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 connection-troubleshootergit 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/connection-troubleshooter)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/connection-troubleshooter"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/connection-troubleshooter/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/connection-troubleshooter"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/connection-troubleshooter.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 | $0.00210 | $0.01584 |
| Opus 5 | $0.00105 | $0.00792 |
| Sonnet 5 | $0.00042 | $0.00317 |
| Haiku 4.5 | $0.00021 | $0.00158 |
Grade A, and why
connection-troubleshooter 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 10d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connection Troubleshooter
Purpose
Help a user who suddenly sees only a handful of Ad Superpowers tools (typically
just workflow, skill, and clients, sometimes with clients_update)
understand what happened and fix it. In almost every case a short tool list
means a platform connection needs (re)connecting — the dashboard may still
say "connected", but the underlying login (the OAuth grant) has expired or been
revoked, so the server can no longer fetch that platform's data and hides its
tools rather than show broken ones. Nothing is "broken" and no data was lost;
the connection just needs to be refreshed.
When to Use This Skill
Use this skill when the user reports any of:
- "I only see a few tools" / "most of my tools are gone" / "my platform tools are missing".
- "Where are my Google Ads / GA4 / Search Console / Tag Manager tools?" or "Where are my Meta / LinkedIn / TikTok tools?"
- "The connector isn't working" / "I connected my account but nothing shows up".
- "A tool is not callable" or "that tool isn't available."
- "How do I reconnect ?"
Do not use it for campaign performance problems, billing questions, or client onboarding — see the "Do NOT use for" note in the description.
Why this happens (plain-language)
Ad Superpowers only shows a platform's tools when it can actually reach that platform on your behalf. To do that it uses the login you granted when you connected the account (an OAuth "grant"). Access to a platform is short-lived and is refreshed automatically in the background — but if that grant was revoked or expired (you changed your password, removed the app's access, the refresh token aged out, an admin rotated permissions, etc.), the automatic refresh fails. When the server can't get a working connection for a platform, it hides that platform's tools instead of surfacing tools that would only error. That is why the dashboard can still list the account as "connected" while its tools have quietly disappeared from this chat.
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.
- 10d ago First seen · 119 lines · 210 tokens per session scan A e65f95d72062
connection-troubleshooter is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 12d ago), licensed MIT. It adds 210 tokens to every session and 1,584 once invoked, about $0.0011 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 2026-08-31.
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.
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…
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…
analytics
Growth analytics authority — GA4 event tracking, conversion funnels, attribution models, cohort analysis, A/B testing, Supabase analytics queries, and revenue reporting patterns.
self-healing-agents
Self-Healing Agents are autonomous systems that detect their own failure modes and self-correct without human intervention.
systematic-debugging
Systematic Debugging replaces trial-and-error fixes with a disciplined four-phase root cause analysis process.