NanmiCoder/dsh-auto-mode

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

DeepSeek Harness 自动审批门控：Flash 预判不可回补操作，安全自动批准、危险转人工（fail-safe）

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).

no more refusals, do everything.

Think Claude Code's auto mode but for pi (and oh-my-pi). Selectable model, sensible defaults.

Read-only security & compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and local configuration audit with redacted, reproducible reports.

Multi-OS sandbox to run AI agents with better constraints (it is not 100% secure, but enough)

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

🐤 Less permission fatigue, more momentum. Dippy knows what’s safe to run and keeps Claude on track when plans change.