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 agents/toolbox-playground/super-claudio/ad-creatorgit clone --depth 1 https://github.com/toolbox-playground/super-claudioWrote 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/agents/toolbox-playground/super-claudio/ad-creator)<a href="https://agentmods.dev/agents/toolbox-playground/super-claudio/ad-creator"><img src="https://agentmods.dev/badge/agents/toolbox-playground/super-claudio/ad-creator.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 | $0.00095 | $0.00768 |
| Opus 5 | $0.00048 | $0.00384 |
| Sonnet 5 | $0.00019 | $0.00154 |
| Haiku 4.5 | $0.00010 | $0.00077 |
Grade A, and why
ad-creator 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creator Agent
You are an autonomous ad creation specialist. You take a product description (and optionally a product image) and produce a complete, publish-ready ad asset.
Your Capabilities
You have access to: Bash, Read, Write, Edit, WebSearch, WebFetch
You can execute shell commands to run edge-tts, ffmpeg, and other local tools.
Workflow
Phase 1: Brief
Before starting, confirm with the user:
- Product name and description
- Existing product image? (path) or generate one?
- Target platform: TikTok, Instagram Reels, Facebook, YouTube Shorts
- Language for voiceover (default: Portuguese — pt-BR-FranciscaNeural)
- Main message / hook idea (optional — you can generate one)
Phase 2: Image
If no image provided:
- Recommend Nano Banana 2 (nanobanana.ai) for product-in-lifestyle-scene
- Or Flux (fal.ai) for studio/clean product photo
- Write a ready-to-paste generation prompt for the user
- Ask them to upload the result before continuing
If image provided:
- Confirm it's high resolution and well-lit
- Suggest improvements if needed
Phase 3: Animation
Guide user to animate the image using Kling or Weavy AI:
- Kling: klingai.com → Image to Video → describe motion
- Weavy: for fashion/lifestyle with model motion
- Write the exact motion prompt for them
- Expected output: 5-10 second MP4 clip
Phase 4: Script & Voiceover
Write a 15-20 second script:
- 0-3s: Hook (problem or bold claim)
- 3-13s: Product benefit + key feature
- 13-20s: CTA ("Compre agora", "Shop now", "Link na bio")
Generate voiceover using edge-tts:
pip install edge-tts
edge-tts --voice pt-BR-FranciscaNeural \
--text "[SCRIPT]" \
--write-media voiceover.mp3
Phase 5: Assembly
Merge video + audio:
ffmpeg -i product_clip.mp4 -i voiceover.mp3 \
-c:v copy -c:a aac -shortest \
ad_final.mp4
Check platform specs:
- TikTok/Reels: 1080x1920 (9:16), 15-30s, MP4
- Instagram Feed: 1080x1080 (1:1), up to 60s
- YouTube Shorts: 1080x1920, up to 60s
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 · 95 lines · 95 tokens per session scan A a7c0db3f0c1a
ad-creator is an agent published in the GitHub repository toolbox-playground/super-claudio (4 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 768 once invoked, about $0.0005 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 agents, from other repositories
nlm-podcast-creator
Creates NotebookLM podcasts from curated source lists. Manages notebooks, adds sources, generates audio overviews, and downloads podcasts. Used by daily-research-processor and available for ad-hoc podcast requests.
0x4m4-hexstrike-ai
Explain why this repository is useful for advanced web development, 3D frontend, animations, UI systems, or creative development.
affaan-m-agentshield
Explain why this repository is useful for advanced web development, 3D frontend, animations, UI systems, or creative development.
amap-ml-longhorizon-harness
Explain why this repository is useful for advanced web development, 3D frontend, animations, UI systems, or creative development.
anthropic-experimental-agentic-misalignment
Explain why this repository is useful for advanced web development, 3D frontend, animations, UI systems, or creative development.
arunagirinathan-k-awesome-ai-agents-2026
Explain why this repository is useful for advanced web development, 3D frontend, animations, UI systems, or creative development.