agentmods.dev

new-client-launch

new-client-launch is a command for coding agents from Ad-Superpowers/ad-superpowers-plugin. It costs 16 tokens per session (589 once invoked), scanned A, original, MIT.

A step-by-step workflow for bringing on a new advertising client and preparing their campaigns for launch.

In plain words
What is it for?
Use it to gather business goals and budgets, review connected platforms, audit Google Tag Manager and Google Analytics 4, check advertising pixels, and flag tracking gaps.
Why use it?
It organizes discovery, tracking checks, research, and setup so important launch requirements are not missed.

Command

Part of the ad-superpowers plugin — 17 skills, 35 commands, 5 agents, 1 MCP server shipped together

not rated 5 5d ago A scan 16 tokens original MIT
View the source file Ad-Superpowers/ad-superpowers-plugin
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/ad-superpowers/ad-superpowers-plugin/new-client-launch
Clone the repo
git clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-plugin

Or install ad-superpowers, the plugin that ships this one along with the rest of its 17 skills, 35 commands, 5 agents, 1 MCP server.

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 new-client-launch

README.md
[![agentmods](https://agentmods.dev/badge/commands/ad-superpowers/ad-superpowers-plugin/new-client-launch.svg)](https://agentmods.dev/commands/ad-superpowers/ad-superpowers-plugin/new-client-launch)
Your own site
<a href="https://agentmods.dev/commands/ad-superpowers/ad-superpowers-plugin/new-client-launch"><img src="https://agentmods.dev/badge/commands/ad-superpowers/ad-superpowers-plugin/new-client-launch.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 589 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 $0.00016 $0.00589
Opus 5 $0.00008 $0.00295
Sonnet 5 $0.00003 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 3d ago against content hash 0339bcc71949, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-client-launch 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 3d 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.

plugin/commands/new-client-launch.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Client Launch

Guide the user through a complete new client/account onboarding workflow. This is a structured, multi-step process.

Phase 1: Discovery (Gather Information)

Ask the user for:

  1. Business type: E-commerce, Lead Gen, SaaS, Local Business, or other
  2. Platforms to use: Which ad platforms are connected? Check with meta_list_ad_accounts, google_ads_list_accounts, linkedin_list_ad_accounts, tiktok_get_advertiser_info
  3. Monthly budget: Total and per-platform allocation
  4. Primary KPI: Revenue/ROAS, Leads/CPL, Traffic, Brand Awareness
  5. Target audience: Who is the ideal customer?
  6. Current performance: Pull existing data if accounts have history

Phase 2: Tracking Audit

  1. GTM Check: gtm_list_containers → gtm_audit — are tracking tags properly configured?
  2. GA4 Check: ga4_list_properties → ga4_run_report — are events firing correctly?
  3. Platform pixels: Verify Meta Pixel, Google Ads tag, LinkedIn Insight Tag, TikTok Pixel are installed
  4. Flag issues: List any tracking gaps that need fixing before launch

Phase 3: Competitive & Market Research

  1. Keyword landscape: google_ads_run_keyword_planner for search volume and competition
  2. Organic position: gsc_search_analytics for existing organic rankings
  3. Existing performance: Pull last 30 days from any active campaigns

Phase 4: Campaign Strategy

Based on discovery, recommend:

  1. Channel mix with budget per platform
  2. Campaign structure per platform
  3. Target audiences per platform
  4. Creative requirements (formats, messaging themes)
  5. KPI targets with benchmarks

Phase 5: Launch Checklist

Present a checklist before execution:

  • Tracking verified on all platforms
  • Audiences created and exclusions set
  • Campaign structure approved
  • Creatives ready
  • Budget confirmed
  • Attribution windows configured
  • Reporting cadence agreed (weekly/bi-weekly)

Phase 6: 30/60/90 Day Plan

Read the full file on GitHub · 59 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. 3d ago First seen · 59 lines · 16 tokens per session scan A 0339bcc71949

Subscribe to this mod's changes

new-client-launch is a command published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 589 once invoked, about $0.0001 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.

Marketing and SEOProject managementadvertisingattributioncampaign-optimizationclaudeclaude-codega4
Related

Other commands, from other repositories

refresh-brand-context

Re-scan brand docs and update CLAUDE.md with latest info.

amekala/ads-mcp · 14 tokens

feed-audit

Audit Merchant Center feed quality — disapprovals, attributes, identifiers, custom labels.

HYPD-AI/ads-mcp-plugin · 16 tokens

keywords

Keyword research — for a new search campaign or to expand an existing one, with volumes and CPCs.

HYPD-AI/ads-mcp-plugin · 20 tokens

campaign

Reklam videosu kampanyası kurar — röportaj yapar, yaratıcı ekiple kurguyu çıkarır, planı onayına sunar ve fal.ai'a import edilecek workflow.json'u üretir.

mertagralii/fal.ai-butler · 47 tokens

setup

First-run setup for the ga-mcp-full MCP server — install the CLI if needed, then complete the browser login.

ringo380/ga-mcp-full · 24 tokens

auth-logout

Clear cached Google Analytics OAuth credentials for the ga-mcp-full MCP server.

ringo380/ga-mcp-full · 15 tokens