Plugins

Sandbox rules for DeepSeek Harness: extra writable roots, write-protected path names with a narrow escalation level for them, read-protected paths.

Implicit session plans with Tab-completable next-message suggestions for DeepSeek Harness

A desktop pet living in the corner of DSH: every hour it brings one official prompt technique from OpenAI or Anthropic — verbatim copy-ready EN template, 1:1 Chinese translation, personalised rationale, and 9 switchable skins.

A OneShot-themed desktop pet (World Machine) with the original game-style dialogue window, per-turn token usage , an optional OpenAI-compatible chat API, lightweight memory and a customizable persona card.

Desktop pet fork of dsh-pet that can be installed alongside the original (separate package id, commands and data directory), adding scheduled reminders with custom bubble text and a random show/hide cycle.

Game market and runtime for DSH. While the agent runs a long task, a game fills the main workspace and a small whale in the corner shows the agent state (working, waiting for you, done, error); progress is saved and continues next time. Ships five built-in games, a game SDK and CLI, and a community catalog installable from the market.

Tarot readings with a dealt card table, a reading tool, and a reviewable history.

When enabled, exchanges the running process's launch token for a browser-session cookie at a configurable public URI (default /trustme), so a first visit needs no ?token= in the URL.

Automatic approval and audit frame for DSH tool calls: a four-outcome rule table (deny, ask, AI review, allow) over commands, file access, network and tool scope, with security rules, rule-based auto-approve/auto-deny, AI fast/deep review, human approval, permission tiers, workspace boundaries, secret redaction and placeholder restore, a hash-chained audit trail and a simulator. Target files are inspected by metadata only.

Ask the executing AI — and the auto-review AI when DSH's auto-review plugin is installed and enabled — about a pending tool approval before you allow or reject it; the executing AI's answers are saved into the session.

Checkup for the whole plugin lifecycle: before install it verifies dsh.bundle, engine and peer compatibility, native build needs, platform limits and whether the new patch would mount a loader name that is already installed (install-shadow prediction); after install it groups every installed plugin by capability; before update it runs the same checks against the new version and reports only the problems the update introduces. Ships a CLI that runs even when DSH will not boot, plus three read-only tools.

Minecraft server ops via RCON with static command blocking, pluggable local/Pterodactyl adapters, configurable community voting, and multi-layer process detection for Paper, Forge, Fabric, and vanilla servers. The QQ group surface requires the @tencent-connect/dsh-qqbot plugin first; the local adapter runs through PowerShell 5.1 on Windows.

Sends one system notification when a DSH turn ends: per-outcome switches for completed, error and interrupted, a minimum-duration threshold, silent subagents and unfocused-window-only delivery. Works on Windows, macOS and Linux, delivered through a connected page or a native fallback (PowerShell toast, osascript, notify-send; the Linux native fallback needs libnotify). Clicking the notification brings DSH back to the front on the page/Electron channel; PowerShell and notify-send notifications are not clickable.

Sends a QQ direct message through a local NapCat (OneBot) instance when DeepSeek Harness asks for permission, after verifying the bot QQ; requires owner/bot QQ ids plus the NapCat endpoint and token, and falls back to a Windows notification when NapCat is unreachable.

Turns a stated rule into a checkable intake card and writes it into the right AGENTS.md, and keeps project plans, a rule ledger, project records, handoffs, a change log and a timeline.

Accounts-payable three-way match: import invoices, purchase orders and goods receipts, apply the tolerance policy and export the exception workpaper — 4 `ap.*` tools.

Logic-risk review before rewriting: audit the source, decide each fix, generate several drafts in parallel, and export with a per-draft audit report. Bring your own OpenAI-compatible API endpoint and key - the plugin ships no model and returns 403 until one is configured.

Skill shell that installs, runs and troubleshoots React-Monitor-Agent, a human-agent operation board built on review replay and checkpoints: the agent writes its work as a structured replay timeline of screen-recording, screenshot, diff and text nodes, and the human decides at plan, progress, risk and delivery checkpoints, with verdicts branching the timeline and rejected branches kept greyed-out for audit. The skill guides cloning the source repo and starting a zero-dependency Node event service on 127.0.0.1:8790 plus a React board on localhost:5173 that ships an offline FIXTURE demo mode. The bundle embeds the skill only; product source stays in the repo.

Measures one university department's research output: matches author affiliation strings against a college's known name variants (detecting same-named departments at other universities), backfills papers that only name the university by faculty author IDs, classifies each paper by journal tier (CAS partition with Top flag, JCR quartile, CCF, Chinese core via a CNKI export merger), splits staff from student first authors, and writes a workbook with a dashboard sheet, a filterable paper list, a teacher-by-direction matrix and per-teacher statistics. Student authorship is inferred from affiliation and staff lists, not verified against enrolment records. Requires Python 3.9+ with pandas and openpyxl (pip install -r requirements.txt); papers come from the OpenAlex API, whose free per-IP quota is limited, and Chinese-journal coverage needs a manual CNKI export.

Replaces the full skill catalog with keyword-based discovery, per-skill enable/disable switches, and system-prompt section controls. Disabled skills are refused by the skill tool, and their slash-command invocations are blocked at pre-step.

Skill bundle that installs the codex-collab skill for driving the local OpenAI Codex CLI as a vendor instead of a consultant: every delegation carries acceptance criteria and a self-test script, the result is verified by running those tests locally, and a failure is handed back with its original error output; batch delegation runs sequentially (parallel subprocesses are not usable locally) and multi-turn continuation stays inside one session. Requires the local Codex CLI and PowerShell 7+; the helper scripts are Windows-native and only partially work on macOS/Linux.

Publish agent output to Reviso for human review, browse published documents from the sidebar, and find them again from the session that produced them. OAuth is host-mediated: Reviso tokens stay in DSH credentials and the browser only receives short-lived embed sessions. Requires a Reviso account or a compatible self-hosted Reviso server.

DeepSeek Harness tools and a Skill for md-report/1: validate and render Markdown plus declared SQLite/CSV datasets into one offline interactive HTML report or dashboard, with AntV G2 charts (ECharts fallback) and chart/table data and source-SQL views.

Audio tools for DSH: inspect audio/video files, transcode or extract the audio track from a video, trim and normalize, and transcribe speech with local whisper.cpp or an OpenAI-compatible API. Requires ffmpeg and ffprobe on PATH (not bundled); local transcription also needs a whisper-cli binary and a ggml model.