Plugins

Policy-layer guard that checks tool calls before they run: a read whitelist, a sensitive-path deny list (credentials, browser profiles, chat history, other users' home directories), dangerous-command blocking, subagent isolation, and a static scan that quarantines executables. Every denial is appended to an audit log. It is a text-and-path filter, not a sandbox or antivirus: dynamically built paths, encoded payloads and packed binaries can get past it, and it does not replace the OS antivirus.

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.

Compares installed plugins against a downloaded DSH update and reports which interfaces they use that the update no longer exposes. Runs before you install, with a dry-run diagnose command for when it declines to act. Windows only, on the DSH desktop app, with Node.js 18+.

Config-driven lifecycle hooks for DSH: block or observe tool calls, and react to completed turns, messages, and title changes with shell commands.

Compiles a repository into a source-grounded code map: structured pages where every claim carries a verifiable path:line citation, an interactive dependency graph, knowledge cards, four model tools and the /codemap command. Deterministic, no model calls, zero dependencies.

GitHub Trending radar inside the Harness Web UI: fetches the daily, weekly or monthly board (optionally filtered by a language), analyzes each repository into description, star gain, tech stack, highlights and risks, renders the result as a filterable card panel with paging, and registers the github_trending tool plus the /github-trending command.

Turn a script into a narrated explainer video: text-card slides by default (fast and exact for tutorials) or AI-generated footage per segment (needs AGNES_API_KEY); 14 online neural Chinese voices plus 3 offline Windows voices, with a one-command sample pack for picking a voice by ear. Requires ffmpeg, and the bundled video-remix skill copied to <workspace>/.dsh/skills/video-remix with npm install run there for the online voices.

A DSH plugin that queries the account balance and opens the top-up page through commands.

Adds a /context slash command to DeepSeek Harness: shows how much of the session context window is used, how much is free, and a per-category breakdown (system prompt, memory files, skills, messages, tool results). Read-only, local, no model calls.

Native DSH /side conversation tabs with a clean transcript and inherited context, hidden from the main session list using independent Session forks and the official chat UI, with timestamps, token usage, streaming and the command menu. Extracted from dsh-better-sidebar 0.29.0 (MIT); do not enable it alongside dsh-better-sidebar's own /side entry — the two command entries conflict, so stop one before using the other. Requires Windows DSH Desktop 0.2.1-rc.5 and dsh-delete-session for confirmed permanent cleanup.

Adds a prompt-refine button to the DSH composer and, when auto mode is on, refines the prompt before the agent starts by rewriting the text with recent session context through a side-channel model call, asks on the native question card when the rewrite cannot be decided, reports each stage as a command card in the chat, and keeps the original text when analysis fails.

Security plugin that intercepts file deletion and write commands, requiring user token authorization.

Drives the installed AutoCAD over COM and exposes it to the agent as 18 mcp__autocad__ tools: connect and status, cancel the current command, list registered ProgIDs, list or create documents, save, create and list layers, draw lines, circles, rectangles, polylines, arcs and text, list entities, zoom to extents, and pass any native command through. A sidebar panel owns the Python bridge process — start, stop, restart, dependency bootstrap, live logs and crash recovery — and resolves every path at runtime, so the same bundle serves both the web app and the desktop app. Windows only, Python 3.10-3.12, AutoCAD 2022-2024 documented (2024 is the default; other versions require setting CAD_PROG_ID to the matching ProgID).

Keep this session working until a wall-clock deadline: one button in the composer picks 22:30, +90m, or tomorrow 07:00, and after every finished turn the plugin posts one continuation message so the session keeps working; nothing is posted once the deadline passes. Stops early on a round cap (400), three consecutive failed turns, or four consecutive rounds that called no tool; a manual stop button is always there. The last part of the watch switches to wrap-up wording, sized to at most half the remaining time so a short watch is not entirely wrap-up. Armings persist to $DSH_HOME/nightwatch.json via an atomic write and are re-adopted after a restart. No slash command is registered by default (enableCommand turns one on); the continuation message carries source.kind cordis-host-runner, not user.

Action Float for DeepSeek Harness - live, per-session file diffs and command status in a quiet floating ticker.

Desktop pet for DSH with voice chat, personas, memory, Bilibili and QQ context, and command-gated computer control; enable DSH built-in voice input first to use voice chat. A fork of dsh-pet (MIT), not installable alongside the original.

Multi-agent agent team of employee AI subagents for DeepSeek Harness — dsh-company: employee management, CEO bidding, n8n workflow orchestration, drag and drop canvas. DeepSeek Harness plugin with seven built-in roles (project director, product manager, tech lead, engineer, data analyst, QA, reviewer), each with its own persona, model and tool whitelist. Broadcast a mission and the employees bid for it themselves — the first line of their answer must be 【accept】 or 【decline】 — so accepted work runs in parallel instead of down a pipeline. The workflow canvas wires employee nodes with the start node, references each upstream result with {{input}}, and runs the graph in topological layers: parallel across employees, serial per employee, downstream skipped when upstream fails. Ships a web panel for the employee management tab, the mission board and each employee's transcript, the /dsh-company slash command, a live mirror into the built-in agent-team panel, deletable missions, and a private memory directory per employee.

Local-first knowledge base for DeepSeek Harness: each base is a folder of UTF-8 text, text PDFs and OCR-read images; the plugin retrieves from the session's selected bases before every turn with Chinese n-gram and BM25, answers carry citations that open in a right-sidebar reader, and the agent gets five kb_* tools (list, search, read, stats, propose text) plus /kb commands for create, use, files, search and rescan.

Export the current session as a readable Markdown file with dialogue only: user messages, assistant text, and ask_user_question answers, from a session-header button or the /md command.

Generates a session title from the conversation with the session's own model, either from the /ai-title command or from a button in the rename dialog. Four title shapes (subject, action, subject + outcome, custom prompt) and an optional MM-DD prefix, all editable on the plugin's settings page.

Action Hub for DSH: a standard Agent Skill library whose SKILL.md files can run as model-visible Skills or user-only Commands, with groups, project scopes, import/export and a native Alt+A palette.

Auditable mathematical proving for DeepSeek Harness: a local stdio MCP server with 23 machine-checking tools, a bundled workflow skill, and the /prove and /audit-proof commands. proven, refuted and inconclusive are never conflated, and unproven steps are reported instead of hidden. Needs Python 3.10+ with pip install -r requirements.txt on first run; the 23 tools are unavailable until then.

Adds handoff, context-decision and context-diagnose skills, self-contained context_pressure/context_history tools (peak tokens, compaction stats), per-route realWindows with windowSource evidence, routeKey, handoffAt forced-handoff line, and slash commands.

Refuses Git inside a Jujutsu workspace and hands the model the jj command instead. Eleven jj tools, prompt teaching, and a jj-hunk bridge for the DeepSeek Harness.