Acts without authorization and ignores stop interrupts

“Claude repeatedly acted autonomously after questions, ignored interrupts (ESC/stop), and asked confirmation questions instead of answering directly.”

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/448/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

Growing. 1 report in the last 7 days and none the week before, down from 2 a week at the mid-September peak. Not fixed, but a workaround is known.

Questions are treated as commands and tool calls launch anyway; ESC or typing "stop" does not halt execution.

Is this your bug?

File my report

Where: Tool execution
Versions: 2.1.273 to 2.1.302
Platforms: macOS, Windows
How bad: Security risk: something exposed, or done without permission.

Part of: Ignores instructions and rules46 bugs

Unauthorized edits despite rules14 people
Ignores brevity instructions8 people
Agent ignores instructions17 people
Ignores claude.md rules and skills8 people
Memory and protocol files not reloaded after context compaction1 person
Saved memory not applied8 people
Verdict reversal under pushback1 person
Ignores user instructions5 people
Stale schedule lane rows1 person
Unverified search claims stated1 person

Show all 45Show only the largest 10

Replies exceed brevity rule2 people
Model expands task scope5 people
Durations not from timestamps4 people
Writes temp files against rule1 person
CLAUDE.md rules ignored3 people
Ignores provided source files4 people
Banned .txt memory dumps1 person
Ignores explicit user instructions3 people
Model ignores CLAUDE.md rules, skills and enforcement hooks3 people
Short options despite long-form rule1 person
Git run despite git ban1 person
Ignores instruction to research first3 people
Task list not advancing3 people
Guesses on ambiguous instructions1 person
Delays filing requested reports1 person
Direct user questions ignored3 people
Agent acts on stale facts1 person
Asks questions instead of building1 person
Skips requested actions on computer2 people
Claims deploy tool removes old links without verifying it1 person
Ssh commands run in zsh1 person
Commits leave stale documentation1 person
Written rules ignored intermittently1 person
Ignores absolute file path rule1 person
Remote host builds not checked1 person
Issue created with empty body1 person
Stale document dates in commits1 person
Skips design approval2 people
Issues missing documents table1 person
Bundles several questions in one1 person
Unasked messages to other sessions1 person
Ignores CLAUDE.md rules2 people
Agent reports tasks done without verifying against real systems2 people
Detours before filing issues1 person
Opus 5.5 ignores loaded rules19 people

Not quite your bug?

Fabricated user turns11 people

Original reports11, newest first

Nov 5, 2026Model ignores a direct question in a mid-turn message and launches tool calls instead of answering#107552
Oct 19, 2026Model answers the user's questions with new tool calls instead of an answer, despite a loaded 'a question is a question' rule#103577
Oct 18, 2026Claude Code ignores user instructions, overrides decisions, and completes no requested work#103180
Oct 12, 2026Model answers a yes/no question by running commands under a zero-autonomy instruction#101583
Oct 6, 2026AI do not stop. when i made the typo so i tried to stop the ai. the problem was…#99867
Oct 2, 2026[Model behavior] Launched tool work when the user asked a question#99086
Oct 1, 2026[Critical] Runaway: agent could not be stopped by any in-product means; only closing the VS Code window with the X button stopped it#98708
Sep 25, 2026Claude repeatedly acts autonomously after questions and ignores ESC/stop interrupts#97260
Sep 21, 2026Automode executes code for passive analysis tasks instead of responding#95965
Sep 17, 2026Assistant repeatedly acts without permission despite explicit, repeated, written instructions not to — full session audit with exact quotes#95201

Show all 11Show only the newest 10

Sep 16, 2026Claude Code executes actions without explicit user authorization and cannot be reliably stopped mid-execution#94703