fb-ads-automation: Command for Claude Code

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

creative-refresh is a command for Claude Code from shashankrai1983/fb-ads-automation. It costs 0 tokens per session (589 once invoked), scanned A, original, MIT.

A command that reviews ad creative fatigue for a Facebook campaign and prepares a refresh plan. Creative fatigue means an ad may be losing effectiveness because people have seen it too often.

In plain words
What is it for?
Use it to inspect fatigued ads from the past 14 days, analyse their messaging and visuals, and draft two or three new variations for each affected ad.
Why use it?
It connects fatigue findings with the ad’s copy, images, calls to action, landing page, and recent performance so replacement ideas fit the existing campaign.

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/creative-refresh.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 creative-refresh

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/shashankrai1983/fb-ads-automation/creative-refresh"><img src="https://agentmods.dev/badge/commands/shashankrai1983/fb-ads-automation/creative-refresh.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 589 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 $0.00589
Opus 5 $0.00000 $0.00295
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 7d ago against content hash efd72399bcfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 7d 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/creative-refresh.md · 82 lines

What it actually says

Analyze creative fatigue and guide a creative refresh for a campaign.

Argument: $ARGUMENTS (campaign ID)

Steps

  1. Call get_creative_fatigue_report for the specified campaign with days=14.

  2. For fatigued ads (severity = warning or critical): a. Call get_ad for each to get creative details b. Call get_ad_creative for the linked creative ID c. Call get_ad_insights with date_preset=last_14d and time_increment=1 for performance trends

  3. Analyze the existing creative elements:

    • Headlines and body copy
    • Images used
    • CTAs
    • Landing page URLs
  4. Present creative refresh plan:

## Creative Refresh — [Campaign Name]

### Fatigued Creatives
| Ad | Creative | Frequency | CTR Trend | Severity |
|----|----------|-----------|-----------|----------|
[List of fatigued ads with metrics]

### Current Messaging Analysis
- Primary headlines: [List]
- Body copy themes: [Summary]
- CTAs used: [List]
- Images: [Description]

### Suggested New Variations
For each fatigued ad, suggest 2-3 alternatives:

**Ad: [name]**
1. Variation A: [New headline] + [New body copy] + [Same/new CTA]
2. Variation B: [Different angle headline] + [New body copy]
3. Variation C: [Completely different approach]

### Execution Plan
1. Create new creatives (all PAUSED initially)
2. Create new ads linking to existing ad sets
3. Once approved, pause fatigued ads and activate new ones

### Ready to execute?
  1. On approval:

    • Create new ad creatives using create_ad_creative
    • Create new ads using create_ad (status=PAUSED)
    • Only pause old ads and activate new ones after explicit confirmation
  2. After copy variations are created and approved, offer visual refresh:

## Visual Refresh

Your new copy variations are live. Would you also like to generate matching
visual assets (images or video) using AI?

This will use the Creative Generator agent to create on-brand visuals that
complement the new copy.

Options:
1. Yes — generate matching images
2. Yes — generate a short video ad
3. No — keep existing visuals

If yes → load the Creative Generator agent by reading agents/creative-generator.md. Pre-populate the creative brief with:

  • Fatigued ad context (existing visual style, campaign objective)
  • New copy variations (headline + body from the approved options above)
  • Start the brief at question 2 (provider selection) since asset type was chosen above

All write operations require step-by-step user approval.

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. 7d ago First seen · 82 lines · 0 tokens per session scan A efd72399bcfd

Subscribe to this mod's changes

creative-refresh 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 589 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.