A tool for preparing online advertising materials for a landing page or its test version. UTM tags are labels added to links so analytics can identify where visitors came from.

Use it to prepare materials for Yandex Direct and Google Ads, including ad text, keywords, negative keywords, UTM links, and upload files for their editing tools.

It gathers the text, search terms, exclusions, and tracking links needed for an ad campaign without creating the campaign or spending money. It also helps keep advertising data consistent with analytics and A/B-test data.

landing-ads — Skill for Claude Code by monthu56/landforge

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/monthu56/landforge

agentmods

npx agentmods add skills/monthu56/landforge/landing-ads

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/monthu56/landforge/landing-ads/github.svg)](https://agentmods.dev/skills/monthu56/landforge/landing-ads)

Your own site

<a href="https://agentmods.dev/skills/monthu56/landforge/landing-ads"><img src="https://agentmods.dev/badge/skills/monthu56/landforge/landing-ads/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/monthu56/landforge/landing-ads"><img src="https://agentmods.dev/badge/skills/monthu56/landforge/landing-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,102 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.

Model	Per session	Once invoked
Fable 5.1	$0.00106	$0.01102
Opus 5.5	$0.00042	$0.00441
Sonnet 5.5	$0.00021	$0.00220
Haiku 4.5	$0.00011	$0.00110

Measured 2mo ago against content hash 8fc46180cf05, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

landing-ads 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build_utm.py, scripts/check_ads.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/init-landing-system/reference/system/skills/landing-ads/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

landing-ads — рекламные материалы для лендинга

Готовит всё, что нужно загрузить в рекламные кабинеты на лендинг (или вариант A/B): UTM-ссылки, тексты объявлений в рамках форматов, ключевые фразы и минус-слова, экспорт-файлы. Артефакты, не запуск. Токенов на API сейчас нет (ADR-0007), поэтому skill не создаёт кампании и ничего не тратит — только собирает материалы и инструкции.

Жёсткие правила

Деньги — решение человека. Skill НЕ запускает кампании и НЕ тратит бюджет. Он отдаёт материалы + инструкцию по загрузке. Запуск, ставки и бюджет выставляет человек.
Правдивость (правила копирайта проекта). Объявления не обещают того, чего нет: без выдуманных цифр, гарантий, «№1», несуществующих акций. Источник фактов — бриф (в будущем — RAG по базе знаний).
UTM консистентны с аналитикой. Разметка должна сходиться с целями Метрики/GA4 и метками A/B-варианта, иначе статистику по каналам/вариантам не свести (см. landing-experiment).
Трафик-гейт. Лить платный трафик имеет смысл, когда лендинг готов к замерам (аналитика подключена). Предупреди, если запускают рекламу на неготовую к конверсии страницу.

Workflow

1. Вход

Бриф (оффер, аудитория, SEO-тема, ограничения) — формат в .claude/skills/new-landing/reference/brief-schema.md.
URL лендинга (прод) и, если это A/B, — id эксперимента и список вариантов.
Каналы: Яндекс.Директ и/или Google Ads.

2. UTM-разметка

python3 .claude/skills/landing-ads/scripts/build_utm.py \
  --url https://example.com/ --campaign <slug> [--channels yandex,google] [--variants A,B]

Схема и соглашения — reference/utm-scheme.md. Выдаёт таблицу ссылок (канал × вариант) и CSV в ads/<campaign>/utm.csv.

3. Тексты объявлений

Сгенерируй по reference/ad-formats.md (лимиты символов и количество для каждого канала; правила копирайта). Под каждый канал, при A/B — под каждый вариант (с соответствующим utm_content). Сохрани в ads/<campaign>/ads.<channel>.json.

Read the full file on GitHub · 71 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 71 lines · 106 tokens per session scan A 8fc46180cf05

Subscribe to this mod's changes

landing-ads is a skill published in the GitHub repository monthu56/landforge (11 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 1,102 once invoked, about $0.0004 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 2026-08-31.

Analytics and metrics Claude Code Marketing and SEO ab-testing claude-skills landing page landing-page-generator marketing

landing-ads next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
landing-adsmonthu56/landforge	Skill	11	5mo ago	MIT	A	106	Claude Code
landing-page-scaffoldserejaris/kimi-skills	Skill	11	3mo ago	MIT	A	81	Claude Code, Codex
Landing Page Copy ImproverNotysoty/openagentskills	Skill	9	2mo ago	MIT	A	24	Claude Code, Codex
ads-performance-analyticsrampstackco/claude-skills	Skill	1.0k	11d ago	MIT	A	147	Claude Code
paid-media-strategyrampstackco/claude-skills	Skill	1.0k	11d ago	MIT	A	142	Claude Code
ads-creative-developmentrampstackco/claude-skills	Skill	1.0k	11d ago	MIT	A	124	Claude Code
ecommerce-full-pipelineanbeime/skill	Skill	9.2k	yesterday	none	A	96	Claude Code, Codex