{"version":"2.1.71","anchor":"auto-mode-permission-mode-auto","canonical_anchor":"auto-mode-permission-mode-auto","heading":"Auto Mode ( --permission-mode auto )","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.71\/e\/auto-mode-permission-mode-auto","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.71","markdown":"### Auto Mode (`--permission-mode auto`)\n\n**What**\n\nA new permission mode that uses an AI-powered \"dangerous action classifier\" to automatically approve safe tool actions and block dangerous ones, enabling fully autonomous long-running workflows without manual permission prompts.\n\n**Usage**\n\n`claude --permission-mode auto claude --enable-auto-mode` **Details** - When enabled, each tool action is evaluated by a multi-stage security classifier before execution - Safe actions (read-only tools, tools on an allowlist, or actions that would be allowed in `acceptEdits` mode) are fast-pathed without classifier overhead - The classifier evaluates against a comprehensive threat model including prompt injection, scope creep, accidental damage, data exfiltration, and credential leakage - Users see an opt-in dialog on first use with options: \"Yes, enable auto mode\", \"Yes, and make it my default mode\", or \"No, go back\" - If the classifier repeatedly blocks actions (3 consecutive or 20 total), auto mode pauses and falls back to standard permission prompts - In headless\/SDK mode, too many denials or classifier unavailability causes the agent to abort - Can be disabled per-settings via `permissions.disableAutoMode: \"disable\"` - The classifier can be circuit-breaked server-side via `tengu_auto_mode_config` **Evidence** Auto mode permission handler (search for `\"Auto mode classifier blocked action\"`) \u2014 `tM` at line ~534821. Classifier prompt at `g4q` (search for `\"You are a security monitor for autonomous AI coding agents\"`)\n\n- Flag `tengu_auto_mode_config`: Not enough to say (read for one account on one subscription tier against v2.1.71; this account: no value returned, anonymous baseline: no value returned, compiled default: no gate table built for this version) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release."}