Plugins

Red-team engagement mode: send one target organization name; a planner session runs five execution roles (recon, asset triage, vulnerability discovery, exploitation, internal pivot) with configurable concurrency; preflight checks skills/resources; scoring uses four stages (recon, internet, boundary, internal) with server-side caps and privilege-wins dedup; findings stay in a local SQLite fact base. The persistent right-side console has nine pages and includes asset mapping, agents, sessions/tunnels, findings, score targets, reports, POC knowledge base and skill library. v0.15.2 adds automatic HTTP evidence/action records, batch ingest, scope check, tunnel pivot probe, data proof, cleanup ledger and T0-T3 asset admission to prevent scope drift. 59 redteam_* tools; 38 bundled skills.

Framework-upgrade safety and plugin gating for DSH: a pre-upgrade session-format contract preflight that adapts incompatible plugins and agent presets before you upgrade, automatic rollback on failure, auto-quarantine of plugins that broke a boot, plus environment fingerprinting and a public contract-rule pack. The built-in multi-source marketplace is a discovery layer only.

Asset governance console for self-hosted AI infrastructure. Registers MCP servers, skills, agents, AI apps, model channels, SaaS connectors and NAS storage in one ledger with a lifecycle state machine, per-tool RBAC permission points, department x agent x skill cost attribution, dependency topology and an append-only audit trail. Self-hosted, MIT, no hosted tier and no cloud contract.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

A plugin management panel: one-click enable/disable for installed plugins plus a GitHub dsh-plugin marketplace with details and one-click installs.

Automate Huawei eNSP labs: generate .topo files, start and stop devices, and push configuration one command at a time with per-command error reporting. On Windows it drives the eNSP window with simulated mouse clicks and window screenshots used to locate buttons (administrator rights needed), sends commands to the device consoles over local TCP, and may force-kill running eNSP clients when it has to relaunch.

Ecosystem infrastructure: a thin browser console for managing official repository plugins (zero patches) plus a make-dsh-plugin skill for guided plugin development.

Mebular memory, task graph, and shared Console for DeepSeek Harness

Ecosystem infrastructure: a thin browser console for managing official repository plugins (zero patches) plus a make-dsh-plugin skill for guided plugin development.

Hacker News tools for feeds, discussion threads, search, and user profiles.

One-command backup, restore & migration for all DSH user data (~/.dsh) with a visual Settings panel: scheduled auto-backup with tiered retention, sha256 verification, hardened restore with auto-rollback and a result receipt, typed sub-backups (--types), credential redaction into a local vault, private-repo GitHub sync for moving to a new machine, and an out-of-process rescue console (zero-dependency rescue web UI in the backup dir) that works even when the host won't boot. /backup doctor checks and repairs corrupt session logs from a known-good backup and quarantines them before rotation; migrate-check statically predicts which sessions a host upgrade would break (frozen event-list rules, filename/generation mismatch, hardlink support, legacy credentials); the credential sentinel preserves pre-migration copies before the host rewrites them; smart backup snapshots before host upgrades; /backup check-update and /backup update report and install new releases (snapshotting first). Restore handles attachment hard links and arbitrarily large archives (streamed listing). Current npm version 0.13.4; spans DSH 0.1.1-rc.2 through 0.2.0-rc.1, including 0.2.0's install-time peer gate. macOS/Linux/Windows.

Feishu (Lark) UI for DeepSeek Harness — a panel-driven control console: every slash command is a button on the ⚙️ control-panel card, in-card approvals and questions, live streaming cards, and one-QR app setup.

QQ channel for DeepSeek Harness over OneBot 11 / NapCat: keeps one fixed persona across sessions with long-term memory, answers in group and private chats, sends stickers and voice replies, and ships a local web console that shows what the bot is doing. Persona and memory files are yours to write — the repository only ships examples.

Provides local and remote knowledge bases with project- and session-scoped recall, controlled write-back, and an embedded Web management console.

One-shot mcp-unity integration for DeepSeek Harness: bundled MCP server with zero manual config lets the agent drive the Unity editor through 34 tools - scenes, game objects, transforms, materials, prefabs, menu items, play mode, tests and console logs - with auto-reconnect.

Linkr Bee (BLE/UART wireless serial bridge) as a DeepSeek Harness plugin: a live xterm console in the right column, driven by keystrokes, plus agent tools that run commands on the target board through bee-cli.

Agent governance kingdom for DeepSeek Harness: territories, role bindings (bind/unbind/session with model/agent identity), and a plan→assign→execute→review task loop where Worker claims never auto-complete (Claim ≠ Fact), with a local GUI operations console.

Pair a phone with this computer's DSH instance by QR code or a six-digit code, then drive it remotely — send instructions, view images, answer approvals — from the panel, with public-tunnel support for pairing across networks.

Unofficial QQ bot plugin for DeepSeek Harness (requires a NapCat/OneBot v11 endpoint): editable persona, per-user memory with condensing, session rotation with summaries, image and Bilibili video understanding, sticker library, slang and catchphrase learning, favorability, group management, reminders, cross-group messaging, and a built-in web console. Default-deny: replies to nobody until QQ user and group allowlists are configured. Derived from dsh-onebot; cannot be installed together with dsh-onebot (both register /onebot/api and answer the same NapCat). Video frame grids need ffmpeg on PATH.

A governed registry for MCP connectors (stdio and streamable-http): four-level fail-closed authorization, mcpServers JSON import that rejects malformed args, credential redaction at every output boundary, an agent bridge that returns an honest review verdict instead of a fake approval, and a /mcp-reg operator console plus a settings page.

Drive the Chrome browser you already use: open new tabs or reuse logged-in ones to read pages, click, fill, drag, scroll, screenshot, upload files, export PDFs, inspect console and network logs, and group tabs by task — 38 tools in all. Several harnesses can connect to the same Chrome at once, each working on its own tabs; a tab belongs to one harness at a time, so they never fight over it, and they can message each other. With foreground mode off, operations never bring the window to the front. Requires Chrome 120+; install the extension from the store and pair with an 8-digit code.

Path to Nowhere MBCC dossier theme for DSH, with dark and light palettes, a boot splash, a balance capsule and a settings panel.

One fixed button inside the DSH window that restarts DSH and reopens it automatically, with no console window; right-click it for a built-in self check that writes a single diagnostic report.

One-tap connect SenseNova Token Plan language and image models into DSH (off by default), with image recognition and thinking level filled in automatically. On a rate limit it backs off and retries on its own instead of misreading it as an exhausted quota. After signing in to the SenseNova console you can see the usage pill, credit pools and per-model consumption. Xiaohuanxiong can also be signed in by QR code, bringing in its models and their consumption multipliers, and taking over DSH web search.