Safety door for DeepSeek Harness
A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run.
Project overview
A second brain for your DeepSeek Harness agent
When the agent proposes something destructive, a strong model (default anthropic/claude-opus-5) reads it and answers: Verdict · What happens Verdict: safe · What happens: proceeds to the normal permission chain, untouched Verdict: dangerous · What happens: denied, with a reason the agent can act on Verdict: uncertain · What happens: escalated to you — the normal approval prompt
It only ever narrows. A call the reviewer clears still faces every sandbox, permission, and approval gate you already have — and an escalation defers to them too: if a stricter policy would have denied the call, you get that denial rather than an approval prompt. This does not replace your permission system; it sits in front of it.