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/seancrowe01/ads-machine/ad-analyzergit 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-analyzer)<a href="https://agentmods.dev/commands/seancrowe01/ads-machine/ad-analyzer"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-analyzer.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 | $0.00047 | $0.03030 |
| Opus 5 | $0.00023 | $0.01515 |
| Sonnet 5 | $0.00009 | $0.00606 |
| Haiku 4.5 | $0.00005 | $0.00303 |
Grade A, and why
ad-analyzer scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -L -o /tmp/ads-machine/{ad_archive_id}.mp4 --max-time 60 "{video_url}" How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Analysis Engine
You are a creative analysis system. You process unanalyzed ads from the Swipe File -- downloading videos, transcribing speech, extracting hooks, classifying angles and formats, running visual analysis, and scoring each ad.
What you produce: Fully enriched Swipe File records with transcripts, hooks, classifications, visual analysis, and composite scores -- ready for /ad-ideator to work from.
Prerequisites
- Airtable MCP connected
- Unanalyzed ads in the Swipe File (run
/ad-pollerfirst) - ffmpeg installed -- for audio extraction (check:
ffmpeg -version) - whisper.cpp installed -- for transcription (check:
whisper-cli --help)- If not installed, skip transcription and note it in the summary
- Gemini API key in
.envasGEMINI_API_KEY(optional -- for visual analysis)
Config
Read from CLAUDE.md:
Airtable Base ID: YOUR_AIRTABLE_BASE_ID
Ad Swipe File Table: YOUR_SWIPE_FILE_TABLE_ID
Step 1: Fetch Unanalyzed Ads
Use Airtable MCP: list_records
base_id: {from CLAUDE.md}
table_id: {Swipe File table ID}
filter: {Is Analyzed} = FALSE()
fields: Ad Archive ID, Competitor, Display Format, Body Text, Title, Video URL, Image URL, Hook Copy
Print count: Found {N} unanalyzed ads to process.
If the user passed a count argument, limit to that many. Otherwise process all.
Step 2: Process Video Ads
For each ad where Display Format = Video AND Video URL exists:
2a. Download Video
mkdir -p /tmp/ads-machine
curl -s -L -o /tmp/ads-machine/{ad_archive_id}.mp4 --max-time 60 "{video_url}"
If download fails, log it and continue to the next ad.
2b. Get Metadata
ffprobe -v quiet -print_format json -show_format -show_streams /tmp/ads-machine/{ad_archive_id}.mp4
Extract:
duration(seconds, rounded)widthandheight-> calculate aspect ratio:
ratio = width / height
if abs(ratio - 9/16) < 0.05: aspect = "9:16"
elif abs(ratio - 4/5) < 0.05: aspect = "4:5"
elif abs(ratio - 1) < 0.05: aspect = "1:1"
elif abs(ratio - 16/9) < 0.05: aspect = "16:9"
else: aspect = "Other"
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.
- 3d ago First seen · 336 lines · 47 tokens per session scan A b034b33c26fe
ad-analyzer is a command published in the GitHub repository seancrowe01/ads-machine (20 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 3,030 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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).
b2b-pipeline-review
B2B lead pipeline review — CPL trends, lead quality scoring, and MQL-to-SQL conversion analysis across LinkedIn and Google Ads.
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.…
channel-strategy-advisor
AI-powered channel selection advisor that matches campaign objectives with optimal platform mix. Analyzes audience fit, platform strengths, funnel stage requirements, and budget constraints to recommend the ideal channel strategy. Includes budget allocation suggestions and expected performance benchmarks per channel.…