Plugins

GitHub-topic-driven plugin & skill marketplace: a Settings page that browses the auto-collected registry (the whole dsh-plugin topic plus the skills index, CI-refreshed every 2 hours) with one-click install, type detection, install-script and host-shadow-dependency safety confirmations, env-key management, and the STANDARD.md recognition spec.

Rewind conversation and workspace state, powered by a persistent Change Ledger.

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

Install safety net for DeepSeek Harness: pre-install snapshots, one-click/automatic rollback, guarded boot, and incident reports that auto-trigger agent analysis. 中文: DeepSeek Harness 插件安装安全网（安装前自动快照、一键/自动回退、守护启动、事故报告自动触发 Agent 分析）。

Feishu/Lark bridge for DeepSeek Harness: scan-to-connect PersonalAgent binding, streaming cards, git-worktree project workspaces, parallel per-scope tasks, multi-role agents, cross-session notify, in-chat model/key management, and a safety-net guardian that still answers in Feishu after dsh crashes.

AGI long-term memory base: multi-agent spatiotemporal memory graph, self-evolving knowledge flywheel, self-cognition, and auditable trust guardrails.

Claude Code /rewind for DeepSeek Harness: git-first workspace snapshots before every mutating tool execution, turn-boundary session forks, and a one-shot /rewind command that restores files and forks the session back to a checkpoint.

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

Cross-platform Computer Use for DeepSeek Harness: virtual-mouse human-like operation (screen_observe + computer_click + type + key + scroll + drag, 11 tools), AX-tree zero-vision-cost mode with free GLM-4V-Flash vision fallback, safety guards (snapshot TTL / app whitelist / dangerous-action approval / password-box protection).

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting

Agent- and GUI-controlled DG-LAB Coyote e-stim plugin: eight `coyote_*` tools plus a DSH web panel behind one safety envelope (soft limits, asymmetric rate limiter, session cooldown, playback caps, disconnect fail-safe); optional auto-stim layer maps agent events (tool calls, errors, turn end) to bounded pulses; official V3 socket protocol with QR pairing, programmable waveforms. Adults only.

Scheduled agents on a cron: run a prompt on a schedule and get the digest where you already are, with overlap/missed-run/timeout safety defaults.

Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.

dsh-shell for DeepSeek Harness: runs cmd / PowerShell commands on Windows (and bash-like shells on POSIX) with a bash-inspired safety model — timeouts, output truncation, exit codes, background jobs and a cwd allowlist

Destructive-command interception gate for dsh: parses shell semantics, judges risk against 41 built-in rules, and holds irreversible rm -rf, git reset --hard, and git push --force style commands at a confirmation gate.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

Chemical safety intelligence through the hosted MSDS Chain MCP endpoint: 23 tools for compatibility and mixing order, GHS hazards, PPE, storage, waste disposal, exposure limits, transport classification, multi-region regulatory compliance, SDS lookup and version diffs, and signed audit reports, each answer citing the supplier SDS and revision date it is grounded in.

A hands-off safety net: directories the agent deletes go to a trash folder first and symlinks are never followed, with zero approvals.

A development safety kit: rolling config snapshots, automatic rollback on plugin failures, boot-failure rescue, and an in-settings management panel.