The execution maze for DSH agents: maze timeline, per-step data tracks, deterministic execution analysis, multi-session comparison. Formerly dsh-trace-compare.
Description collected from the plugin's own repository or package metadata.
npx @deepseek-ai/dsh plugin add dsh-maze
@PensiveFei
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible
@holny
Agent Harness (Loop Engineering) dev guide - complete architecture & core modules, based on production-grade agent source: Claude Code, DeepSeek Harness, OpenCode, Pi, Codex, OpenClaw & Hermes. English & Chinese
@amlyczz
Google Antigravity (agy CLI) models for DeepSeek Harness - stream Gemini/Claude/GPT-OSS subscriptions into DSH with thinking, tool activity, token usage and in-GUI Google OAuth login.