analyze-performance

A command for reviewing Google Ads and Google Analytics 4 data together. Google Ads tracks paid advertising, while GA4 tracks visits and actions on a website.

In plain words
What is it for?
Use it to compare campaigns, spending, clicks, conversions, cost per acquisition, click-through rate, paid and unpaid traffic, keywords, search terms, and possible landing-page or attribution problems.
Why use it?
It brings the two data sources into one review so gaps between ad clicks, website sessions, conversions, and privacy-related tracking are easier to find.

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

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 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 $0.00011 $0.00377
Opus 5 $0.00005 $0.00188
Sonnet 5 $0.00002 $0.00075
Haiku 4.5 $0.00001 $0.00038

Measured 2d ago against content hash 9e404ca8fdb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-performance 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/analyze-performance.md · 35 lines

What it actually says

Analyze Google Ads and GA4 performance: $ARGUMENTS

1. Pull data (AdLoop MCP)

  • get_campaign_performance — relevant date range (default: last 30 days)
  • analyze_campaign_conversions — cross-referenced Ads + GA4 data with GDPR gap detection
  • If specific campaigns mentioned, filter by name
  • If keywords are relevant, also pull get_keyword_performance and get_search_terms

Context tip: for the account-wide pass, call the performance tools with compact=true — you get totals, top-10 rows, and pre-computed offender lists instead of every row. Only switch to full mode when drilling into a specific campaign/keyword. In harnesses that support subagents, this whole data-pull step can be delegated to a subagent that returns just the summary.

2. Analyze

  • Spend, Clicks, Conversions, CPA, CTR per campaign
  • Paid vs organic comparison (from non_paid_channels)
  • GDPR gap (clicks vs sessions ratio — 2:1 to 5:1 is normal in EU)
  • Flag: zero conversions with significant spend, CPA > 3x target, QS < 5, wasteful search terms

If conversion issues found: run attribution_check If landing page problems suspected: run landing_page_analysis

3. Present results

  • Summary table of all campaigns with key metrics
  • Highlight what's working and what's not
  • Ranked list of recommended actions with priority and estimated impact
  • If search terms show waste, quantify the amount and suggest negatives

Keep the GDPR consent gap in mind — never diagnose clicks > sessions as broken tracking without considering consent rejection 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. 2d ago First seen · 35 lines · 11 tokens per session scan A 9e404ca8fdb0

Subscribe to this mod's changes

analyze-performance is a command published in the GitHub repository kLOsk/adloop (253 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 377 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.