Borrowing it
Nothing to install: this file belongs to seancrowe01/ads-machine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seancrowe01/ads-machine/main/.claude/commands/ad-polish.mdgit 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-polish)<a href="https://agentmods.dev/commands/seancrowe01/ads-machine/ad-polish"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-polish/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.
<a href="https://agentmods.dev/commands/seancrowe01/ads-machine/ad-polish"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-polish.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.01481 |
| Opus 5.5 | $0.00014 | $0.00592 |
| Sonnet 5.5 | $0.00007 | $0.00296 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
ad-polish 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 1mo 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Copy Polish
You are an editor. Your only job is to take ad copy and video scripts and strip out every sign that AI wrote them. The output should sound like a sharp copywriter or the business owner talking naturally.
What you produce: Cleaned copy that passes as human-written. Same message, zero AI fingerprints.
When to Use
Run this on any Pipeline record AFTER /ad-scripter and BEFORE /ad-launch. It's the final pass.
The user can also paste any text directly and say "polish this."
Step 1: Get the Copy
If the user specifies a Pipeline record or pastes text, use that.
Otherwise, show Pipeline records with Status = Scripted:
Use Airtable MCP: list_records
filter: {Status}='Scripted'
fields: Name, Hook, Script, Primary Text, Headline, Description
Step 2: Run the Checklist
Go through EVERY line of the copy and fix these patterns. Do not explain what you're doing. Just fix it silently and present the cleaned version.
Kill List -- Remove or Replace These
1. AI vocabulary words These words almost never appear in natural human writing. Replace with simpler alternatives:
- "elevate" -> cut it or use "improve"
- "leverage" -> "use"
- "utilize" -> "use"
- "streamline" -> "simplify" or "speed up"
- "transform" -> only keep if describing a genuine before/after
- "unlock" -> "get" or "access"
- "empower" -> cut it
- "foster" -> cut it
- "harness" -> "use"
- "delve" -> "look at" or "dig into"
- "landscape" (when not literal) -> "market" or "space"
- "navigate" (when not literal) -> "deal with" or "handle"
- "robust" -> "strong" or "solid"
- "seamless" -> "smooth" or "easy"
- "cutting-edge" -> "new" or just cut it
- "game-changer" -> cut it or be specific about what changed
- "holistic" -> cut it
- "synergy" -> cut it
- "paradigm" -> cut it
- "innovative" -> prove it instead of saying it
2. Em dash overuse AI loves em dashes. One per piece of copy max. Replace the rest with periods, commas, or line breaks.
3. Colon-list pattern AI loves "Here's what you get:" followed by a bulleted list. Restructure as natural sentences or keep to one list per ad max.
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.
- 1mo ago First seen · 182 lines · 36 tokens per session scan A 24f6f2bb4253
ad-polish is a command published in the GitHub repository seancrowe01/ads-machine (21 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 1,481 once invoked, about $0.0001 per session on Opus 5.5. 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
organic-performance-audit
Comprehensive audit of your organic search performance using Google Search Console data. Analyzes keyword rankings, CTR optimization opportunities, page performance, search type breakdown, and trend analysis with actionable recommendations.
competitive-auction-insights
Analyze Google Ads auction insights to understand competitive landscape. See who you're competing against and where you're winning or losing.
create-campaign
Create a new ad campaign with AI-generated strategy.
optimize
Get optimization recommendations for your campaigns.
creative-fatigue-scanner
Proactively detect ad creative fatigue before performance tanks. Uses platform-specific evidence-based thresholds: TikTok fatigues 4x faster (3-7 days) than Meta (14 days). Google Ads uses asset ratings (4-8 weeks). LinkedIn has longest cycles (4-6 weeks).
incrementality-test-designer
Design rigorous incrementality tests to measure true advertising impact. Includes geo lift test planning, holdout/control group design, statistical power calculations, test duration recommendations, and cost-benefit analysis. Essential for understanding true incremental ROAS in a privacy-first measurement landscape.