GitHub issue #80988 in anthropics/claude-code, opened 2026-07-24 by elaye-canopy, records a report that Claude Code 2.1.219 injects a system-prompt section registered internally as heron_brook whose default text tells the model not to call the AgentTool and not to use workflows or deep-research unless the user requested it, that the section is enabled by model capability for Opus 5 rather than by user configuration, and that it offers no documented opt-out, with the reporter saying it overrode an explicit standing delegation instruction in CLAUDE.md.
Verbatim Excerpts from Cited Records
“Do not call the AgentTool unless the user requested it”
·
anthropics/claude-code (issue 80988 opening body, default heron_brook text)
·
2026-07-24T22:08:03Z
·GitHub Issue ↗
“Do not use workflows or deep-research unless the user requested it”
·
anthropics/claude-code (issue 80988 opening body, default heron_brook text)
·
2026-07-24T22:08:03Z
·GitHub Issue ↗
“The problem is not the guidance itself. It is that an undisclosed, server-gated prompt section countermands a documented, user-configured behavior (subagents / the Agent tool), reads to the model as user-authored instruction, and offers no opt-out.”
·
anthropics/claude-code (issue 80988 opening body, What is Wrong section)
·
2026-07-24T22:08:03Z
·GitHub Issue ↗
Counter-record: Issue remains open as of 2026-10-29 with 38 comments. Surveyed comments include multiple independent confirmations on 2.1.219 through 2.1.251 across macOS, Windows and Linux, including a 2.1.220 headless probe showing the two lines on Opus only, and a separate filing on the AgentTool name mismatch in issue 81263. The latest surveyed comment, dated 2026-10-29, says the instruction is no longer present in recent releases, for example 2.1.310, citing another issue comment, so the claim documents the original report and its corroboration, not a verified current state. No maintainer resolution appears in the surveyed thread.
Falsification probe: If issue #80988 is deleted without archive, if the author edits the opening body so the quoted lines no longer match verbatim, or if the author or maintainers post a definitive retraction showing the described behavior was mischaracterized, this claim drops to Withdrawn.
Audit verification: Verified 100% continuous verbatim substring against official GitHub REST API by
scripts/verify_claim_verbatim.py.