Permissions Articles
3 articles across AI Catchup's news, guides, tutorials, and comparisons.
All Permissions articles
Claude Managed Agents Adds a Terminal Session Viewer and Auto Permission Mode
Claude Managed Agents now includes a terminal workflow for attaching to live sessions and a local web session viewer. Anthropic also added an auto permission mode that evaluates each agent or MCP tool call against the intent in user.message and runs, denies, or pauses for approval.
Claude Code Will Make Auto Mode the Default on August 14
As of September 2026, auto mode is the default permission mode for new Claude Code sessions on Pro, Max, and Team plans; the switch took effect on August 14, 2026, as Anthropic announced on August 7. Enterprise plans, Console API keys, and the Bedrock, Agent Platform, Foundry, and Claude Platform on AWS integrations still start in manual (default) mode. The mode routes tool calls through a safety classifier, keeps manual approval available, and does not charge Pro, Max, or Team for classifier calls.
Codex Permission Profiles: Least-Privilege Controls for Local Agent Work
OpenAI shipped Codex permission profiles in beta -- reusable, inheritable policies that replace the coarse sandbox_mode/sandbox_workspace_write combo. A profile binds OS-enforced filesystem read/write/deny rules (down to **/*.env) to per-domain network and Unix-socket rules. Enterprise admins get fail-closed allowlists via requirements.toml. Profiles govern local sandboxed command execution only, not MCP servers, app connectors, browser, or cloud.