Worker Agent System Prompt / Claude Code v2.1.217

Worker agents launched in multi-agent workflows now receive a structured system prompt covering environment awareness, scope limits, resumed task handling, error escalation, and output format. Key guidelines:

Don't modify code you don't understand; stop and report to the coordinator if confused
Complete exactly what was asked; suggest follow-ups for unrelated issues found
If you have the Task tool, you may use it to fan out — but workers at the depth cap don't receive it
Output structured: "What you did or found" then "Summary: one sentence"

The subagent spawn depth ceiling is now configurable via tengu_hazel_trellis (feature flag) or CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH (environment variable).

Evidence

Worker prompt (search for "You are a worker agent executing a task assigned by the coordinator") and depth env var (search for "CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Read from

Feature flag

tengu_hazel_trellis Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.217: not a boolean we can read

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.217. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since

Flag reading moved 10 Sep 2026 The flag server now returns 3 for tengu_hazel_trellis, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.

Flag reading moved 10 Sep 2026 The flag server now returns nothing at all, having stopped carrying it for tengu_hazel_trellis, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.

See this across every release →

How sure we are

One source agreesOne thing we can check says the same as this entry.

Anthropic's release notes agreeChanged subagents to no longer spawn nested subagents by default; set CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH to allow deeper nesting

See this entry in the whole of v2.1.217 →

The build it came inv2.1.217

21 Jul 2026 · 27 entries, this one is #11.

Either side of it

v2.1.216Older
v2.1.218Newer

Open the release →

Names in this entry

flagtengu_hazel_trellis
Default 3. Maximum subagent nesting depth, used when CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH is unset; a value that is not an integer of at least 1 uses 3, and the result is cached after the first read. Launching an agent at or past this depth fails with Subagent nesting limit reached (depth N of M), and several agent-tool checks compare against it, some only asking whether it is above 1.
envCLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH
Number of subagent layers allowed below the main conversation (default: 3). At the default, subagents can spawn their own subagents, and a subagent at the third layer can't spawn further; set 1 to turn nesting off. In v2.1.217 through v2.1.218, the default was 1, so a subagent couldn't spawn its own unless you raised the limit; v2.1.219 raised the default to 3. Accepts a positive whole number in plain digits; anything else is ignored, so the limit can be adjusted but not removed. Requires Claude Code v2.1.217 or later

Anthropic's note

Upstream's own release notes for v2.1.217 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Changed subagents to no longer spawn nested subagents by default; set CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH to allow deeper nesting

Is this right?