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.
git 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/campaign-battle-report)<a href="https://agentmods.dev/commands/ad-superpowers/ad-superpowers-plugin/campaign-battle-report"><img src="https://agentmods.dev/badge/commands/ad-superpowers/ad-superpowers-plugin/campaign-battle-report/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/commands/ad-superpowers/ad-superpowers-plugin/campaign-battle-report"><img src="https://agentmods.dev/badge/commands/ad-superpowers/ad-superpowers-plugin/campaign-battle-report.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 | $0.00028 | $0.00969 |
| Opus 5 | $0.00014 | $0.00485 |
| Sonnet 5 | $0.00006 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
campaign-battle-report 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 8d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platforms: meta, google_ads, linkedin, tiktok 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.
Campaign Battle Report
Compare two campaigns or time periods side-by-side.
Comparison Type: ab_test
OUTPUT FORMAT (CRITICAL - follow this EXACT structure)
CONTESTANTS
- A: [Campaign/Period A Name]
- B: [Campaign/Period B Name]
- Period: [Date Range]
HEAD-TO-HEAD
| Metric | A | B | Difference | Winner |
|---|---|---|---|---|
| Spend | [amount] | [amount] | +/-XX% | A/B |
| Impressions | [value] | [value] | +/-XX% | A/B |
| Clicks | [value] | [value] | +/-XX% | A/B |
| CTR | X.XX% | X.XX% | +/-XX% | A/B |
| Conversions | [value] | [value] | +/-XX% | A/B |
| Conv. Rate | X.XX% | X.XX% | +/-XX% | A/B |
| CPA | [amount] | [amount] | +/-XX% | A/B |
| ROAS | X.XXx | X.XXx | +/-XX% | A/B |
WINNER DECLARATION
WINNER: [A or B]
- Primary KPI ([metric]): [Winner] outperformed by XX%
- Statistical Significance: [Significant / Not Significant / Need More Data]
- Confidence Level: [High / Medium / Low]
KEY INSIGHTS
- [Main takeaway]
- [Secondary insight]
- [Unexpected finding]
RECOMMENDED ACTIONS
- [Action based on results]
- [Action based on results]
CAVEATS
- [Data quality issues, external factors, sample size notes]
EXECUTION STEPS
Step 1: Identify Campaigns to Compare
Ask user for campaign names/IDs and platform, or time periods.
Step 2: Pull Campaign Data
Meta (A/B test): meta_get_insights(account_id="...", level="campaign", filtering=[{"field":"campaign.name","operator":"CONTAIN","value":"CAMPAIGN_A"}], date_preset="last_30d", fields=["spend","impressions","clicks","actions","action_values","ctr","cpc","cpm","purchase_roas"])
Repeat for Campaign B.
Meta (period comparison): Same campaign, different time_range parameters.
Google Ads: google_ads_run_gaql(customer_id="...", query="SELECT campaign.name, metrics.cost_micros, metrics.impressions, metrics.clicks, metrics.conversions, metrics.conversions_value, metrics.ctr, metrics.average_cpc FROM campaign WHERE campaign.name LIKE '%CAMPAIGN_A%' AND segments.date DURING LAST_30_DAYS")
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.
- 8d ago First seen · 98 lines · 28 tokens per session scan A 165bf3505507
campaign-battle-report is a command published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 10d ago), licensed MIT. It adds 28 tokens to every session and 969 once invoked, about $0.0001 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
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.
audit
Google Ads command — audit.
logout
Google Ads command — logout.
status
Google Ads command — status.
checklist
Generate a custom checklist for the current feature based on user requirements.