Tag: subagents

Claude Code v2.1.296 lets a subagent auto-compact earlier than the main conversation. Set autoCompactWindow in the subagent's frontmatter or --agents JSON as a plain integer from 100000 to 1000000, and watch out for the 200k parsing trap, the CLAUDE_CODE_AUTO_COMPACT_WINDOW override, and the --agent session mode where the field does nothing.

A practical setup for Cursor Projects: prepare the repo so every worker starts warm, seed the Project's shared Context with a plan, conventions and a slice ledger, cut the work into disjoint PR-sized slices, and let subscriptions keep it moving. Covers Cursor 3.24, plan and admin gates, and the gotchas of a Context that lives outside git.

A side chat branches off what the agent already knows; a subagent goes and finds out something new. Claude Code's /btw has no tools at all, Cursor's /btw opens a full agent, and a plain subagent sees none of your conversation. A decision guide for Claude Code 2.1.278 and Cursor 3.11+.

The cold start of a subagent is not what costs you money. Measured across 117 real Claude Code subagent transcripts, startup context was 0.6% to 18% of each agent's total spend. Depth is expensive because every layer runs its own agentic loop and hands the layer above a summary instead of evidence. Here is the compression test that tells you which layer to delete.

A named subagent starts cold, a fork inherits your whole conversation and shares your prompt cache, and a background agent is a second Claude Code session entirely. The trap is the naming: /fork stopped being the in-session fork at v2.1.212 and /subtask took over.

By default a headless Claude Code run emits only tool_use and tool_result blocks from its subagents, so the delegated reasoning is invisible. Pass --forward-subagent-text (Claude Code 2.1.211+) to get subagent text and thinking in the stream-json output, and demultiplex it by parent_tool_use_id.

Version 2.1.219 raises the default subagent spawn depth from 1 to 3, adds a workflowSizeGuideline settings key, and ships a fail-closed sandbox network allowlist.

Version 2.1.218 moves /code-review off your main conversation into a background subagent, and fork-context skills now background by default. Here is what changed and how to opt out.

Version 2.1.213 caps concurrent subagents and stops nested spawns by default, building on the per-session limits from 2.1.212. Here are the new defaults and env vars.

Both let one agent spawn isolated workers from a Markdown file, but Claude Code nests five levels deep with per-agent tool allowlists and worktree isolation, while Cursor keeps it to two levels with a single readonly switch and reads Claude's format for free. Pick by where your agents run, not by brand.