Plugins

Authorized-security DSH collection: nine work modes (redteam coordinator, pentest, code audit, binary analysis, attack-defense, AV evasion, incident response, cloud security, CTF solving) and fifteen runtime plugins, managed from a settings page with one-click deploy, install, update and uninstall.

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).

Causal memory for dsh: a zero-dependency MCP stdio bridge that mounts the 17 tools of the causal-memory server under clean names (no mcp__ prefix) — decision → outcome edges with typed relations (caused / enabled / prevented) in a local SQLite store that survives compaction — plus a pinned system-prompt section. Requires the causal-memory server binary on PATH (pip install causal-memory, or a prebuilt release).

Third-party adapter that registers the upstream REA (Reverse Engineer Anything) MCP server into DeepSeek Harness as mcp__rea__* tools. 2.x provisions its own runtime (Node, the REA CLI, a JDK, Ghidra) under <DSH_HOME>/plugins/rea-bundle and launches REA through a shim, so a machine with nothing pre-installed works after one setup run; 1.x (branch v1, npm 1.0.6) is configuration-only and expects REA and Ghidra to be installed already. Analysis is upstream's: native binaries (Hopper/Ghidra/IDA), JavaScript/Electron apps, .NET assemblies, websites, Android APKs and adb devices, firmware, and process captures.

Answers the built-in web_search from a self-hosted RustXNG metasearch instance, downloading and starting that binary on demand and stopping it after an idle timeout; an optional fetch provider also decodes pages whose charset is declared only in <meta>.

Unit conversion toolbox covering 20 categories — length, mass, temperature, area, volume (incl. US cooking units), speed, time, data sizes (decimal MB vs binary MiB), data transfer rates (Mbps vs MB/s), acceleration incl. g-force, illumination (lux / foot-candle), pressure, energy, angle, frequency, power incl. three horsepower definitions, force, torque, typography (px/pt/em/rem), and fuel economy (mpg ↔ L/100km). Two tools — convert_unit and list_units — zero runtime dependencies, pure arithmetic; each result includes the formula applied.

Bridges a local MATLAB MCP server into DSH: evaluate MATLAB code, run .m scripts and tests, and inspect installed toolboxes via mcp__matlab__* tools. Requires MATLAB and the MathWorks MATLAB MCP Server binary, and a path edit after install — the plugin on its own registers no tools.

Text viewer and editor for the dock workbench: undo/redo, Ctrl+S save, unsaved-change confirmation and binary detection, registered as the default file viewer.

LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.

Runs a Douyin subagent that browses videos and reads comments in valley hours and reports back, with dy_* tools for publishing and replying (comments sent from the already-logged-in page with its own request signature, no IM ticket), a daily quota timer, and a settings panel under Settings → Douyin: master switch, auto mode, valley windows, rounds per day and report depth. Windows-oriented; needs the separate douyin-mcp binary (yunsur/douyin-mcp releases, path set via dy_config mcpExe) and an Edge/Chromium login; replying needs a logged-in browser on a CDP port; publishing needs extra credentials most accounts lack.

Shrinks oversized bash and job_output text by piping it through the external rtk binary, keeps the original in a spill file and lets the model fetch it back on demand; keeps the original text when rtk is missing or fails.

Registers 12 CatPaw (妙手) models as a DeepSeek Harness provider, with per-model reasoning effort, harness-executed tool calls, and QR-code login. The bundled catpaw-cli is a macOS arm64 binary (other platforms must supply their own copy), and calls use the signed-in CatPaw account quota.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Runs the locally installed ZCode CLI as a `zcode` model route in DSH: all traffic is signed by the official binary, the plugin never sends its own request, forges client requests or sends credentials off the machine (the plan token is decrypted in memory only to hand back to the official CLI), no API key is needed, and both a paid one-shot and a free app-server channel are supported. Since v0.3.0 it ships an HTTP MCP bridge so tool calls run through the DSH approval surface. Backed by a contract document and a node --test gate.

Claude Code (the official, unmodified binary, via the Agent SDK) as a model provider and subagent inside DeepSeek Harness

Visual browser for DeepSeek Harness: a right-sidebar tab under the built-in Browser that streams Chrome live as a binary JPEG frame stream (no screenshot polling) while the Agent drives it through a token-light numbered view of interactive elements, never

On-screen test-progress HUD for DSH — a click-through panel drawn over the app under test, showing each step's expectation vs actual and whether the waiting human may take back the mouse and keyboard. Ships a universal prebuilt binary (arm64 + x86_64), so no Xcode Command Line Tools are needed; the panel itself requires macOS 14+.

Keeps the DSH desktop window the size you left it: records the last outer frame of the main window in physical pixels and restores it, centred on the work area, on the next start - and it acts before the window is ever shown, so the boot animation plays at the right size. The settings page offers 12 presets (1024x768 to 3840x2160), free-form custom width and height, a centre-on-restore switch and an apply-now action; a choice takes effect immediately and persists. Resizing goes through a small helper executable compiled on the user's own machine: the C# source ships inside the plugin, is built on first run with the in-box Windows csc.exe (measured ~110 ms once, cached next to the state file, ~90 ms to start), and falls back to a short-lived powershell.exe process when that is not possible. The package ships no binary, declares no npm dependencies and makes no outbound network request. Windows only.

Read Windows service state from WSL: list services, or inspect one by name with its dependencies, logon account and binary path.

Release playbook for AI agents. npm-installable CLI + DSH plugin + skill bundle. Covers npm, GitHub+Gitee dual remote, DSH marketplace, cargo crates.io, PyPI, PyInstaller exe, Go single-binary, Rust single-binary, Electron/Tauri desktop. Bilingual EN/ZH.

Subagent delegation provider that runs any Claude-compatible CLI binary pointed at by a configurable executablePath field.

Installs and runs Android native command-line tools from inside DSH: fetches aarch64 bionic packages from the Termux repository, unpacks them in pure JS and runs them through /system/bin/linker64, with no root, no Shizuku and no external package manager.

Connects DeepSeek Harness to LRC's local structured memory: distills conclusions every 8 turns, drops near-duplicates by character-level Jaccard similarity (≥ 0.85), and writes them to a local LRC store. Five tools — lrc_recall, lrc_forget, lrc_remember_now, lrc_handoff and lrc_status — cover on-demand recall, retracting wrong entries, immediate writes, session handoff and a status line. On first run it downloads a per-platform LRC binary (win32-x64, darwin-arm64 or linux-x64, SHA256-verified) and starts an isolated instance, so the LRC desktop app is not required; data stays in $DSH_HOME/cache/lrc-plugin/data unless LRC_BASE points at an existing instance.