ad-copy-builder

ad-copy-builder is a command for Claude Code from keith-wohnv/Static-Ads. It costs 111 tokens per session (2,785 once invoked), scanned A, original, MIT.

A command that turns selected brand images into advertising text and a CSV file for Meta Ads Uploader, Facebook and Instagram’s ad-upload tool.

In plain words
What is it for?
Use it to create ad copy from a completed image batch and produce one upload-ready CSV for different ad placements.
Why use it?
It removes the manual work of writing copy for each image and formatting the results for upload. It uses the brand’s voice, pricing rules and selected images as input.

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/keith-wohnv/static-ads/ad-copy-builder
Clone the repo
git clone --depth 1 https://github.com/keith-wohnv/Static-Ads

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-copy-builder

README.md
[![agentmods](https://agentmods.dev/badge/commands/keith-wohnv/static-ads/ad-copy-builder.svg)](https://agentmods.dev/commands/keith-wohnv/static-ads/ad-copy-builder)
Your own site
<a href="https://agentmods.dev/commands/keith-wohnv/static-ads/ad-copy-builder"><img src="https://agentmods.dev/badge/commands/keith-wohnv/static-ads/ad-copy-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,785 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 $0.00111 $0.02785
Opus 5 $0.00056 $0.01392
Sonnet 5 $0.00022 $0.00557
Haiku 4.5 $0.00011 $0.00279

Measured 4d ago against content hash 06004890aae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ad-copy-builder 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.

.claude/commands/ad-copy-builder.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ad Copy Builder

Turns a completed image batch into a production-ready Ads Uploader CSV with compliant Meta ad copy drawn from the Hook Bank framework library.

What You Need Before Starting

  1. A completed image batch — e.g. brands/{brand}/outputs/{version}/
  2. selections.json in that folder — from the gallery selector (see below)
  3. brand-dna.md — at brands/{brand}/brand-dna.md

If selections.json is missing, stop and run:

node skills/references/gallery-selector.mjs --output-dir brands/{brand}/outputs/{version} --open

Then: open gallery.html → pick best image per group → Save Selections → copy selections.json into the output folder.


Phase 1 — Load Context

Read these files in parallel:

  • brands/{brand}/brand-dna.md — brand voice, pricing rules, visual identity, key stats
  • brands/{brand}/outputs/{version}/selections.json — which images were chosen
  • hook-bank.md — hook framework library (in project root)

From selections.json, build the working list: one entry per template — { template, images: { '1x1': path, '9x16': path } }. The two ratios are the same ad served on different placements (feed vs. Stories/Reels), so they share one set of copy.


Phase 2 — Match Hooks to Templates

For each template in the selections, pick hook frameworks from hook-bank.md — one per funnel stage (TOF, MOF, BOF).

Read references/template-hook-map.md for the template → hook type → specific hook recommendations.

How to pick the right hook per stage:

  1. Look up the template name in template-hook-map.md to get the recommended hook types
  2. Map those hook types to funnel stages using this guide:
Funnel Stage Audience Preferred Hook Types
TOF (Cold) Never heard of the brand Curiosity gap, Identity call-out, Pain/Empathy, Contrarian, Narrative
MOF (Warm) Visited site, watched video, engaged Social proof, Comparison, Feature callout, Objection removal
BOF (Retargeting) Abandoned checkout / started signup Direct offer, Urgency, Risk reversal, Guarantee

Read the full file on GitHub · 246 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. 4d ago First seen · 246 lines · 111 tokens per session scan A 06004890aae1

Subscribe to this mod's changes

ad-copy-builder is a command published in the GitHub repository keith-wohnv/Static-Ads (11 stars, last pushed 5mo ago), licensed MIT. It adds 111 tokens to every session and 2,785 once invoked, about $0.0006 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.