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.
npx agentmods add instructions/keith-wohnv/static-ads/claude-mdgit clone --depth 1 https://github.com/keith-wohnv/Static-AdsWrote 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/instructions/keith-wohnv/static-ads/claude-md)<a href="https://agentmods.dev/instructions/keith-wohnv/static-ads/claude-md"><img src="https://agentmods.dev/badge/instructions/keith-wohnv/static-ads/claude-md.svg" alt="Measured on agentmods" 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 | $0.02097 | $0.02097 |
| Opus 5 | $0.01048 | $0.01048 |
| Sonnet 5 | $0.00419 | $0.00419 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade A, and why
Static-Ads CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
Automated static ad generator: Claude Code + Google Gemini (primary) / FAL.ai Nano Banana 2 (backup). Takes brand name + URL, researches the brand, generates 50 ad prompts, fires them to the image generation API, downloads images, and builds an HTML gallery. Based on Alex Cooper's framework.
Key Files
.claude/skills/static-ads/SKILL.md— Canonical skill definition (3-phase pipeline + 50 prompt templates).claude/commands/static-ads.md— Synced copy of SKILL.md for slash command invocationskills/references/generate_ads_gemini.mjs— Primary Node.js generation script (Google Gemini API)skills/references/generate_ads.mjs— Backup Node.js generation script (FAL.ai API)skills/references/gallery-selector.mjs— Standalone script: scans output folder → builds gallery.html with radio-button image selection UI → exportsselections.json.claude/skills/ad-copy-builder/SKILL.md— Ad copy skill: reads selections.json + brand-dna.md + hook-bank.md → writes Ads Uploader CSV.claude/commands/ad-copy-builder.md— Slash command copy of ad-copy-builder skillhook-bank.md— 100 hook frameworks from Hook Bank (D-Double-U Media), tagged by type/awareness/goalbrands/{name}/— Per-brand workspace:product-images/,brand-images/,brand-dna.md,prompts.json,outputs/
4-Phase Pipeline
- Phase 1 (Brand DNA): Firecrawl scrapes brand site + screenshots → Claude visually inspects screenshots (primary color source) → web research →
brand-dna.md+brand-images/ - Phase 2 (Prompts): Fill 50 templates from SKILL.md with brand details →
prompts.json - Phase 3 (Images):
node generate_ads_gemini.mjs→ Gemini API →outputs/{date}-V{n}/+gallery.html(with image selection UI) - Phase 4 (Ad Copy): Open
gallery.html→ pick best image per group → Save Selections → dropselections.jsonin output folder →create copy for [brand] [version]→upload.csv+upload-2.xlsx+copy-summary.md→ upload to Ads Uploader → publish paused
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.
- 4d ago First seen · 136 lines · 2,097 tokens per session scan A 579a257b933f
Static-Ads CLAUDE.md is an instructions file published in the GitHub repository keith-wohnv/Static-Ads (11 stars, last pushed 5mo ago), licensed MIT. It adds 2,097 tokens to every session, about $0.0105 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.
Other instructions, from other repositories
linkedin-content-engine CLAUDE.md
Claude Code instructions for mdbailin/linkedin-content-engine, covering claude implementation brief, goal, architecture constraints, required mcp tools and readbrandprofile.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线（6 步）.
ai-workflow-kit CLAUDE.md
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
glm-image-mcp-server CLAUDE.md
Claude Code instructions for ex-takashima/glm-image-mcp-server, covering claude.md - development guide, project overview, build & run commands, install dependencies and build typescript.
sound-effects-mcp CLAUDE.md
Claude Code instructions for sawa-zen/sound-effects-mcp, covering claude.md, プロジェクト概要, よく使うコマンド, 開発 and テスト.
mcp-svg-marp CLAUDE.md
Claude Code instructions for koppe-pan/mcp-svg-marp, covering mcp-svg-marp tool instructions, mcp tools available, 📊 convertsvgtomarp, 🔍 analyzesvg and automatic slide creation workflow.