{"version":"2.1.304","anchor":"claude-api-managed-agents-secure-guard-on-ant-commands","canonical_anchor":"claude-api-managed-agents-secure-guard-on-ant-commands","heading":"\/claude-api now blocks some ant commands before they run","tier":"notice","area":"Skills","scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.304\/e\/claude-api-managed-agents-secure-guard-on-ant-commands","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.304","markdown":"### \/claude-api now blocks some `ant` commands before they run\n\nThe \/claude-api skill now blocks `ant` commands with certain IDs and managed-agents-secure commands changed from the guide\n\n**What**\n\nWhen the `\/claude-api` skill loads, it now sets up a `PreToolUse` hook, a check that runs before a tool call and can block it. The check refuses:\n\n- `ant` commands carrying an ID that contains a `staging_`, `local_`, `vrtx_` or `bdrk_` part.\n\n- managed-agents-secure commands that were changed from the ones given in the guide.\n\nWhen a command is refused, Claude Code tells you it did not run it and why. The skill also does not allow one tool, and if the check cannot run, the skill is not available at all. Claude Code records each refusal.\n\n**Why**\n\nThis limits what the skill's commands can do, so commands that point at the wrong place or stray from the guide are stopped before they run.\n\n- Area: Skills\n- Names: `\/claude-api`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: yes"}