diagnose-tracking

A command for checking whether Google Ads and Google Analytics 4, a website measurement service, are recording advertising and conversion data correctly.

In plain words
What is it for?
Use it to inspect conversion events, compare ad clicks with analytics sessions, review tracking code, validate events, and find pages that receive traffic but no conversions.
Why use it?
It helps distinguish normal gaps caused by European privacy consent rules from tracking code that is missing, broken, or not firing.

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/diagnose-tracking
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 396 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 $0.00012 $0.00396
Opus 5 $0.00006 $0.00198
Sonnet 5 $0.00002 $0.00079
Haiku 4.5 $0.00001 $0.00040

Measured 2d ago against content hash 5f07c7cbb6b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnose-tracking 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/diagnose-tracking.md · 45 lines

What it actually says

Diagnose tracking and conversion issues for: $ARGUMENTS

1. GDPR check first

Before investigating anything technical, consider:

  • Are Ads clicks > GA4 sessions? This is likely GDPR consent rejection (normal in EU, 2:1 to 5:1 ratio)
  • State this upfront before deeper investigation

2. Attribution check

  • Run attribution_check with relevant conversion_events (e.g., sign_up, purchase, form_submit)
  • Review the insights[] — the tool already factors in GDPR consent gaps
  • Only proceed to deeper investigation if insights suggest a real tracking problem

3. Codebase analysis

  • Search for gtag('event' and dataLayer.push({event: to find tracking code
  • Search for gtag('consent' to check Consent Mode v2 implementation
  • Extract all event names from code

4. Validate tracking

  • Run validate_tracking with the extracted event names
  • Compare results: matched (working), missing (in code but not firing), unexpected (in GA4 but not in code)
  • Missing events = code not deployed or behind untriggered conditions
  • Unexpected events = likely from tag managers

5. Landing page check

  • Run landing_page_analysis to check pages with traffic but zero conversions
  • If codebase is accessible, read flagged pages for UX issues

6. Diagnosis

  • Only diagnose tracking as BROKEN when discrepancy can't be explained by consent
  • Signs of real issues: zero sessions for ALL sources, organic also anomalous, events in code but never fire
  • If tracking code needs to be added, use generate_tracking_code to produce the snippet

Present unified diagnosis: GDPR impact + tracking status + specific recommendations.

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 · 45 lines · 12 tokens per session scan A 5f07c7cbb6b2

Subscribe to this mod's changes

diagnose-tracking is a command published in the GitHub repository kLOsk/adloop (255 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 396 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.