Review process not scaled to risk

“Claude Code turned a UI-only change into a multi-hour, multi-agent pipeline.”

Is this your bug? What gets counted gets fixed. Pile on.

Paste this into your agent. It files your report, with your error and version.

I hit this bug: rapsheet.dev/sheets/claude-code/issues/2786/file
Follow it to file my report. Show me the text before you send.

No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends

Runs full multi-agent reviews on low-risk changes despite instructions. Heavyweight implementer, reviewer and fix pipelines run on UI-only or app code changes, burning usage limits and hours.

Is this your bug?

File my report

Where: subagent orchestration
Versions: 2.1.296
Platforms: macOS
How bad: Breaks a normal workflow.

Part of: Unrequested agent fan-outs drain usage5 bugs

Unrequested multi-agent workflows launch and exhaust usage limits without estimate or conf5 people
Ultracode overspawns agents5 people
Subagents spawned despite instructions3 people
Subagent fan-out exhausts usage limit2 people

Not quite your bug?

Model expands task scope5 people
Credits billed despite weekly limit2 people

Original reports2, newest first

Oct 13, 2026Severe: Claude Code runs a multi-hour multi-agent pipeline on a UI-only change and ignores explicit ordering instructions#101695
Oct 4, 2026Orchestrator drifted from the user's ratified light-review tier into fleet-wide full fan-out reviews and burned the weekly usage budget#99376