A command for creating a responsive search ad in Google Ads, with multiple headlines and descriptions that Google can combine for different searches.

Use it to research a campaign, inspect its ad groups and landing page, verify tracking, and draft validated headlines and descriptions in the page's language.

It checks campaign setup, conversion tracking, quality scores, language, and character limits before writing ad copy, helping avoid adding ads when a broader campaign problem needs attention.

create-ad — Command by kLOsk

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/klosk/adloop/create-ad

Clone the repo

git clone --depth 1 https://github.com/kLOsk/adloop

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 371 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00371
Opus 5	$0.00006	$0.00186
Sonnet 5	$0.00002	$0.00074
Haiku 4.5	$0.00001	$0.00037

Measured yesterday against content hash b22e094c32bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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 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.

.claude/commands/create-ad.md · 43 lines

What it actually says

Create a Google Ads responsive search ad for: $ARGUMENTS

1. Research

get_campaign_performance — find campaign structure and campaign.id
run_gaql — get ad group IDs: SELECT ad_group.id, ad_group.name FROM ad_group WHERE campaign.id = {id}
get_tracking_events — verify conversion tracking exists

2. Pre-write validation (CRITICAL)

Before drafting anything, check:

Is the bidding strategy appropriate? MANUAL_CPC = warn user, adding ads won't help before fixing bidding
Does the campaign have conversions? High spend + zero conversions = warn, adding ads won't help
Quality scores? All below 5 = relevance problem, not ad problem
If systemic issues found, warn user before proceeding

3. Landing page analysis

Read the landing page code to extract value propositions
Determine the correct language — if unclear, ASK the user before writing any copy

4. Write ad copy

8-10 diverse headlines (MAX 30 characters each — count every one!)
3-4 descriptions (MAX 90 characters each)
Count characters BEFORE calling draft_responsive_search_ad
Aim for 25 chars on headlines to leave margin
Write in the landing page's language
Make headlines diverse — don't repeat the same message

5. Draft and confirm

Call draft_responsive_search_ad with the copy
Show full preview to user including any warnings
Wait for explicit approval
confirm_and_apply(plan_id=..., dry_run=true) first
Only dry_run=false after user explicitly confirms

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.

yesterday First seen · 43 lines · 12 tokens per session scan A b22e094c32bc

Subscribe to this mod's changes

create-ad is a command published in the GitHub repository kLOsk/adloop (253 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 371 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 2026-08-30.

Analytics and metrics Data and AI Research ai cursor ga4 google-ads google-analytics marketing

create-ad

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

1. Research

2. Pre-write validation (CRITICAL)

3. Landing page analysis

4. Write ad copy

5. Draft and confirm

What this file has done since we first saw it

Other commands, from other repositories

seo-audit

google-docs

setup

auth-login

auth-status

auth-logout