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/ad-superpowers/ad-superpowers-plugin/ai-creative-refreshgit 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/ai-creative-refresh)<a href="https://agentmods.dev/commands/ad-superpowers/ad-superpowers-plugin/ai-creative-refresh"><img src="https://agentmods.dev/badge/commands/ad-superpowers/ad-superpowers-plugin/ai-creative-refresh.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 | $0.00077 | $0.01594 |
| Opus 5 | $0.00039 | $0.00797 |
| Sonnet 5 | $0.00015 | $0.00319 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
ai-creative-refresh 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platforms: meta 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.
Creative Refresh
End-to-end creative refresh pipeline: analyze performance → detect fatigue → build a creative brief from top performers → upload your new image → deploy as a paused ad for review.
Image generation is intentionally NOT part of this workflow. Use whatever image tool you prefer (Photoshop, Canva, Midjourney, ChatGPT/Gemini in your client, etc.) — this workflow handles everything around the image: the analysis, the brief that tells you what to make, the upload, and the deployment.
Requirements:
- Connected Meta Ads account
- A new image you want to deploy (after Step 5):
- Local file upload: any PNG/JPEG up to 4 MB raw. Your AI client reads and base64-encodes the bytes for you.
- Public URL: any HTTPS link (Canva export, S3, CDN, etc.). No size limit beyond Meta's own (~30 MB).
OUTPUT FORMAT
CREATIVE AUDIT SUMMARY
| Metric | Value |
|---|---|
| Account | {account name} |
| Campaign | {campaign name} |
| Active Ads | {count} |
| Fatigued Ads | {count} |
| Top Performer | {ad name} (CTR: X%, ROAS: Y) |
| Avg Creative Age | {days} days |
TOP PERFORMERS (Reference for the Creative Brief)
| Ad Name | CTR | CPC | ROAS | Impressions | Days Active | Image Style |
|---|
FATIGUED ADS (Need Refresh)
| Ad Name | Frequency | CTR Decline | CPM Change | Days Active | Fatigue Score |
|---|
CREATIVE BRIEF (For You to Execute Externally)
- Visual style: {derived from top performer}
- Subject / focal point: {derived}
- Color palette: {derived}
- Composition / framing: {derived}
- Lighting: {derived}
- Aspect ratio: 4:5
- Variations to produce: 2
- Negative cues (avoid): {derived}
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 · 143 lines · 77 tokens per session scan A 808356fc743d
ai-creative-refresh is a command published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 6d ago), licensed MIT. It adds 77 tokens to every session and 1,594 once invoked, about $0.0004 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
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.
ad-ideator
Take 1 winning ad from the Swipe File and generate 5 ad variations using different hook, format, angle, and framework combinations. Creates new records in the Ad Pipeline.
ad-brief
Generate a production-ready creative brief from a scripted Pipeline ad. Includes shot list, filming card, B-roll suggestions, text overlay specs, and equipment notes. Ready to print and film.
ad-scripter
Write video scripts and ad copy for Pipeline ideas. Generates timed scripts with visual directions, primary text, headline, description, and CTA. Updates Pipeline records to Scripted status.