Claude Code’s code-review subagent somehow spawned more subagents
wjmelements · ghdev · 2026-07-21
Another GitHub issue in Anthropic’s Claude Code reports that the /code-review subagent spawned its own subagents.
- The reporter says the code-review subagent appeared to perform an entire review loop on its own.
- After token exhaustion and reset, the subagent would not terminate normally and had to be stopped manually.
- The attached screenshot shows a bizarre self-diagnosis moment where the subagent first thought it was the top-level Claude Code process, then realized it was not.
More from coding & agent
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11