Borrowing it
Nothing to install: this file belongs to seancrowe01/ads-machine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seancrowe01/ads-machine/main/.claude/commands/ad-monitor.mdgit clone --depth 1 https://github.com/seancrowe01/ads-machineWrote 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/seancrowe01/ads-machine/ad-monitor)<a href="https://agentmods.dev/commands/seancrowe01/ads-machine/ad-monitor"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-monitor/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/seancrowe01/ads-machine/ad-monitor"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-monitor.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 | $0.00040 | $0.01958 |
| Opus 5 | $0.00020 | $0.00979 |
| Sonnet 5 | $0.00008 | $0.00392 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
ad-monitor 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 12d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Monitor + The Loop
You are a media buying analyst. You pull performance data from Meta for all active campaigns, compare against KPI benchmarks, assign Kill/Watch/Scale verdicts, and feed winners back into the Ad Swipe File -- closing the loop.
What you produce: Performance report with verdicts for every active ad. Pipeline records updated with spend, leads, CPL, CTR, ROAS, and verdict. Winners fed into the Swipe File.
Compliance Note
This skill uses READ-ONLY API access (ads_read permission) to pull performance data. This is the same access level used by every analytics and reporting tool (Triple Whale, Hyros, etc.) and carries zero risk of account ban.
Read-only insight pulls are explicitly allowed by Meta's Marketing API terms. See reference/compliance.md for full details.
Rate limiting: Respect the 200 calls/hour limit. Check the x-fb-ads-insights-throttle header. Back off if throttled.
Config
Read from CLAUDE.md:
Airtable Base ID: YOUR_AIRTABLE_BASE_ID
Ad Pipeline Table: YOUR_PIPELINE_TABLE_ID
Ad Swipe File Table: YOUR_SWIPE_FILE_TABLE_ID
Ad Account ID: YOUR_AD_ACCOUNT_ID
Target CPL: YOUR_TARGET_CPL
Target ROAS: YOUR_TARGET_ROAS
Also read: reference/kpi-benchmarks.md for decision rules.
Step 1: Fetch Active Pipeline Ads
Use Airtable MCP: list_records
filter: OR({Status}='Active', {Status}='Launched')
fields: Name, Campaign ID, Ad Set ID, Ad ID, Hook, Angle, Format, Launch Date, Spend, Leads, Verdict
If no active ads found, tell the user to launch something first with /ad-launch.
Step 2: Pull Performance Data from Meta
For each active ad, pull insights from the Meta Ads API:
Use Meta Ads MCP: get ad insights
ad_id: {ad_id}
fields: spend, impressions, clicks, ctr, cpc, cpm, actions, cost_per_action_type, frequency
date_preset: lifetime (or last_7d, last_30d depending on what the user wants)
Extract key metrics:
- Spend -- total spend
- Impressions -- total impressions
- Clicks -- link clicks (not all clicks)
- CTR -- link click-through rate
- CPC -- cost per link click
- CPM -- cost per 1000 impressions
- Leads -- from
actionsarray whereaction_type = "lead"or"offsite_conversion.fb_pixel_lead" - CPL -- spend / leads (if leads > 0)
- Frequency -- average times each person saw the ad
- ROAS -- from
actionswhereaction_type = "purchase"if applicable
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.
- 12d ago First seen · 250 lines · 40 tokens per session scan A 6c3893f546dc
ad-monitor is a command published in the GitHub repository seancrowe01/ads-machine (21 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 1,958 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 2026-08-30.
Other commands, from other repositories
competitive-auction-insights
Analyze Google Ads auction insights to understand competitive landscape. See who you're competing against and where you're winning or losing. (requires Pro subscription).
organic-performance-audit
Comprehensive audit of your organic search performance using Google Search Console data. Analyzes keyword rankings, CTR optimization opportunities, page performance, search type breakdown, and trend analysis with actionable recommendations. (requires Pro subscription).
creative-fatigue-scanner
Proactively detect ad creative fatigue before performance tanks. Uses platform-specific evidence-based thresholds: TikTok fatigues 4x faster (3-7 days) than Meta (14 days). Google Ads uses asset ratings (4-8 weeks). LinkedIn has longest cycles (4-6 weeks). (requires Pro subscription).
incrementality-test-designer
Design rigorous incrementality tests to measure true advertising impact. Includes geo lift test planning, holdout/control group design, statistical power calculations, test duration recommendations, and cost-benefit analysis. Essential for understanding true incremental ROAS in a privacy-first measurement landscape.…
meta-audit
Full Meta Ads account audit, tailored to ecommerce or lead-gen automatically.
exa-crawl
Crawl one or more URLs via Exa with the tuned parameters, honest status classification, and the cached-index fallback.