{"version":"2.1.269","anchor":"subagenttask-launch-pipeline-agent-tool-substantially-rew","canonical_anchor":"subagenttask-launch-pipeline-agent-tool-substantially-rew","heading":"Subagent\/Task launch pipeline (Agent tool) substantially reworked with new caps and teammate rules","tier":"internal","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/subagenttask-launch-pipeline-agent-tool-substantially-rew","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Subagent\/Task launch pipeline (Agent tool) substantially reworked with new caps and teammate rules\n\nSubagent launching gets a nesting-depth cap, a bypassable concurrency cap, and new teammate\/model-inherit rules\n\n**What**\n\nThe code that launches subagents (used by the `Agent` tool, sometimes called Task, to spin up a separate Claude instance to work on a piece of a task) was rewritten with several new limits and rules:\n\n- a cap on how deeply subagents can be nested (spawning subagents that spawn further subagents), which can refuse a launch with \"Subagent nesting limit reached\"\n\n- a cap on how many subagents can run at once, which can be bypassed with a flag\n\n- in-process teammates are now forbidden from spawning further teammates or background agents\n\n- coordinator-spawned workers can override to inherit the coordinator's model instead of using a separate one\n\n**Why**\n\nThese limits guard against runaway or excessive subagent spawning, keeping nested or concurrent agent work bounded and predictable.\n\n- Flag `tengu_amber_kestrel`: Not enough to say (read for one account on one subscription tier against v2.1.269; this account: no value returned, anonymous baseline: no value returned, compiled default: off)\n- Area: Subagents\n- Tier: Under the hood\n- Useful: 4\/5\n- Signal: 3\/5"}