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 skills add Ad-Superpowers/ad-superpowers-plugin --skill google-ads-conversion-tracking-debuggergit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-conversion-tracking-debugger)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-conversion-tracking-debugger"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-conversion-tracking-debugger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-conversion-tracking-debugger"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-conversion-tracking-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00098 | $0.01470 |
| Opus 5.5 | $0.00039 | $0.00588 |
| Sonnet 5.5 | $0.00020 | $0.00294 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
google-ads-conversion-tracking-debugger 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversion Tracking Debugger
Systematic troubleshooting guide for Google Ads conversion tracking issues. Use the diagnostic flow below to quickly identify root causes, then follow the detailed decision trees in the references.
Quick Diagnosis Flow
WHAT IS THE PROBLEM?
│
├─► [A] Conversions NOT appearing
│ ├── Timing check: Wait 24-48 hours before debugging
│ ├── Check: Google Ads → Goals → Conversions → Status column
│ │ ├── "Inactive" → Tag not found on site
│ │ ├── "Unverified" → Setup incomplete
│ │ └── "No recent conversions" → Tag found but not firing
│ ├── Verify tag: Chrome DevTools → Network → filter "googleads"
│ └── Detailed steps: See references/decision-trees.md Section 1
│
├─► [B] Too MANY conversions (duplicates)
│ ├── Add unique transaction_id to conversion tag
│ ├── Set Count: "One" for leads, "Every" for purchases
│ ├── Check for duplicate tags (GTM + hardcoded)
│ └── Detailed steps: See references/decision-trees.md Section 2
│
├─► [C] Numbers DON'T MATCH (GA4 vs Ads)
│ ├── 10-30% difference = NORMAL (different attribution models)
│ ├── Align attribution windows for comparison
│ ├── Compare "All Conversions" column in Google Ads
│ └── Detailed steps: See references/decision-trees.md Section 3
│
├─► [D] Enhanced Conversions not working
│ ├── Check user_data object in dataLayer
│ ├── Verify consent: ad_user_data = "granted"
│ ├── Validate SHA-256 hash format (if pre-hashed)
│ ├── Wait 48-72 hours for status update
│ └── Detailed steps: See references/decision-trees.md Section 4
│
├─► [E] Offline conversion import failing
│ ├── Validate GCLID format and age (< 90 days)
│ ├── Check timestamp timezone (must match account)
│ ├── Verify conversion action name matches exactly
│ ├── Handle partial failures via error report
│ └── Detailed steps: See references/decision-trees.md Section 5
│
└─► [F] Tag/Pixel firing issues
├── Check JS console for errors
├── Verify GTM container is published
├── Test trigger conditions in GTM Preview
├── Remove duplicate implementations
└── Detailed steps: See references/decision-trees.md Section 6
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 184 lines · 98 tokens per session scan A 1ff0d704e511
google-ads-conversion-tracking-debugger is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 98 tokens to every session and 1,470 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
traffic-diagnosis
Systematically diagnose why traffic changed — spike, drop, or shift in mix. Follow these steps in order. Each step narrows the hypothesis.
incident-postmortem
Close the learning loop after a rescue or incident — reconstruct the timeline from actionlog, run root-cause analysis (platform / site / measurement / external), produce a structured postmortem document, distill reusable insights via /learn, and propose preventive guardrails. Use after a /rescue, a CPA spike, a…
ai-hive-a2a-cancel-handoff-check
A verification workflow for tasks handed from one AI agent to another using A2A, a protocol for agent-to-agent communication. It checks remote status, task identifiers, handoff outputs, and cancellation results.
ai-hive-agents-api-session-recovery
A design guide for recovering long-running hosted-agent sessions, their execution events, and result files after interruptions.
sealeap-amazon-featured-offer-loss-triage
Triage loss of the Amazon Featured Offer by checking account health, order defect signals, price competitiveness, offer and fulfillment state, listing classification, unauthorized sellers, and external price evidence before escalating. Use when the Buy Box or purchase button disappears or repeatedly returns. Do not…
self-healing-agents
Self-Healing Agents are autonomous systems that detect their own failure modes and self-correct without human intervention.