А ну и напоследок - у кодекса появилось оказывается ДОХУИЩЕ флажков которыми мож

agents.<name>.nickname_candidates: display nicknames for that role.

approval_policy.granular.sandbox_approval: allow sandbox escalation prompts.

approval_policy.granular.rules: allow prompts triggered by execpolicy rules.

approval_policy.granular.mcp_elicitations: allow MCP elicitation prompts.

approval_policy.granular.request_permissions: allow request_permissions prompts.

approval_policy.granular.skill_approval: allow skill-script approval prompts.

allow_login_shell: allow login-shell semantics for shell tools.

default_permissions: choose a named permissions profile by default.

permissions.<name>.filesystem: define filesystem permissions profile.

permissions.<name>.filesystem.<path>: read/write/none for a specific path.

permissions.<name>.filesystem.":project_roots".<subpath>: scoped access relative to project roots.

permissions.<name>.network.enabled: enable network in that profile.

permissions.<name>.network.mode: limited | full.

permissions.<name>.network.proxy_url: HTTP proxy.

permissions.<name>.network.socks_url: SOCKS proxy.

permissions.<name>.network.enable_socks5: expose SOCKS5 listener.