/ 
Claude-Agent-0.12
/ Claude::Agent::Permission

NAME

Claude::Agent::Permission - Permission handling for Claude Agent SDK

SYNOPSIS

use Claude::Agent::Permission;

# In a can_use_tool callback:
my $options = Claude::Agent::Options->new(
    can_use_tool => sub {
        my ($tool_name, $input, $context) = @_;

        if ($tool_name eq 'Bash' && $input->{command} =~ /rm/) {
            return Claude::Agent::Permission->deny(
                message => "Delete commands not allowed"
            );
        }

        return Claude::Agent::Permission->allow(
            updated_input => $input
        );
    },
);

DESCRIPTION

This module provides permission handling utilities for the Claude Agent SDK, including factory methods for creating permission responses.

PERMISSION MODES

  • default - Normal permission behavior

  • acceptEdits - Auto-accept file edits

  • bypassPermissions - Bypass all permission checks

  • dontAsk - Auto-deny unless explicitly allowed

PERMISSION CLASSES

CLASS METHODS

allow

my $result = Claude::Agent::Permission->allow(
    updated_input => $input,
);

Create an "allow" permission result.

Arguments

  • updated_input - The (optionally modified) input to pass to the tool

  • updated_permissions - Optional permissions update

deny

my $result = Claude::Agent::Permission->deny(
    message => "Not allowed",
);

Create a "deny" permission result.

Arguments

  • message - Reason for denial (shown to Claude)

  • interrupt - Optional, if true interrupts the entire query

AUTHOR

LNATION, <email at lnation.org>

LICENSE

This software is Copyright (c) 2026 by LNATION.

This is free software, licensed under The Artistic License 2.0 (GPL Compatible).