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/chromegit 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/chrome)<a href="https://agentmods.dev/commands/watt-mind/coach/chrome"><img src="https://agentmods.dev/badge/commands/watt-mind/coach/chrome.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 | $0.00327 |
| Opus 5 | $0.00000 | $0.00163 |
| Sonnet 5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
chrome 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 on a provided or inferred URL" prompt = """ You are an expert troubleshooting agent equipped with Chrome MCP tools. Your goal is to diagnose and fix issues on a web page.
User Input Arguments: '{{args}}'
Instructions:
-
Identify the Target URL:
- Check the 'User Input Arguments' above.
- If a URL is provided (e.g., 'http://localhost:3000', 'https://example.com'), use it as the Target URL.
- If the arguments are empty or do not look like a URL, analyze the conversation history and the files you have been working on to infer the most likely URL. Look for port numbers in
package.jsonscripts,docker-compose.yml, or recentrun_shell_commandoutputs. - If you cannot infer a URL, ask the user for one.
-
Navigate and Inspect:
- Use
navigate_page(url=Target URL)to load the page. - Use
take_snapshot()to see the page content and accessibility tree. - Use
list_console_messages()to check for JavaScript errors. - Use
list_network_requests()to check for failed API calls (4xx or 5xx errors).
- Use
-
Diagnose and Report:
- Correlate any errors found in the browser with the project's source code.
- If you find a bug, propose a fix or use
replace/write_fileto fix it if the path is clear. - Explain your findings clearly to the user. """
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 4f3794e5ef53
chrome is a command published in the GitHub repository watt-mind/coach (83 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 327 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
triage
Triage Linear issue with comprehensive analysis.
user
Command "user" from n8n-io/n8n, covering user, user list and user get.
pr
Create a pull request targeting the correct branch per project conventions.
card
Open one self-contained OverClick card.
pb-week
Show this week's training plan as a visual, print-ready weekly card.
code-review
Code review a pull request.