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 agentmods add commands/ad-superpowers/ad-superpowers-plugin/incrementality-test-designergit 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/commands/ad-superpowers/ad-superpowers-plugin/incrementality-test-designer)<a href="https://agentmods.dev/commands/ad-superpowers/ad-superpowers-plugin/incrementality-test-designer"><img src="https://agentmods.dev/badge/commands/ad-superpowers/ad-superpowers-plugin/incrementality-test-designer.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.01921 |
| Opus 5 | $0.00028 | $0.00960 |
| Sonnet 5 | $0.00011 | $0.00384 |
| Haiku 4.5 | $0.00006 | $0.00192 |
Grade A, and why
incrementality-test-designer 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platforms: meta, google_ads, linkedin, tiktok, google_analytics Tier: pro
This command requires the Ad Superpowers MCP connector to access your ad account data. Connect at https://app.adsuperpowers.ai if you haven't already.
Incrementality Test Designer
Design a rigorous incrementality test for your platform. In a privacy-first world (40-60% iOS signal loss, 50-65% modeled conversions), incrementality testing answers the only question that matters: "What revenue did this advertising create that wouldn't have happened anyway?"
OUTPUT FORMAT (CRITICAL - follow this EXACT structure)
TEST RECOMMENDATION
| Factor | Value |
|---|---|
| Recommended Test Type | [Geo Lift / Conversion Lift / Holdout / Ghost Bids / MMM] |
| Why This Test | [2-3 bullet reasons based on spend, platform, geography] |
| Estimated Duration | [X weeks total incl. baseline + cooldown] |
| Confidence Level | [High / Medium-High / Medium] |
Test Type Selection Reference:
| Test Type | Best For | Min Budget | Min Duration | Confidence |
|---|---|---|---|---|
| Geo Lift | Any channel, any size | 5K/mo | 4-6 weeks | High |
| Conversion Lift (Meta) | Meta only | 2K/mo | 2-4 weeks | Medium-High |
| Brand Lift (Google) | Brand awareness | 5K+ | 2 weeks | High |
| Holdout Test | Retargeting | 3K/mo | 3-4 weeks | Medium |
| Ghost Bids | Display/Video | 10K/mo | 4 weeks | High |
| Full MMM | All channels | 100K+/mo | 8-12 weeks | Highest |
GEO SPLIT DESIGN
| Factor | Test Regions | Control Regions |
|---|---|---|
| Population | [50% of target] | [50% of target] |
| Historical similarity | Must match within 15% | Baseline |
| Suggested regions | [List 3-5] | [List 3-5] |
Pre-built geo splits (use if applicable):
Netherlands:
| Option | Test | Control | Balance |
|---|---|---|---|
| North/South | Noord-Holland, Zuid-Holland, Utrecht | Noord-Brabant, Gelderland, Limburg | 85% |
| Randstad/Rest | Amsterdam, Rotterdam, Den Haag | All other provinces | 72% |
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.
- 4d ago First seen · 159 lines · 56 tokens per session scan A fd94d8448cef
incrementality-test-designer is a command published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 1,921 once invoked, about $0.0003 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 commands, from other repositories
feed-audit
Audit Merchant Center feed quality — disapprovals, attributes, identifiers, custom labels.
meta-audit
Full Meta Ads account audit, tailored to ecommerce or lead-gen automatically.
setup
First-run setup for the ga-mcp-full MCP server — install the CLI if needed, then complete the browser login.
ad-brief
Generate a production-ready creative brief from a scripted Pipeline ad. Includes shot list, filming card, B-roll suggestions, text overlay specs, and equipment notes. Ready to print and film.
ad-polish
Strip AI patterns from ad copy and scripts. Makes text sound like a real person wrote it, not a language model. Run on any Pipeline record before launch.
audit
Google Ads command — audit.