Borrowing it
Nothing to install: this file belongs to WingedGuardian/GENesis-AGI. 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/WingedGuardian/GENesis-AGI/main/.claude/commands/activate-browser.mdgit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWrote 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/wingedguardian/genesis-agi/activate-browser)<a href="https://agentmods.dev/commands/wingedguardian/genesis-agi/activate-browser"><img src="https://agentmods.dev/badge/commands/wingedguardian/genesis-agi/activate-browser/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/commands/wingedguardian/genesis-agi/activate-browser"><img src="https://agentmods.dev/badge/commands/wingedguardian/genesis-agi/activate-browser.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 | $0.00026 | $0.00836 |
| Opus 5.5 | $0.00010 | $0.00334 |
| Sonnet 5.5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
activate-browser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activate Browser (On-Demand MCP)
Add Chrome DevTools MCP to .mcp.json for sessions that need full browser
capabilities beyond the built-in genesis-health browser tools.
When to Use
- You need network request inspection or console access
- You need Lighthouse audits or performance tracing
- You need to connect to a remote Chrome instance (user's browser)
- The built-in
browser_navigate/browser_clicktools aren't sufficient
Activation
Add this entry to ~/genesis/.mcp.json under mcpServers:
"chrome-devtools": {
"command": "npx",
"args": [
"[email protected]",
"--headless",
"--executablePath", "<path to a Chrome or Chromium binary>",
"--userDataDir", "${HOME}/.genesis/devtools-profile",
"--chrome-arg=--no-sandbox"
]
}
--executablePath: Genesis installs do not ship Google Chrome. Use any installed Chrome/Chromium. Playwright's own Chromium, if installed, is under~/.cache/ms-playwright/chromium-*/, inchrome-linux64/chromeon recent Playwright andchrome-linux/chromeon older releases; list the executable itself withls ~/.cache/ms-playwright/chromium-*/chrome-linux*/chrome.--userDataDir: keep it separate from~/.genesis/browser-profile, which the Chromium fallback layer uses. Two Chromium processes on one profile fail to start or corrupt it.--chrome-arg=--no-sandbox: Chrome flags must go through--chrome-arg. A bare--no-sandboxis read as an option of chrome-devtools-mcp itself, which has no such option, and is dropped without a warning.
Then restart the CC session to pick up the new MCP server.
Remote Browser (the user's Chrome)
Launching the user's Chrome for remote debugging and reaching its port is
described in ONE place: the browser-automation skill, "Remote CDP setup"
(src/genesis/skills/browser-automation/SKILL.md). Chrome 136+ ignores
--remote-debugging-port on the default profile, and headed Chrome binds the
port to loopback, so follow that section. Once the endpoint answers, replace
the config above with the following, using the same endpoint as
GENESIS_CDP_URL in place of http://127.0.0.1:9222 (that value is the SSH
tunnel case):
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.
- 6d ago Changed · +1 lines ba746e0f0258
- 19d ago Changed · +15 lines scan B → A 388ba6b37b7b
- 1mo ago First seen · 70 lines · 26 tokens per session scan B 22197ad3ab56
activate-browser is a command published in the GitHub repository WingedGuardian/GENesis-AGI (99 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 836 once invoked, about $0.0001 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 commands, from other repositories
labs-perplexity
Run a query using Perplexity's /labs mode via Playwright browser automation. Similar to /research-perplexity but uses Perplexity's experimental labs mode with a longer 15-minute timeout for complex queries.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.
review-prs
Check open PRs for human feedback before picking new work.
next-issue
Fetch the next ready-for-agent issue by priority.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.