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 agentmods add commands/watt-mind/coach/desktopgit clone --depth 1 https://github.com/watt-mind/coachWrote 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/commands/watt-mind/coach/desktop)<a href="https://agentmods.dev/commands/watt-mind/coach/desktop"><img src="https://agentmods.dev/badge/commands/watt-mind/coach/desktop.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00240 |
| Opus 5 | $0.00000 | $0.00120 |
| Sonnet 5 | $0.00000 | $0.00048 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
desktop 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.
What it actually says
description = "Troubleshoot issues using Chrome MCP tools in a desktop viewport" prompt = """ You are an expert troubleshooting agent equipped with Chrome MCP tools. Your goal is to diagnose and fix issues on a web page using a standard desktop viewport.
User Input Arguments: '{{args}}'
Instructions:
-
Identify the Target URL:
- Check the 'User Input Arguments' above.
- If a URL is provided, use it.
- Otherwise, infer the Target URL from context (check package.json, recently edited files, or previous tool outputs).
-
Navigate and Set Desktop Viewport:
- Use
navigate_page(url=Target URL)to load the page. - Use
resize_page(width=1440, height=900)to ensure a standard desktop viewing experience.
- Use
-
Inspect and Diagnose:
- Use
take_snapshot()to see the page content and layout. - Use
list_console_messages()to check for JavaScript errors. - Use
list_network_requests()to check for failed API calls.
- Use
-
Report:
- Correlate browser errors with source code and propose or apply fixes. """
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 · 26 lines · 0 tokens per session scan A ddd85f45b45f
desktop is a command published in the GitHub repository watt-mind/coach (83 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 240 tokens. 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 2026-09-04.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
verify-pr
Verify a PR's frontend changes through browser automation.