Skip navigation
Jev + Vercel Sandbox Mod in Claude Code
0:00 / 0:31

Jev + Vercel Sandbox Mod in Claude Code

Daniel San

@dani_avila735K followers

Visit on X
75 likesDownloadOriginal post

16,889 views

Jev + Vercel Sandbox Mod in Claude Code This Mod spins up a sandbox on Vercel, while Jev classifies which commands should run inside the sandbox and which ones should run locally Install: npx claude-code-templates@latest --mod security/jev-vercel-sandbox Link: Mods are a great way to customize your Claude Code workflows and connect other platforms directly into the agent loop

10 Comments

Comments from the original post on X (Twitter)

  • Sebastian Hardy's profile picture

    @aiopshq

    Full shell access on day one is how agents wipe folders.

    1 like

  • Bessi S's profile picture

    @LLMpsycho

    Jev classifying sandbox vs local.

  • Anishek Kamal's profile picture

    @anishekkamal

    Splitting what runs in a sandbox versus locally based on command risk is a nice pattern. Saves you from sandboxing everything just to be safe.

  • Richard E. Greene's profile picture

    @GamingGreenez

    claude code getting a whole sandbox mod is kinda sick

  • David Qu's profile picture

    @thedavidqu

    Keeping the bulk edits in a separate patch is useful when you've already got uncommitted work. Way easier to tell what the agent actually changed

  • Lee Wyatt Corp's profile picture

    @LeeWyattCorp

    A Jev sandbox mod on day one. The ecosystem is not waiting around.

  • Kizuno18's profile picture

    @Kizuno18

    dynamic command routing between local and sandbox is the cleanest security pattern: isolating only risky commands preserves local speed. in our pipeline targeting brazil, classifiers route untrusted fetches to sandboxes while ffmpeg and piper run on bare metal for $0. fast & safe

  • Shahid🇵🇸's profile picture

    @shahidcodes

    read the page. a default i'd flip: with confirmSandbox on, a claude -p run has nobody to answer, so even untrusted_code (curl | sh) falls through to local. headless runs are where nobody reads the command, so that case should go to the sandbox

  • TobiasJames.ΞTH ᵍᵐ's profile picture

    @tobiasjames_eth

    Oh that’s sick

  • Michael Waitze's profile picture

    @MichaelWaitze

    This is a clever way to use Jev for security. We actually went deeper on the Cloudflare Clef models that are also pushing the boundaries of decision models here: