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.
npx agentmods add commands/klosk/adloop/optimize-campaigngit clone --depth 1 https://github.com/kLOsk/adloopWhat 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 | $0.00008 | $0.00433 |
| Opus 5 | $0.00004 | $0.00217 |
| Sonnet 5 | $0.00002 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
optimize-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 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.
What it actually says
Optimize Google Ads campaign: $ARGUMENTS
Follow this checklist in order — earlier items have higher impact.
Context tip: run the diagnosis reads with compact=true (totals + top offenders instead of full row dumps); switch to full mode only when drafting a change against a specific entity.
1. Diagnose
get_campaign_performance— current metricsattribution_check— is tracking working?- If zero conversions + significant spend: STOP and resolve tracking first
2. Search term cleanup
get_search_terms— identify irrelevant terms wasting budgetget_negative_keywords— what's already blocked (avoid duplicates)- Propose negatives with
add_negative_keywords(show preview, wait for approval) - Group negatives by theme for clarity
3. Quality Score
get_keyword_performance— check QS for each keyword- QS < 5 = relevance problem (landing page + ad copy mismatch)
- Suggest specific improvements to ad copy or landing page
4. Ad copy
get_ad_performance— which ads perform best- If CTR < 2% across all ads: headlines need rewriting
- If fewer than 3 active ads: create new ones with
draft_responsive_search_ad - Count characters before drafting (30 char headline limit)
5. Bidding strategy
- Check if campaign uses Smart Bidding or Manual CPC
- Manual CPC + Broad Match: MIGRATE to Phrase/Exact OR switch to Smart Bidding
- Recommend Maximize Conversions if sufficient conversion data exists
6. Budget
- Is daily budget >= 5x target CPA?
- If not: either increase budget or focus on reducing CPA first
- Use
estimate_budgetif considering budget changes
Rules
- One change at a time — show preview, wait for approval
- Never edit during Learning Phase
- Priority order: tracking > negatives > QS > ad copy > bidding > budget
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 · 55 lines · 8 tokens per session scan A 6fd92bafc1a8
optimize-campaign is a command published in the GitHub repository kLOsk/adloop (253 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 433 once invoked, about $0.0000 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.
Other commands, from other repositories
seo-audit
Run a multi-agent SEO/discoverability audit of a page (URL or local .html), grounded in the Google docs KB, and write a scored cited report.
google-docs
Answer a question from the local Google docs knowledge base (Search/SEO, Search Console, Ads, GA4) with citations to the original sourceurl.
setup
First-run setup for the ga-mcp-full MCP server — install the CLI if needed, then complete the browser login.
auth-login
Run the Google Analytics OAuth browser flow and cache credentials for the ga-mcp-full MCP server.
auth-status
Show the current Google Analytics auth status for the ga-mcp-full MCP server.
auth-logout
Clear cached Google Analytics OAuth credentials for the ga-mcp-full MCP server.