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/amnibro/grok-remote/remote-startgit clone --depth 1 https://github.com/Amnibro/grok-remoteWhat 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 | $0.00021 | $0.00386 |
| Opus 5 | $0.00010 | $0.00193 |
| Sonnet 5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
remote-start 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 2d 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.
What it actually says
/remote-start
Start Grok Remote for phone/desktop control. Arguments: $ARGUMENTS
Run
$PLUGIN = if ($env:GROK_PLUGIN_ROOT) { $env:GROK_PLUGIN_ROOT } elseif (Test-Path "$env:USERPROFILE\.grok\plugins\grok-remote\scripts\ensure-running.ps1") { "$env:USERPROFILE\.grok\plugins\grok-remote" } else { (Get-Location).Path }
$CWD = if ("$ARGUMENTS".Trim()) { "$ARGUMENTS".Trim() } else { (Get-Location).Path }
powershell -NoProfile -ExecutionPolicy Bypass -File "$PLUGIN\scripts\ensure-running.ps1" -Force -IgnoreConfig -Reason "command"
Start-Sleep -Seconds 2
try { Invoke-RestMethod "http://127.0.0.1:2421/health" -TimeoutSec 4 | ConvertTo-Json -Compress } catch { "health: $_" }
if (Test-Path "$PLUGIN\connect.url") { Get-Content "$PLUGIN\connect.url" }
Tell the user
- Phone:
http://LAN_IP:2421/?auto=1(same Wi‑Fi; not 127.0.0.1 on phone) - PC browser:
http://127.0.0.1:2421/?auto=1 - Stop: UI Stop button,
/remote-stop, or Desktop Grok Remote Stop - Pin: run
/remotethen UI Pin, orscripts\install-shortcut.ps1
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.
- 2d ago First seen · 28 lines · 21 tokens per session scan A d0176ea6bc5d
remote-start is a command published in the GitHub repository Amnibro/grok-remote (5 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 386 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
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.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.