Plugins

Bridge Claude Code's .claude/ directories into DSH with zero migration: project and user-level skills, commands, rules (one system-reminder envelope), agent files, hooks (PreToolUse/PostToolUse/UserPromptSubmit/ SessionStart/SessionEnd) and .mcp.json servers, plus Claude Code plugin marketplaces. Ships /cc-plugin for full plugin/marketplace management (claude CLI first, self-implemented fallback), /cc-resume to list and import Claude Code sessions into DSH as native event-sourced logs, and /cc-export to write DSH skills back as Claude Code skills. Two-way Claude Code <-> DSH bridge, versioned and released as dsh-claude-compat.

Smart Charts skill: turns CSV/TSV/TXT/XLSX/XLS/JSON data files into standalone interactive ECharts HTML - 32 chart types including offline maps, 3 themes, no CDN. A --profile data profile (per-column dtype, cardinality, missingness, samples, statistics, entity grain, insight signals) lets the agent read the data and pick the chart itself; each chart embeds a fact sheet (plot_stats + data_preview) whose numbers are the only quotable values. LLM transform code runs in a restricted sandbox (blacklist + AST whitelist + safe builtins); --doctor self-checks the Python environment. Fully offline, ECharts bundled.

Project file explorer in the details column (multi-select, drag-move, upload, download, rename, trash, system-open) with an in-session read-only preview tab for Markdown/HTML/JSON/CSV/notebook/PDF + code highlighting, a live model throughput badge, and a multiline GoalBar.

AI image and video studio as a floating DSH panel, so creation runs alongside the conversation instead of replacing it: text-to-image, image-to-image and multi-image composition at 1K-4K across eight aspect ratios; text-to-video and image-to-video with first-frame control at 4-12 seconds; short-drama mode that imports a script (.txt/.md/.json), breaks it into storyboard shots for preview and batch generation; and a prompt-expert workspace. Zero runtime dependencies.

Tool-output repair layer for DeepSeek Harness — JSON schema enforcement, parameter mapping, and JSON repair for tool calls.

Cordis /hongtou command: two-phase pipeline (LLM structured JSON + deterministic Word 2003 XML template rendering)

Fifteen curated theme families and nine complete dsh-web-ui skin replicas in one plugin behind a single settings entry, with CSS-only custom theme JSON, controlled custom skin-pack import via folder picker, preview, apply, delete and restore-default. Ships on npm as `dsh-appearance-gallery`.

Multi-dimensional quality scoring for DeepSeek Harness plugins that scores a repo or npm package across install success, maintenance activity, documentation completeness, security scan, and protocol compliance using real CLI evidence, and produces a JSON or Markdown leaderboard report.

Faithful port of the hermes-agent MEMORY.md / USER.md mechanism for DSH: bounded dual-bank memory (2200/1375 chars), a single `memory` tool (add/replace/remove/batch), frozen-snapshot injection per session, nudge reminders, DSH-native JSON storage — zero external dependencies, zero LLM cost.

SearXNG-backed web_search provider for the web seam: free, self-hosted, key-less metasearch through your own instance's JSON API, with a bundled loopback-only docker-compose example.

Turns the DeepSeek Harness agent into any character: a global cosplay switch, SillyTavern v2 role cards with JSON import/export, a neutral/role thinking-style toggle, and natural-language card authoring via a built-in skill.

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 23-check M-gate, a G0-G14 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 11 zero-dependency verification scripts, with five-language READMEs.

General-purpose knowledge base for DSH: import md/txt/json/yml/docx/pdf, folder management, FTS5 full-text search (BM25), and a Web management UI.

Browser-local prompt library with a composer picker for injecting multiple session-scoped system prompts, branch inheritance, bilingual UI, favorites, and JSON backups.

Renders OpenTiny GenUI charts, forms, calculators and mini apps inline in DSH replies via schemaJson fences, with user actions flowing back into the conversation.

Authentication gate for the DeepSeek Harness Web UI: the login gate covers pages, /api, /plugins and WebSocket upgrades; PBKDF2 password hashing, HttpOnly SameSite session cookies and IP-based login lockout; invite-code registration; two-factor login with TOTP or passkeys (WebAuthn: several keys per account, phone enrolment by QR, username-less sign-in, and a password or second-factor step-up before any login factor is added or removed); a user-management settings panel (users edit their own profile and manage their own TOTP and passkeys, admins add or remove users, reset passwords, manage invites and clear the passkeys of a lost device); admin-only model and API-key configuration guards; per-user isolation on the REST/list APIs and on the WebSocket event streams; session persistence across restarts; a JSONL audit log; and a fail-closed gateway. Runs on both DSH transport lines (0.1.1-rc.2 legacy and 0.1.2+ modern) with no configuration; passkey login needs a localhost or HTTPS origin because browsers require a secure context.

Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.

Browses checkpoints produced by dsh-checkpoint-rewind as a timeline of time nodes and shows per-file line diffs between any two of them, with trace replay from session logs (no snapshot producer needed) and preview-first workspace rollback with single-shot undo, via /diff and /rollback commands, a JSON HTTP API, and a GUI panel.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Session deep links, full session export (markdown/JSON), approved cross-session messaging with pairing, and team roster, rotation and recovery tools for multi-session work.

DSH Desktop enhancement plugin: it puts verifiable facts on the table. Constraints are injected only when relevant, so idle chat costs no extra tokens; injection is layered (session-stable text in the system prompt, volatile content as a tail snapshot) and the prompt cache stays valid. Discipline: each turn is classified (question / research / discussion / diagnosis / execution) with boundaries enforced - no file edits on question turns, no unsolicited fixes on diagnosis turns; citing code lines not opened this session, negative claims about unseen symbols, requirements that do not match the deliverable, and dressing up “I did not check” as “waiting for your decision” are all called out; replies are written for humans - a code, field name or id must be explained in plain words the first time it appears. Memory and knowledge: 75%/90% context warnings plus an exported session recap (say "continue" in a new session); project knowledge accumulated across sessions by working directory, auto-captured and deletable by id. Inspectable artifacts: task contract / change record (auto-logged, unverified items flagged at delivery) / hypothesis record (conclusions must pass an evidence gate) / design decisions. Dashboard and personas: routing, trigger hits and block assembly are written to lume-metrics.jsonl and queryable via lume_metrics; personas are distilled from chat logs, novels, scripts or character sheets, with long-term and temporary memory, a memory star map and persona card export/import.

FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. Thin bundle that spawns the local Python CLI (python -m formatforge) and returns protocol JSON; enhancement is delegated to the cur

Popup guardian for session logs: opens with the Web UI on a configurable reminder interval (10 min-3 h), with one-click incremental backup of every session.jsonl(.zstd) under ~/.dsh/sessions in raw or readable chat-log format.