Borrowing it
Nothing to install: this file belongs to Devolutions/avalonia-extensions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Devolutions/avalonia-extensions/master/.github/skills/avalonia-devtools-mcp/SKILL.mdgit clone --depth 1 https://github.com/Devolutions/avalonia-extensionsWrote 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/devolutions/avalonia-extensions/avalonia-devtools-mcp)<a href="https://agentmods.dev/skills/devolutions/avalonia-extensions/avalonia-devtools-mcp"><img src="https://agentmods.dev/badge/skills/devolutions/avalonia-extensions/avalonia-devtools-mcp/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/devolutions/avalonia-extensions/avalonia-devtools-mcp"><img src="https://agentmods.dev/badge/skills/devolutions/avalonia-extensions/avalonia-devtools-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01116 |
| Opus 5.5 | $0.00018 | $0.00446 |
| Sonnet 5.5 | $0.00009 | $0.00223 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
avalonia-devtools-mcp 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 28d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Avalonia DevTools MCP
Use this skill when the task involves validating or debugging runtime UI behavior in a running Avalonia app, especially when visual inspection, tree traversal, property/style inspection, or screenshots are needed.
When to use
- "Show me the visual tree"
- "Find this control in the running app"
- "What styles/properties are applied at runtime?"
- "Take a screenshot of this panel/window"
- "Simulate click/text input and verify result"
Preconditions
- DevTools MCP server configured in user MCP config (for VS Code in this environment):
~/Library/Application Support/Code/User/mcp.json
- Tool installed:
dotnet tool install --global AvaloniaUI.DeveloperTools
- App instrumentation in target app:
AvaloniaUI.DiagnosticsSupportpackage.WithDeveloperTools()orthis.AttachDeveloperTools()at startup- Keep this instrumentation development-only (Debug), since MCP enables live inspection, mutation, and input simulation.
Standard workflow
attach-to-appwith noid- If multiple/any clients returned, select one and call
attach-to-appwith thatid - Inspect with:
tree(roots/subtree)search(type/x:Name)props,styles,resourcesscreenshot
- Interact with:
input,action,set-prop,pseudo-class
detachwhen done
Multiple instances and parallel agents
Assume other developers or agents may be running the same Avalonia app from other worktrees. It is safe for separate agents to inspect separate instances, but each agent must select its client by process ID instead of attaching to whichever app happens to appear first.
- When starting an app, record the new process ID and its worktree/output path. On Windows,
Get-CimInstance Win32_Processcan correlate adotnetPID with its command line; the window title alone is not unique. - Call
attach-to-appwithout anidonly to enumerateavailableClients. - Match the recorded PID to
availableClients[].processId, then callattach-to-appwith its request fieldidset to that exactprocessIdvalue (for example,{"id": 24140}). Do not send a field namedprocessId; that is a response field, not an attachment request field. - Verify the response's
connectedClient.process.processIdandappBaseDirectory. The latter should point into the expected worktree/output directory. - After attaching or switching clients, discard every cached node ID and reacquire the tree/search results. One MCP connection targets one client at a time, and a new attach invalidates nodes from the previous client.
- If the app restarts, enumerate again: process IDs and node IDs are ephemeral.
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.
- 28d ago Changed · +33 lines b1d580992fdd
- 2mo ago First seen · 64 lines · 44 tokens per session scan A 13d4341a63d0
avalonia-devtools-mcp is a skill published in the GitHub repository Devolutions/avalonia-extensions (84 stars, last pushed 15d ago), licensed MIT. It adds 44 tokens to every session and 1,116 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.