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/anomaly-detective)<a href="https://agentmods.dev/commands/ad-superpowers/ad-superpowers-plugin/anomaly-detective"><img src="https://agentmods.dev/badge/commands/ad-superpowers/ad-superpowers-plugin/anomaly-detective.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 5.1 | $0.00040 | $0.01425 |
| Opus 5 | $0.00020 | $0.00713 |
| Sonnet 5 | $0.00008 | $0.00285 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
anomaly-detective 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 7d 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 — 121 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.
Anomaly Detective
Scan all accounts for unusual performance anomalies. Sensitivity: medium.
OUTPUT FORMAT (CRITICAL - follow this EXACT structure)
EXECUTIVE SUMMARY
| Severity | Count | Daily Budget at Risk |
|---|---|---|
| CRITICAL | ||
| HIGH | ||
| MEDIUM | ||
| LOW | ||
| Total Weekly Impact if Unaddressed | amount |
CRITICAL - ACT NOW (0-4 hours)
For each:
| Account | Platform | Anomaly | Change | Daily Impact | Root Cause | Action |
|---|
HIGH - ACT TODAY (4-24 hours)
Same table format as CRITICAL.
MEDIUM - MONITOR (24-48 hours)
| Account | Platform | Anomaly | Change | Seasonal? | Recommendation |
|---|
LOW - REVIEW THIS WEEK
Bullet list: [Account]: [metric] [change]% - [context]
SEASONALITY CONTEXT
| Account | Anomaly | Seasonal? | Confidence | Expected Pattern |
|---|---|---|---|---|
| (Mark: YES = don't panic | MAYBE = monitor | NO = investigate) |
INVESTIGATION CHECKLISTS
Conversion drops: Pixel/tag firing? Landing page loading? Checkout flow? Payment processing? Ad disapprovals? Spend spikes: Budget caps? Bid strategy? Bid limits? Audience expansion?
NO ANOMALIES
[List accounts with stable performance - GREEN status]
EXECUTION STEPS
Step 1: Discover Accounts
meta_list_ad_accounts()google_ads_list_accounts()linkedin_list_ad_accounts()tiktok_get_advertiser_info()
Step 2: Pull Time-Series Data (Last 14 Days, Daily Granularity)
Meta: meta_get_insights(account_id="FROM_STEP_1", date_preset="last_14d", level="account", fields=["spend","impressions","clicks","actions","action_values","cpm","cpc","ctr","purchase_roas"], time_increment=1)
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.
- 7d ago First seen · 121 lines · 40 tokens per session scan A 4dd526ed7759
anomaly-detective is a command published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 1,425 once invoked, about $0.0002 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.
logout
Google Ads command — logout.
status
Google Ads command — status.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.