adspirer-get-started

adspirer-get-started is a skill for Claude Code, Codex from amekala/ads-mcp. It costs 168 tokens per session (2,201 once invoked), scanned D, original, MIT.

A setup guide for Adspirer, an AI advertising agent that connects to advertising accounts on Google, Meta, TikTok, LinkedIn, Amazon, and ChatGPT Ads. It guides authentication and linking at least one advertising platform.

In plain words
What is it for?
Installing or updating Adspirer, connecting advertising accounts, and getting ready to manage campaigns across the supported advertising platforms.
Why use it?
It removes the manual work of installing the connection and figuring out how to authorize advertising accounts before using them from an AI assistant.

Skill for Claude CodeCodex

Written for Claude Code and Codex: Claude Code plugin machinery, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the adspirer-advertising-agent plugin — 19 skills, 5 commands, 1 agent, 2 MCP servers shipped together

Good fit Installing or updating Adspirer, connecting advertising accounts, and getting ready to manage campaigns across the supported advertising platforms.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amekala/ads-mcp/adspirer-get-started
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.

Any agent
npx skills add amekala/ads-mcp --skill adspirer-get-started
Clone the repo
git clone --depth 1 https://github.com/amekala/ads-mcp

Made for: Claude Code, Codex.

Or install adspirer-advertising-agent, the plugin that ships this one along with the rest of its 19 skills, 5 commands, 1 agent, 2 MCP servers.

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 adspirer-get-started

README.md
[![agentmods](https://agentmods.dev/badge/skills/amekala/ads-mcp/adspirer-get-started/github.svg)](https://agentmods.dev/skills/amekala/ads-mcp/adspirer-get-started)
Your own site
<a href="https://agentmods.dev/skills/amekala/ads-mcp/adspirer-get-started"><img src="https://agentmods.dev/badge/skills/amekala/ads-mcp/adspirer-get-started/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 adspirer-get-started

Your own site · 80×15
<a href="https://agentmods.dev/skills/amekala/ads-mcp/adspirer-get-started"><img src="https://agentmods.dev/badge/skills/amekala/ads-mcp/adspirer-get-started.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00168 $0.02201
Opus 5 $0.00084 $0.01100
Sonnet 5 $0.00034 $0.00440
Haiku 4.5 $0.00017 $0.00220

Measured 11d ago against content hash 26ec209e053b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade D, and why

adspirer-get-started scanned grade D with 3 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 11d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

(or `curl -fsSL https://www.adspirer.com/install.sh | bash`).

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Codex (`~/.codex/config.toml`) | **Codex** |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(or `curl -fsSL https://www.adspirer.com/install.sh | bash`).
skills/adspirer-get-started/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Get started with Adspirer

Skill version: 1.2.1

Act immediately. When this skill loads — whether installed, fetched from a URL, or pasted into the chat — start the flow now: detect the environment, present the single next action, and guide the user through it. Do not summarize these instructions, list the options, or ask what they'd like to do first.

Adspirer connects AI assistants to the user's real ad accounts — 400+ tools across Google Ads, Meta Ads, TikTok Ads, LinkedIn Ads, Amazon Ads, and ChatGPT Ads — through one remote MCP server:

https://mcp.adspirer.com/mcp

Your job with this skill: get the user from "nothing installed" to a working, authenticated Adspirer connection with at least one ad platform linked, then hand off to their first real task.

To install or update this skill: npx skills add amekala/ads-mcp --skill adspirer-get-started -g (or curl -fsSL https://www.adspirer.com/install.sh | bash).

Current docs

Instructions drift. For anything not covered here — pricing, plans, quotas, troubleshooting, a client not listed below — read the live docs before answering, and trust them over this file:

Step 1 — Detect the environment

First decide which KIND of client this is, because the install paths are completely different:

  • Chat app (Claude web/desktop/mobile, Claude Cowork, ChatGPT app): no shell, no filesystem. NEVER give these users terminal commands — give them the official directory listing to click and in-app steps.
  • Coding agent (Claude Code, Cursor, Codex, Gemini CLI): has a shell and config files; use the plugin/config installs.

Then identify the specific client:

Signal Environment
You can run shell commands and CLAUDECODE=1 is set Claude Code
You are Claude with connectors/apps but no local shell Claude web/desktop or Cowork (chat app)
You are ChatGPT ChatGPT app (chat app)
Cursor (rules, ~/.cursor/) Cursor
Codex (~/.codex/config.toml) Codex
Gemini CLI Gemini CLI

Read the full file on GitHub · 213 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. 11d ago First seen · 213 lines · 168 tokens per session scan D 26ec209e053b

Subscribe to this mod's changes

adspirer-get-started is a skill published in the GitHub repository amekala/ads-mcp (89 stars, last pushed 4d ago), licensed MIT. It adds 168 tokens to every session and 2,201 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

adspirer-ads-agent

Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 100+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…

LeoYeAI/openclaw-master-skills · 141 tokens

adcp-advertising

Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…

LeoYeAI/openclaw-master-skills · 103 tokens

_mureo-shared

Skill "_mureo-shared" from logly/mureo, covering mureo shared patterns, installation, setup, claude code (recommended) and manual configuration.

logly/mureo · 22 tokens

_mureo-strategy

Strategy Context: Manage business strategy files (STRATEGY.md, STATE.json) for strategy-driven ad operations.

logly/mureo · 28 tokens

daily-check

Run a daily health check on all configured ad accounts (Google Ads, Meta Ads, Amazon Ads, TikTok Ads, Search Console, GA4, and any configured plugin platform). Use when the user asks for a daily review, health check, status update, anomaly detection, or 'how are my campaigns doing today'. Reads STRATEGY.md and…

logly/mureo · 145 tokens

_mureo-google-ads

Google Ads: Manage campaigns, ad groups, ads, keywords, budgets, and performance analysis.

logly/mureo · 26 tokens