AIHero

    Tools & Environment

    Permission mode

    The permission-gating slice of an agent mode — which tool calls trigger a permission request and which run automatically.

    Matt Pocock
    Matt Pocock

    The permission-gating slice of an agent mode — which tool calls trigger a permission request and which run automatically. The original purpose of mode systems before harnesses started bundling behavioral instructions on top.

    Harnesses ship a ladder of these modes:

    ModeReadsWrites & shellTypical use
    Read-only / planAutoBlockedResearch, planning, reviewing
    DefaultAutoAskDay-to-day supervised work
    Auto-editAutoEdits auto, shell asksTrusted repos, mechanical changes
    "Yolo" / full-autoAutoAutoSandboxes, AFK runs

    Choosing a rung is a trade between safety and interruption, and both failure modes are felt. Too tight, and you become the bottleneck: the agent stops every few seconds for harmless reads, you click approve on autopilot, and the approvals stop meaning anything — rubber-stamping is the worst of both worlds, all the interruption with none of the protection. Too loose, and the agent edits files and runs commands you'd have wanted to see first.

    The loose end is most defensible inside a sandbox, where the blast radius of a bad tool call is contained. Outside one, most people settle on auto-approving reads and keeping a human in the loop for anything irreversible.

    Usage:

    "It paused on every grep — totally killed the AFK run."

    "Loosen the permission mode for read-only tools, keep prompting on writes and shell. Most permission requests on a research session are noise."

    Want more than vocabulary?

    Join AI Hero for practical skills, thinking on AI engineering, and resources that keep you ahead of the curve.

    I respect your privacy. Unsubscribe at any time.

    Share