create-campaign

A command for creating Google Ads search campaigns after checking existing campaigns, budgets, bidding, keywords, and conversion tracking.

In plain words
What is it for?
Use it to estimate a budget, choose campaign settings, draft ad groups and keywords, and review warnings before launch.
Why use it?
It reduces the risk of duplicating campaigns or spending money before tracking, budget, and bidding settings are suitable.

Command for Claude Code

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-campaign
Clone the repo
git clone --depth 1 https://github.com/kLOsk/adloop

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 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 $0.00010 $0.00417
Opus 5 $0.00005 $0.00209
Sonnet 5 $0.00002 $0.00083
Haiku 4.5 $0.00001 $0.00042

Measured 2d ago against content hash 2a2cf424ea78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-campaign 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 2d 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.

.claude/commands/create-campaign.md · 47 lines

What it actually says

Create a new Google Ads campaign for: $ARGUMENTS

1. Research existing structure

  • get_campaign_performance — understand existing campaigns, avoid duplicate names
  • Check what's already running and what bidding strategies are in use

2. Budget estimation

  • If user hasn't specified a budget, call estimate_budget with proposed keywords
  • Ask for target geography and language if not clear (common: 2276=Germany, 2840=USA, 2826=UK)
  • Present the forecast: estimated clicks, impressions, cost, avg CPC

3. Pre-write checks (CRITICAL)

  • Bidding strategy: recommend MAXIMIZE_CONVERSIONS or TARGET_CPA over MANUAL_CPC
  • Conversion tracking: run attribution_check — if zero conversions across the board, WARN that a new campaign won't help until tracking is fixed
  • Budget: must be <= max_daily_budget in config, ideally >= 5x target CPA
  • Keywords: if using BROAD match, campaign MUST use Smart Bidding — otherwise use PHRASE or EXACT

4. Draft campaign

  • Call draft_campaign with:
    • campaign_name, daily_budget, bidding_strategy
    • ad_group_name
    • Optional keywords with appropriate match types
  • Review the preview and any warnings (budget sufficiency, bidding, match type safety)

5. Present and confirm

  • Show the complete preview to the user
  • Emphasize: campaign will be created as PAUSED
  • Wait for explicit approval
  • confirm_and_apply(plan_id=..., dry_run=true) first
  • Only dry_run=false after user confirms

6. Next steps

After campaign creation, remind the user to:

  1. Add ads via draft_responsive_search_ad (use /create-ad)
  2. Enable the campaign via enable_entity when ready
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. 2d ago First seen · 47 lines · 10 tokens per session scan A 2a2cf424ea78

Subscribe to this mod's changes

create-campaign is a command published in the GitHub repository kLOsk/adloop (253 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 417 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.