Summary
Claude Code users surfaced a high-engagement public issue where benign prompts such as “hi” triggered usage-policy violation errors. The report is a trust and reliability signal for AI coding tools because safety filters that block ordinary interaction can interrupt workflows as severely as model or API outages.
What changed
A Claude Code GitHub issue reported false-positive usage-policy violations on benign prompts, drawing unusually high community engagement in the June 8 digest.
Why it matters
Safety filtering must be reliable and explainable for developer tools that sit in daily coding workflows. False positives damage trust, waste time, and create ambiguity about whether the user, client, or backend model policy is responsible.
Evidence excerpt
Agents Radar’s June 8 CLI digest identified issue #60366, where “hi” triggered a Usage Policy violation, as the highest-engagement Claude Code issue with 81 comments and active workaround discussion.