agentmods.dev

adextract

adextract is a skill for Claude Code, Codex from ad-vertly/adextract-mcp-server. It costs 37 tokens per session (391 once invoked), scanned A, original, MIT.

A research workflow for studying competitors' online advertisements across Meta, TikTok, Google, and LinkedIn. It finds ads and examines their text, images, videos, emotions, formats, and role in a marketing journey.

In plain words
What is it for?
Use it to find competitor ads, compare creative approaches, explain emotional messages, and infer channel or funnel strategy from current campaigns. A funnel is the path from first awareness to a later action such as a purchase.
Why use it?
It replaces scattered manual searches with a process for finding ads first and analysing the available creative evidence second. It helps compare how brands communicate across advertising platforms.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo yesterday A scan 37 tokens original MIT

Good fit Use it to find competitor ads, compare creative approaches, explain emotional messages, and infer channel or funnel strategy from current campaigns. A funnel is the path from first awareness to a later action such as a purchase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ad-vertly/adextract-mcp-server/adextract
View source ↗ ad-vertly/adextract-mcp-server adextract.co
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 ad-vertly/adextract-mcp-server --skill adextract
Clone the repo
git clone --depth 1 https://github.com/ad-vertly/adextract-mcp-server

Made for: Claude Code, Codex.

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 adextract

README.md
[![agentmods](https://agentmods.dev/badge/skills/ad-vertly/adextract-mcp-server/adextract/github.svg)](https://agentmods.dev/skills/ad-vertly/adextract-mcp-server/adextract)
Your own site
<a href="https://agentmods.dev/skills/ad-vertly/adextract-mcp-server/adextract"><img src="https://agentmods.dev/badge/skills/ad-vertly/adextract-mcp-server/adextract/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 adextract

Your own site · 80×15
<a href="https://agentmods.dev/skills/ad-vertly/adextract-mcp-server/adextract"><img src="https://agentmods.dev/badge/skills/ad-vertly/adextract-mcp-server/adextract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 391 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 $0.00037 $0.00391
Opus 5.5 $0.00015 $0.00156
Sonnet 5.5 $0.00007 $0.00078
Haiku 4.5 $0.00004 $0.00039

Measured yesterday against content hash 6b7ab8da9dae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adextract 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 yesterday.

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.

plugins/adextract/skills/adextract/SKILL.md · 50 lines

What it actually says

adextract

Use this skill when users ask to:

  • find competitor ads
  • analyze top-performing creatives
  • compare brand messaging across platforms
  • explain emotional strategy from ad creatives
  • infer channel strategy from what is currently running

Workflow

  1. Search first, analyze second.
  2. Run searches in parallel when covering multiple platforms.
  3. Use ad_reader on top creatives (image/video URL or thumbnail).
  4. Synthesize cross-platform strategy (format, emotion, funnel role).
  5. If any tool call fails, ask the user to refresh/retry once, then continue.

Key tools

  • search_meta_ads, search_meta_pages, get_meta_page_info, get_meta_ad_details
  • search_google_ads, search_google_ads_advertisers, get_google_ad_details
  • search_linkedin_ads
  • search_tiktok_ads, search_tiktok_advertisers, get_tiktok_ad_details
  • ad_reader

Platform skills (MCP)

For single-library research, read the platform skill resource or use its MCP prompt:

  • Google: adextract://skill/google-ads-research
  • Meta: adextract://skill/meta-ads-research
  • LinkedIn: adextract://skill/linkedin-ads-research
  • TikTok: adextract://skill/tiktok-ads-research

Catalog: adextract://skills

Gotchas

  • TikTok signed media URLs expire quickly; use thumbnails when needed.
  • Google often requires get_google_ad_details to retrieve actual creative assets.
  • Meta can return large payloads; focus analysis on the top results first.
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. yesterday First seen · 50 lines · 37 tokens per session scan A 6b7ab8da9dae

Subscribe to this mod's changes

adextract is a skill published in the GitHub repository ad-vertly/adextract-mcp-server (0 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 391 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-06.

Marketing and SEOResearchad-intelligencead-libraryad-spyai-agentscompetitive-intelligencegoogle-ads
Related

adextract compared with skills from other repositories

adextract next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
adextractad-vertly/adextract-mcp-serverSkill0yesterdayMITA37Claude Code, Codex
admapixfly0pants/admapixSkill62mo agononeA55Claude Code
admapixfly0pants/admapixSkill62mo agononeA55Claude Code, Codex
adspirer-ads-agentLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA141Claude Code, Codex
adsericrisco/rsc-harnessSkill5032d agoMITA81Claude Code, Codex
web-research-workflowyonatangross/orchestkitSkill299yesterdayMITA72Claude Code
google-adsVKirill/claude-lane-stackSkill1248d agoMITA369Claude Code