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-attribution-advisorgit 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-attribution-advisor)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/ga4-attribution-advisor"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/ga4-attribution-advisor/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-attribution-advisor"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/ga4-attribution-advisor.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 | $0.00086 | $0.04633 |
| Opus 5 | $0.00043 | $0.02316 |
| Sonnet 5 | $0.00017 | $0.00927 |
| Haiku 4.5 | $0.00009 | $0.00463 |
Grade A, and why
ga4-attribution-advisor 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 9d 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GA4 Attribution Advisor
Complete guide for choosing and configuring the right attribution model in Google Analytics 4 for accurate conversion attribution.
Quick Decision Tree
GA4 ATTRIBUTION MODEL SELECTION
│
├─► WHAT IS YOUR PRIMARY GOAL?
│ ├─► Maximum Smart Bidding performance
│ │ └─► DATA-DRIVEN ATTRIBUTION (DDA)
│ │ └─► Recommended for Google Ads
│ │
│ ├─► Simple, predictable reporting
│ │ └─► LAST CLICK
│ │ └─► Easy to explain to stakeholders
│ │
│ ├─► Focus on measuring awareness campaigns
│ │ └─► FIRST CLICK
│ │ └─► Values top-of-funnel touchpoints
│ │
│ └─► Value all touchpoints equally
│ └─► LINEAR
│ └─► Fair distribution across journey
│
├─► HOW MUCH DATA DO YOU HAVE?
│ ├─► < 300 conversions/month
│ │ └─► DDA not available
│ │ └─► Use Position-Based or Last Click
│ │
│ └─► > 300 conversions/month
│ └─► DDA recommended
│ └─► Machine learning can find patterns
│
└─► WHICH CHANNELS DO YOU USE?
├─► Only Google Ads
│ └─► DDA in Google Ads
│ └─► Sync with GA4 for consistency
│
├─► Google + Meta/LinkedIn/TikTok
│ └─► GA4 DDA as single source of truth
│ └─► Cross-channel comparison reports
│
└─► Complex multi-touch journey
└─► DDA with Model Comparison tool
└─► Analyze touchpoint value
Attribution Models Comparison
ATTRIBUTION MODELS OVERVIEW
============================
┌─────────────────┬───────────────────────────────────────────────────────┐
│ Model │ How it works │
├─────────────────┼───────────────────────────────────────────────────────┤
│ DATA-DRIVEN │ Machine learning determines credit based on │
│ (DDA) │ actual conversion patterns in your data │
│ │ Best for: Smart Bidding, Google Ads │
│ │ Requires: 300+ conversions/month │
├─────────────────┼───────────────────────────────────────────────────────┤
│ LAST CLICK │ 100% credit to the last touchpoint │
│ │ (excl. direct traffic) │
│ │ Best for: Simple reporting │
│ │ Drawback: Undervalues upper funnel │
├─────────────────┼───────────────────────────────────────────────────────┤
│ FIRST CLICK │ 100% credit to the first touchpoint │
│ │ Best for: Awareness campaign evaluation │
│ │ Drawback: Undervalues converters │
├─────────────────┼───────────────────────────────────────────────────────┤
│ LINEAR │ Equal credit distribution across all touchpoints │
│ │ Best for: Long customer journeys │
│ │ Drawback: No differentiation in touchpoint impact │
├─────────────────┼───────────────────────────────────────────────────────┤
│ POSITION-BASED │ 40% first, 40% last, 20% distributed across middle │
│ │ Best for: Awareness + conversion focus │
│ │ Drawback: Arbitrary distribution │
├─────────────────┼───────────────────────────────────────────────────────┤
│ TIME DECAY │ More credit to more recent touchpoints │
│ │ Best for: Short sales cycles │
│ │ Drawback: Undervalues brand building │
└─────────────────┴───────────────────────────────────────────────────────┘
EXAMPLE: Customer Journey with 4 touchpoints
─────────────────────────────────────────────
Touchpoints: Google Ads → Organic → Email → Direct → Conversion (EUR 100)
Model comparison:
┌─────────────────┬───────────┬─────────┬─────────┬────────┐
│ Model │ Google Ads│ Organic │ Email │ Direct │
├─────────────────┼───────────┼─────────┼─────────┼────────┤
│ Last Click │ EUR 0 │ EUR 0 │ EUR 100 │ EUR 0* │
│ First Click │ EUR 100 │ EUR 0 │ EUR 0 │ EUR 0 │
│ Linear │ EUR 33.33 │ EUR 33.33│ EUR 33.33│ EUR 0 │
│ Position-Based │ EUR 40 │ EUR 10 │ EUR 50 │ EUR 0 │
│ Time Decay │ EUR 10 │ EUR 20 │ EUR 70 │ EUR 0 │
│ DDA │ EUR 35 │ EUR 25 │ EUR 40 │ EUR 0 │
└─────────────────┴───────────┴─────────┴─────────┴────────┘
*Direct is usually excluded and attributed to the previous touchpoint
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.
- 9d ago First seen · 494 lines · 86 tokens per session scan A c9789aeac5f5
ga4-attribution-advisor is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 11d ago), licensed MIT. It adds 86 tokens to every session and 4,633 once invoked, about $0.0004 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.
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…
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.