Plugins

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session resume, and DSH tools bridged in over MCP so they keep DSH sandbox and approval.

Polymarket toolkit for DeepSeek Harness and Claude Code: market-data tools for Gamma/CLOB/Data-API (31 model tools in DSH; read-only subset exposed over MCP), opt-in authenticated trading tools, WebSocket stream service, and an embedded Polymarket knowhow skill.

Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.

DSH Skill Manager: browse, enable/disable, import from Codex/Claude Code/ZCode/WorkBuddy/QCoderWork, auto-discover skills with symlink support.

Project documentation scaffolding skill: question-driven setup of project standards, AI-collaboration workflows, and memory discipline across DSH, Reasonix, Claude Code, and Codex.

Claude Code-inspired skin for the DeepSeek Harness web GUI

Claude Code-style permission rules engine: hard/deny/ask/allow tiers with a hard tier above full access, workspace-scoped rules, wildcard path protection, and a visual staged editor; rules persist in settings.yaml.

Claude Code rules.md-style rule prompts: activate rule markdown files by glob-matching the files an agent reads or edits, with prompt injection and ordering support.

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.

Import local Codex, Grok, Claude, OpenCode, and CC Switch logins into DSH; pick sources and enable models in Settings.

Opens a separately downloaded Windows desktop pixel monitor for pi, Claude Code and DSH sessions. DSH monitoring is read-only.

Search Wikimedia Commons and Openverse for real photos, download them, and verify provenance, magic bytes and dimensions before they reach your agent.

Travel wallpaper for DeepSeek Harness: pick one of three built-in characters (DeepSeek whale girl, GPT dragon girl, Claude young lady) or upload your own reference photo, or observe a world without any character; choose a world and one of 20 art styles, and the plugin assembles the image prompt, generates the wallpaper through your own image channel (ChatGPT or Google subscription, OpenAI-compatible API, Gemini, Volcengine Seedream, or local ComfyUI/MOSS) and applies it to the Windows desktop or lock screen. Character trips also return world events and a letter from the character, and replying to the letter shapes the next scene; observe-world trips return world events only. Every trip stays in a browsable archive with image and ZIP export. Ships daily wallpaper, instant blind-box trips and scheduled blind-box trips. Data lives in ~/.dsh/planet-news; provider credentials are read from DSH's credential store, and the plugin provides no image quota.

One page for every skill on your machine: lists what DSH, WorkBuddy, Claude Code, Codex and Doubao have installed, imports any of them as a DSH skill, and discovers more on GitHub or the ClawHub directory (sorted by real downloads). Experts can be attached per session with a per-turn avatar header.

View and edit the AGENTS.md / CLAUDE.md instruction chain in a native right-sidebar tab — global, shared, and every project directory down to the session working directory — with in-place save that creates missing files, a chat-header toggle, and an /agents command that works without the panel.

Turn code flows into source-linked Mermaid diagrams and interactive CodeWalkthrough explainers.

Adds an Agent docs tab to the conversation view: it lists the AGENTS.md and CLAUDE.md instruction files DSH actually loads for the current session (the ~/.dsh and ~/.agents roots, plus every directory from the project root to the working directory), previews each as Markdown with per-file sizes and the 64 KiB instruction budget, edits and saves them in place after a sha256 version check, and opens the workspace folder from the path button; a saved file takes effect on the next message.

One panel for MCP servers, skills and Claude Code plugins across global/profile/project scopes: live status, import/export, trash & backups, and the official claude-plugins-official market (install/update/uninstall).

Runs a project's Claude Code opening questions and plan, hands the task to DSH, and offers post-turn Claude review choices. Windows only, and requires a locally installed Claude Code CLI (set claudeCliPath if it is not auto-detected). New sessions handed to DSH are switched to danger-full-access. The first Claude run in a project folder sets hasTrustDialogAccepted for it in ~/.claude.json, and optional automatic Claude review is capped by a daily budget ($5 by default).

Browses the awesome-claude-video-skills catalog (373 entries) inside DSH settings and installs a chosen skill into ~/.claude/skills and/or ~/.dsh/skills: it downloads the GitHub archive of that repository and copies the skill directory, and executes no code from the repository. Installs run as background jobs with live progress (bytes downloaded, files copied) and can be cancelled; skills installed by the plugin can be uninstalled, while directories without its marker are left untouched. Rows show an approximate repository size reported by GitHub. The same actions are exposed to the agent as the video_skill_search, video_skill_install and video_skill_uninstall tools.

Superpowers skills for the DeepSeek Harness (dsh): a full engineering methodology served through dsh's own filesystem skill provider, with an always-on bootstrap.

A six-stop reasoning-effort slider for DeepSeek Harness, with a pixel-texture Ultracode mode that sweeps in from right to left and adapts to light and dark themes.

Adds a capability panel to the DSH web GUI: browse, install (upload, zip, host path or URL), enable, edit and export skills, and add or edit Claude Code-compatible MCP servers, at global and per-project scope — with project copies, per-project shadow stubs, live mount status and a zero-side-effect connection probe. A session view toggles capabilities for the current conversation only, and a TypeSafe Jev tab scores skills and MCP servers for the session from the input draft. Requires the dsh web shell 0.2.0-rc.2 or later. Forked from chengdb/dsh-plugin-capability-panel; it shares a patch id with that plugin and with pure-craft/dsh-capability-panel, so do not install them together.

Mounts external skill directories (Claude Code, Codex, ZCode) into DSH as read-only skill providers: frontmatter field mapping, name slug normalization and hot reload.