ad

ad is a command for Claude Code from aaron-he-zhu/aaron-marketing-skills. It costs 50 tokens per session (1,069 once invoked), scanned A, original, Apache-2.0.

A command for running a complete paid-ad workflow, from audience and campaign planning through launch checks, measurement, and attribution.

In plain words
What is it for?
Use it to plan audiences and campaign structure, create ads and tests, check launch readiness, manage budgets and bids, measure results, and reconcile attribution.
Why use it?
It routes a request to the part of the advertising process that matches the user's goal, using exported account data instead of requiring direct access to ad-platform APIs.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the aaron-marketing plugin — 120 skills, 8 commands, 7 hooks shipped together

Good fit Use it to plan audiences and campaign structure, create ads and tests, check launch readiness, manage budgets and bids, measure results, and reconcile attribution.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/aaron-he-zhu/aaron-marketing-skills/ad
About the project

aaron-marketing-skills is a collection of 120 AI-agent skills covering marketing work such as brand narrative, search optimization, social media, email, advertising, influencer campaigns, and launches. Marketers and agent users can install it as a plugin, use its portable skills, or run its described bot team. The catalogue entries are components of this marketing workflow.

aaron-he-zhu/aaron-marketing-skills · 2,767 stars · on GitHub · aaronmarketing.ai

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.

Clone the repo
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills

Made for: Claude Code.

Or install aaron-marketing, the plugin that ships this one along with the rest of its 120 skills, 8 commands, 7 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/aaron-he-zhu/aaron-marketing-skills/ad/github.svg)](https://agentmods.dev/commands/aaron-he-zhu/aaron-marketing-skills/ad)
Your own site
<a href="https://agentmods.dev/commands/aaron-he-zhu/aaron-marketing-skills/ad"><img src="https://agentmods.dev/badge/commands/aaron-he-zhu/aaron-marketing-skills/ad/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 ad

Your own site · 80×15
<a href="https://agentmods.dev/commands/aaron-he-zhu/aaron-marketing-skills/ad"><img src="https://agentmods.dev/badge/commands/aaron-he-zhu/aaron-marketing-skills/ad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,069 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 $0.00050 $0.01069
Opus 5 $0.00025 $0.00535
Sonnet 5 $0.00010 $0.00214
Haiku 4.5 $0.00005 $0.00107

Measured 13d ago against content hash defa85664101, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ad 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 13d 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.

commands/ad.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the paid-ads lifecycle along the ROAS loop (Research → Orchestrate → Activate → Scale). Skills score on the ROAS framework and operate from the user's own-account manual export — keyed ad-platform APIs are never required.

Route

Infer the ROAS-loop phase from the goal (or honor --phase) and route to the matching skill:

  • Research — campaign-architect (account/campaign structure), audience-segment-builder (segments), search-term-miner (converting-query mining + negative-keyword lists), product-feed-optimizer (Shopping/PMax feed, title/attribute fixes); reuse budget-optimizer for spend; consult offer-claims-registry's live-offers table (memory/claims/offers.md) when structuring promo campaigns
  • Orchestrate — ad-creative-builder, ad-test-designer, bid-strategy-planner (tCPA/tROAS target + learning-phase entry), landing-experience-checker (pre-launch Quality-Score + ad-to-page message-match preflight); reuse landing-optimizer for the post-click page; read approved wording from the claims projection and submit [needs source] items as operation: propose events to the claims registry
  • Activate — choose the sibling that matches the request; this is a capability menu, not an automatic four-skill chain: conversion-signal-qa (build/verify tracking), placement-exclusion-manager (brand-safety exclusion lists), conversion-value-mapper (margin→value so tROAS optimizes profit, not orders), or ad-account-auditor (the RQS gate + launch go/no-go; O1/O2 judged against offer-claims-registry's ledger). A pre-launch account-audit request follows the exact narrow chain conversion-signal-qa first → ad-account-auditor; do not insert the placement or value builders unless the user separately requests that work or the completed gate routes a specific finding to remediation.
  • Scale — paid-measurement-loop, attribution-reconciler, budget-pacing-monitor (over/under-spend pacing), fatigue-frequency-manager (frequency/CTR decay + creative rotation); reuse roi-calculator / report-generator / performance-analyzer

Read the full file on GitHub · 31 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. 13d ago First seen · 31 lines · 50 tokens per session scan A defa85664101

Subscribe to this mod's changes

ad is a command published in the GitHub repository aaron-he-zhu/aaron-marketing-skills (2,767 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 1,069 once invoked, about $0.0003 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.