Search

AI-native code security auditor on AgentField that proves exploitability with verdicts, traces, and actionable evidence.

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).

Skills that translate your coding agent's output into plain language: honest reports, straight verdicts, steps you can follow. MIT.