fb-ads-automation: Command for Claude Code

.claude/commands/fb-ads/generate-creative.md

generate-creative is a command for Claude Code from shashankrai1983/fb-ads-automation. It costs 0 tokens per session (237 once invoked), scanned A, original, MIT.

A command for generating images, videos, and carousel assets for Facebook Ads with AI. It uses a client’s brand context and a creative brief before generating and uploading approved work.

In plain words
What is it for?
Use it to define the asset type, placement, provider, concept, references, and copy; generate the assets; review them; and assemble approved creatives on Facebook.
Why use it?
It organises the path from an advertising idea to reviewed assets and keeps generated campaigns paused until approval.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is shashankrai1983/fb-ads-automation's own configuration. It tells Claude Code how to work on fb-ads-automation itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fb-ads-automation configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shashankrai1983/fb-ads-automation. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shashankrai1983/fb-ads-automation/main/.claude/commands/fb-ads/generate-creative.md
Clone the repo
git clone --depth 1 https://github.com/shashankrai1983/fb-ads-automation

Made for: Claude Code.

Wrote 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.

agentmods badge for generate-creative

README.md
[![agentmods](https://agentmods.dev/badge/commands/shashankrai1983/fb-ads-automation/generate-creative/github.svg)](https://agentmods.dev/commands/shashankrai1983/fb-ads-automation/generate-creative)
Your own site
<a href="https://agentmods.dev/commands/shashankrai1983/fb-ads-automation/generate-creative"><img src="https://agentmods.dev/badge/commands/shashankrai1983/fb-ads-automation/generate-creative/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.

agentmods 80×15 button for generate-creative

Your own site · 80×15
<a href="https://agentmods.dev/commands/shashankrai1983/fb-ads-automation/generate-creative"><img src="https://agentmods.dev/badge/commands/shashankrai1983/fb-ads-automation/generate-creative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 237 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00237
Opus 5 $0.00000 $0.00118
Sonnet 5 $0.00000 $0.00047
Haiku 4.5 $0.00000 $0.00024

Measured 9d ago against content hash 06096b60786f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

generate-creative 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 9d 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.

.claude/commands/fb-ads/generate-creative.md · 23 lines

What it actually says

Generate AI-powered visual assets (images, videos, carousels) for Facebook Ads.

Argument: $ARGUMENTS (client slug, e.g., "sunrise-cafe")

Instructions

  1. Load the Creative Generator agent: read agents/creative-generator.md and follow its complete workflow.

  2. Resolve the client from the argument:

    • If $ARGUMENTS is provided, use it as the client slug
    • If no argument, read knowledge/accounts.md and ask which client
  3. Follow the agent's 6-step workflow:

    • Step 1: Load knowledge context + verify Visual Direction is populated
    • Step 2: Collect creative brief (asset type, provider, placement, concept, references, copy)
    • Step 3: Engineer the generation prompt from brief + brand voice
    • Step 4: Generate assets (after prompt approval)
    • Step 5: User reviews generated assets
    • Step 6: Upload approved assets + assemble creative on Facebook
  4. All entities are created PAUSED. Two-stage approval required at every write step.

Changes

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.

  1. 9d ago First seen · 23 lines · 0 tokens per session scan A 06096b60786f

Subscribe to this mod's changes

generate-creative is a command published in the GitHub repository shashankrai1983/fb-ads-automation (0 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 237 tokens. 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 2026-09-01.