Claude Code 2.1.269 Ships a Plugin Eval Runner and a Knob to Raise the Workflow Tool's Concurrent Agent Cap to 256

Anthropic (claude-code CHANGELOG)·high signalXBlueskyLinkedInCopy link

Released 2026-09-11, v2.1.269 adds `claude plugin eval`, which runs a plugin's eval suite against Claude Code and emits scored reproducible JSON and HTML reports, plus `CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS` (1-256) to raise the Workflow tool's per-run agent limit for inference-bound fan-outs. On the security side it fixes a deny or ask permission rule starting with `!` applying beyond the settings source that wrote it; such a rule now applies only within its own source and a bare `!` negation is ignored. Two prompt-cache fixes also land: partial invalidation after an output-token-limit cutoff, and context re-sent differently when resuming a session interrupted mid-thought.