{"version":"2.1.295","anchor":"warning-when-user-config-pushes-claude-to-delegate-to-subage","canonical_anchor":"warning-when-user-config-pushes-claude-to-delegate-to-subage","heading":"Startup warning when your config pushes Claude to delegate to subagents","tier":"notice","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295\/e\/warning-when-user-config-pushes-claude-to-delegate-to-subage","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295","markdown":"### Startup warning when your config pushes Claude to delegate to subagents\n\nA new startup notice, off by default, uses a small model to judge whether your CLAUDE.md, skills or agents push heavy subagent use, and warns you\n\n**What**\n\nA new startup notice, `subagent-config-warning`, can warn you when your setup encourages Claude to hand work off to subagents. Subagents are separate helper Claude instances that run part of a task.\n\n- It reads your CLAUDE.md file, your installed skills and your custom agents.\n\n- It sends that text to a small model, a classifier, which decides whether the config encourages delegating to subagents. The classifier runs under the source name `subagent_config_classifier`.\n\n- If it does, a warning says that editing the config may save tokens on the current model.\n\n- Results are cached in the global config. Classifier calls are limited to 10 per window of time.\n\n- The warning is shown only a limited number of times, with a minimum number of days between showings.\n\n- Three new per-user state keys keep track of this: `subagentConfigWarningShown`, `subagentConfigChecks` and `subagentConfigClassifierCalls`.\n\n- It is off by default through the remote config default `{ off: true }`.\n\n- The environment variable `CLAUDE_CODE_SUBAGENT_CONFIG_WARNING` overrides that default. A true-looking value turns it on with default settings, and a false-looking value turns it off.\n\nThe same release also adds three new usage-tracking events unrelated to this warning.\n\n**Why**\n\nWhen the warning is on, the text of your CLAUDE.md, skills and agents is sent to a model to be judged. The aim is to point out setups that spend extra tokens on subagents. Use `CLAUDE_CODE_SUBAGENT_CONFIG_WARNING` to force the warning on or off.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}