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 cmhenry79/merlonix-mcp --skill merlonix-diagnosticsgit clone --depth 1 https://github.com/cmhenry79/merlonix-mcpWrote 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/cmhenry79/merlonix-mcp/merlonix-diagnostics)<a href="https://agentmods.dev/skills/cmhenry79/merlonix-mcp/merlonix-diagnostics"><img src="https://agentmods.dev/badge/skills/cmhenry79/merlonix-mcp/merlonix-diagnostics/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/cmhenry79/merlonix-mcp/merlonix-diagnostics"><img src="https://agentmods.dev/badge/skills/cmhenry79/merlonix-mcp/merlonix-diagnostics.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 | $0.00058 | $0.01252 |
| Opus 5.5 | $0.00023 | $0.00501 |
| Sonnet 5.5 | $0.00012 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
merlonix-diagnostics 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 today.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merlonix diagnostics
Use live public checks to answer the user's diagnostic question. These checks need no Merlonix account, API key, or payment. They are point-in-time observations from Merlonix's network, not continuous monitoring or a comprehensive security audit.
Connect and scope
Use the connected Merlonix MCP server at https://api.merlonix.com/mcp. If unavailable, read references/connection.md for setup and an HTTP fallback. Do not claim to have checked anything without a successful tool response. Installing this skill does not automatically connect its server.
Explain briefly that the supplied public hostname, URL, or IP will be sent to Merlonix to perform the requested check. Use only the target needed for the user's request. Never submit credentials, private/internal addresses, signed URLs, or URLs containing secrets; request a public credential-free target instead. If the exact MCP endpoint or page is unknown, ask for it rather than probing guessed paths. Extract the hostname from a supplied website URL for hostname-based checks; retain the actual path for MCP and page checks.
Discover available tool schemas with tools/list (or the client's tool discovery) before calling. Client prefixes may differ; match the underlying tool names below. If a schema has changed, use the current schema rather than guessing arguments. This workflow permits only the seven diagnostic tools below, even when the server exposes authenticated or write tools.
Choose the relevant checks
| User's symptom | Tool and arguments | Interpret carefully |
|---|---|---|
| Domain, certificate, or DNS trouble | check_domain_health with hostname |
Evaluate SSL, DNS, and registration legs separately. One failed leg does not establish a total outage. |
| MCP cannot connect or exposes no tools | check_mcp_health with exact url |
Check handshake, inventory, latency, and returned errors. A required login or rejected remote probe does not prove the server is down. |
| Possible vendor outage | list_vendor_status with {}, then get_vendor_status with a returned slug if detail is needed |
Use actual returned vendors and timestamps. An incident is supporting context, not proof it caused the user's symptom. |
| Email deliverability / blocklisting | check_email_blacklist with domain (public domain or IP) |
Not listed does not establish inbox delivery or validate SPF/DKIM/DMARC. Do not attribute delivery problems solely to a listing. |
| Broken links or mixed content | check_broken_links with exact page url |
Checks one page, not the entire site. Rate limits and blocked fetches can leave links unverified. |
| AI crawler / agent readiness | check_agent_readiness with hostname |
A deterministic HTTP assessment, not a rendered-browser audit or a guarantee of AI citations. |
What ships with it
2 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.
- today First seen · 51 lines · 58 tokens per session scan A 2357134ca2da
merlonix-diagnostics is a skill published in the GitHub repository cmhenry79/merlonix-mcp (0 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,252 once invoked, about $0.0002 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 2026-10-21.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.