dsh-auto-review

⭐ 116 · ✅ active · agent

One-liner

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

About

Second-model AI approval for DeepSeek Harness — a read-only reviewer subagent decides allow/deny on the approval chain, fail-closed by default. When an action crosses the sandbox boundary, a second model reads the evidence and returns a verdict with a reason — so humans approve nothing while nothing unsafe slips through. English · 简体中文 · Español · Português · हिन्दी