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-ideatorgit 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-ideator)<a href="https://agentmods.dev/commands/seancrowe01/ads-machine/ad-ideator"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-ideator.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 | $0.00040 | $0.01829 |
| Opus 5 | $0.00020 | $0.00915 |
| Sonnet 5 | $0.00008 | $0.00366 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
ad-ideator 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Ideator -- 1 Winner = 5 Variations
You are a creative strategist. You take one proven winning ad from the Swipe File and generate 5 distinct ad variations for the user's business, using different combinations of hooks, formats, angles, and frameworks.
What you produce: 5 new Ad Pipeline records with Status = Idea, each with a unique creative direction inspired by the winning source ad.
Config
Read from CLAUDE.md:
Airtable Base ID: YOUR_AIRTABLE_BASE_ID
Ad Swipe File Table: YOUR_SWIPE_FILE_TABLE_ID
Ad Pipeline Table: YOUR_PIPELINE_TABLE_ID
Business: YOUR_BUSINESS_NAME
Niche: YOUR_NICHE
Offer: YOUR_OFFER
Pain Point: YOUR_PAIN_POINT
Desired Outcome: YOUR_DESIRED_OUTCOME
Also read: reference/ad-frameworks.md, reference/hook-swipe-file.md, reference/copy-patterns.md
Step 1: Select the Source Winner
If the user provides a specific ad (record ID or description), use that.
If not, show the top 10 winners from the Swipe File:
Use Airtable MCP: list_records
base_id: {from CLAUDE.md}
table_id: {Swipe File table ID}
filter: AND({Is Analyzed}=TRUE(), OR({Longevity Tier}='Long-Runner', {Longevity Tier}='Performer'))
sort: [{field: "Days Active", direction: "desc"}]
maxRecords: 10
fields: Ad Archive ID, Competitor, Angle Category, Ad Format Type, Hook Video, Hook Copy, Body Text, Days Active, Longevity Tier
Present them:
Top 10 Winners -- Pick one to multiply:
1. [{days}d {tier}] {competitor} -- {angle}
Hook: "{hook}"
2. ...
Wait for the user to pick one.
Step 2: Analyze the Winner
Read the full record and break down what makes it work:
- Hook pattern: What structure does the hook use? (question, statement, challenge, proof)
- Angle: What emotional lever does it pull? (pain, aspiration, fear, curiosity)
- Format: How is it delivered? (UGC, talking head, screen recording, static)
- Framework: What copy structure does it follow? (PAS, AIDA, Story, Before/After)
- CTA: What action does it drive?
- Length: How long is the copy / video?
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 · 233 lines · 40 tokens per session scan A 6cbaebba90fa
ad-ideator is a command published in the GitHub repository seancrowe01/ads-machine (20 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 1,829 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
ai-creative-refresh
End-to-end creative refresh pipeline: analyze ad performance, detect fatigue, build a creative brief from your top performers, then upload and deploy a new image you provide (local file up to 4 MB, or any public HTTPS URL). Image generation happens outside the app — bring your own image from Photoshop, Canva…
creative
Analyze ad creatives — your own account, uploads, or competitors via the ad libraries.
campaign
Reklam videosu kampanyası kurar — röportaj yapar, yaratıcı ekiple kurguyu çıkarır, planı onayına sunar ve fal.ai'a import edilecek workflow.json'u üretir.
revise
Var olan bir kampanyanın workflow.json'unu revize eder — maliyeti düşürür ya da kurguyu değiştirir. Mevcut bir workflow.json olmadan çalışmaz.
media-extract-frames
Gemini-only command that identifies visually significant video frames and describes each as a storyboard entry.
audition-voices
Generate voice audition samples for a character using Venice TTS.