ad-swipe

ad-swipe is a command for Claude Code from seancrowe01/ads-machine. It costs 35 tokens per session (901 once invoked), scanned A, original, MIT.

A search tool for an advertising swipe file, which is a collection of ads saved for study and inspiration.

In plain words
What is it for?
Use it to filter ads by theme, format, competitor, score, or how long they have run, then review their hooks, copy, and other available details.
Why use it?
It helps find relevant examples without manually searching the whole collection.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/seancrowe01/ads-machine/ad-swipe
Clone the repo
git clone --depth 1 https://github.com/seancrowe01/ads-machine

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 ad-swipe

README.md
[![agentmods](https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-swipe.svg)](https://agentmods.dev/commands/seancrowe01/ads-machine/ad-swipe)
Your own site
<a href="https://agentmods.dev/commands/seancrowe01/ads-machine/ad-swipe"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/ad-swipe.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.00901
Opus 5 $0.00017 $0.00451
Sonnet 5 $0.00007 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 5d ago against content hash f2c45af61162, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ad-swipe 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 5d 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/ad-swipe.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ad Swipe File Browser

You are a swipe file search tool. You help the user find winning ads from their intelligence database by filtering, sorting, and presenting the best matches for their current need.

What you produce: A curated list of winning ads matching the user's criteria -- with hooks, copy, angles, and scores.


Config

Read from CLAUDE.md:

Airtable Base ID: YOUR_AIRTABLE_BASE_ID
Ad Swipe File Table: YOUR_SWIPE_FILE_TABLE_ID

Step 1: Understand What They Need

Ask the user what they are looking for. Common queries:

  • "Show me the top winners" -- sort by Days Active desc, filter Longevity Tier = Long-Runner
  • "Social proof ads" -- filter Angle Category = Social Proof
  • "UGC talking head ads" -- filter Ad Format Type = UGC Talking Head
  • "What is [competitor] running?" -- filter by Competitor name
  • "Long-runners" -- filter Longevity Tier = Long-Runner
  • "Video ads with transcripts" -- filter Display Format = Video, Transcript is not empty
  • "Best hooks" -- sort by Days Active desc, show Hook Video and Hook Copy fields

If the user just says "show me the swipe file" or similar, default to: top 20 ads by Days Active, Longevity Tier = Long-Runner or Performer.


Step 2: Query Airtable

Build a filter formula based on the user's request.

Common filters:

Request Airtable Filter
Winners AND({Status}='Active', {Days Active}>=30)
Long-runners {Longevity Tier}='Long-Runner'
By angle {Angle Category}='{angle}'
By format {Ad Format Type}='{format}'
By competitor FIND('{name}', {Competitor})
Starred {Status}='Starred'
30d+ {Days Active}>=30
Unanalyzed {Is Analyzed}=FALSE()

Combine filters with AND() when multiple criteria are specified.

Sort by Days Active descending unless the user specifies otherwise.

Limit to 20 results unless the user asks for more.


Step 3: Present Results

Display results in a scannable format:

Read the full file on GitHub · 109 lines

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. 5d ago First seen · 109 lines · 35 tokens per session scan A f2c45af61162

Subscribe to this mod's changes

ad-swipe is a command published in the GitHub repository seancrowe01/ads-machine (20 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 901 once invoked, about $0.0002 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 2026-08-30.

Related

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. (requires Pro subscription).

Ad-Superpowers/ad-superpowers-plugin · 43 tokens

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. (requires Pro subscription).

Ad-Superpowers/ad-superpowers-plugin · 27 tokens

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). (requires Pro subscription).

Ad-Superpowers/ad-superpowers-plugin · 64 tokens

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.…

Ad-Superpowers/ad-superpowers-plugin · 56 tokens

channel-strategy-advisor

AI-powered channel selection advisor that matches campaign objectives with optimal platform mix. Analyzes audience fit, platform strengths, funnel stage requirements, and budget constraints to recommend the ideal channel strategy. Includes budget allocation suggestions and expected performance benchmarks per channel.…

Ad-Superpowers/ad-superpowers-plugin · 53 tokens

account-health-scoring

Get a 0-100 health score for each account with prioritized issue list and quick win recommendations. Perfect for managing large portfolios. (requires Pro subscription).

Ad-Superpowers/ad-superpowers-plugin · 31 tokens