── Better user experience (no repetitive ads)
└── Focus acquisition budget on new customers
Exclude FROM:
├── All acquisition campaigns
├── Prospecting campaigns
└── Generic remarketing
Do NOT exclude from:
├── Cross-sell campaigns (different products)
├── Loyalty/VIP campaigns
└── Replenishment reminders (after X days)
2. ALL CONVERTERS (LIFETIME)
─────────────────────────────
Name: "All Purchasers - Lifetime"
Condition: event_name = purchase (any time)
Duration: 540 days (maximum)
Why:
├── Acquisition efficiency (focus on new customers)
├── Separate campaigns for existing vs new customers
└── Different messaging/offers per segment
Exclude FROM:
├── Pure acquisition campaigns
├── First-time buyer promos
└── New customer discounts
3. LEADS (RECENT SUBMITTERS)
─────────────────────────────
Name: "Leads - Last 14 Days"
Condition: event_name = generate_lead OR form_submit
Duration: 14 days
Why:
├── Already in sales funnel
├── Nurturing via email, not ads
└── Prevent over-exposure
Exclude FROM:
├── Lead generation campaigns
├── Demo request campaigns
└── Generic awareness
4. HIGH-VALUE CUSTOMERS (PROTECT)
──────────────────────────────────
Name: "VIP Customers - LTV 500+"
Condition: user_ltv > 500 OR purchase_count >= 5
Duration: 540 days
Why exclude from certain campaigns:
├── These customers return organically
├── No discount ads needed
├── Protect relationship
Exclude FROM:
├── Discount campaigns
├── Win-back with large discounts
└── Aggressive retargeting
5. CART ABANDONERS (ALREADY TARGETED)
──────────────────────────────────────
Name: "Active Cart Abandoners - 14d"
Condition: add_to_cart (last 14 days) EXCLUDE purchase
Duration: 14 days
Why exclude:
├── These already receive cart abandonment emails/ads
├── Prevent double exposure
└── Budget efficiency
Exclude FROM:
├── General product remarketing
├── Awareness campaigns
└── Top-of-funnel content
6. BOUNCED VISITORS (LOW VALUE)
────────────────────────────────
Name: "Bouncers - Single Page"
Condition: session_duration < 10s OR page_views = 1
Duration: 7 days
Why exclude:
├── Low intent, likely accidental traffic
├── Prevent waste on low-quality traffic
└── Better overall ROAS
Exclude FROM:
├── Remarketing campaigns
├── Consideration campaigns
└── High-intent targeting
What ships with it
1 file 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.
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.
- 10d ago First seen · 626 lines · 97 tokens per session scan A e58828ef79cb
ga4-audience-exclusions is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 12d ago), licensed MIT. It adds 97 tokens to every session and 4,673 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.
Other skills, from other repositories
analytics
Growth analytics authority — GA4 event tracking, conversion funnels, attribution models, cohort analysis, A/B testing, Supabase analytics queries, and revenue reporting patterns.
attribution-scope
GA4 has three distinct attribution scopes. Using the wrong scope gives misleading results. Choose based on the question you are answering.
bot-traffic-detection
Identify and exclude bot, scraper, and spam sessions from GA4 data.
analytics
Use when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PII scrubbing. NOT charting that data (that is dashboard), NOT choosing which metrics matter (that is kpi-framework), NOT experiment math (that is ab-testing), NOT cookie-policy…
sealeap-amazon-product-targeting
An Amazon Ads planning skill for targeting product pages and categories, including competitor, complementary, upsell, and own-product traffic.
cro-optimizer
CRO specialist that pulls live analytics data via the Humblytics MCP, analyzes conversion funnels, identifies drop-off points, and generates prioritized A/B test hypotheses. Use when analyzing conversion rates, diagnosing funnel leaks, optimizing signup flows, or creating test roadmaps. Triggers: CRO, conversion rate…