{"version":"2.1.319","anchor":"auto-mode-classifier-bash-prescreen-retry-and-mcp-tool-chang","canonical_anchor":"auto-mode-classifier-bash-prescreen-retry-and-mcp-tool-chang","heading":"Auto mode's safety check can retry or skip its early shell-command screen","tier":"internal","area":"Auto Mode","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/auto-mode-classifier-bash-prescreen-retry-and-mcp-tool-chang","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### Auto mode's safety check can retry or skip its early shell-command screen\n\nAuto mode's action checker gains options to retry or skip its quick shell-command screen, and gets a remotely controlled switch for MCP tools\n\n**What**\n\nIn auto mode, Claude Code runs a classifier (a separate check that decides whether an action is safe to run without asking you) on what the model wants to do. That check includes a quick early screen of shell commands. The classifier can now be told to retry that screen or to skip it.\n\nOther changes:\n\n- A new remotely controlled switch covers how the classifier treats MCP tools (extra tools that come from add-on servers). The flag server returned off for this site's account and for an anonymous check.\n\n- Deferred tools, whose full descriptions load only when they are needed, are now replaced only when an MCP server is involved.\n\n**Why**\n\nThis changes how auto mode decides whether a shell command or an MCP tool call can go ahead without your approval.\n\n- Flag `tengu_parsed_creek`: Off in both readings (read for one account on one subscription tier against v2.1.319; this account: off, anonymous baseline: off, compiled default: not a boolean we can read) 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.\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}