Plugins

Thesis and empirical-analysis workbench that drives IBM SPSS from the conversation: spss_check (environment self-check), spss_variables (list .sav variables with labels, types, measurement levels, case counts), spss_data (sample case rows to inspect missing and outlying values), spss_run / spss_run_file (execute SPSS syntax or an .sps file, relative CD and GET FILE paths auto-rebased), and spss_analyze (one-shot frequencies, descriptives, crosstabs with chi-square, t-tests, one-way ANOVA, correlation, linear regression). Results come back as structured tables extracted through OMS. SPSS 25-31 is auto-detected; the bundled MCP server is zero-dependency stdio.

Lets Codex delegate tasks to Desktop sessions through a local authenticated bridge and companion MCP server, with Workspace grouping, model and reasoning effort selection, event tracking, waiting, and cancellation.

MiMo voice for DeepSeek Harness — reads each finished answer aloud, turns composer dictation into text, and offers nine built-in voices plus a cloned-voice slot.

Selection mode for HTML preview and browser tabs: click any element in a locally served demo page and its locator (selector, text, HTML snippet) is written into the chat input for precise AI editing.

Adds a Firecrawl search provider with multi-account API-key settings.

Windows desktop control with window-bound screenshots and accessibility state, text readback, DSH approvals, and activity overlays.

Delegates self-contained coding subtasks to the local Claude Code subscription through the official Agent SDK and returns the result to the host session. Nineteen per-call parameters control model, thinking effort, permission mode, allowed tools, turn count and budget cap; background jobs return a jobId immediately and stream incremental output; the result carries a session handle that can be passed back as resume to continue the same conversation; commands expected to run past ~20 seconds go through the built-in mcp__dsh__shell channel, which streams output line by line without consuming model context; a Claude Code monitor panel in the session lists jobs, renders the structured process, shows live output blocks and cancels a run; the delegation procedure ships as a runtime-registered skill, so installing the plugin installs the skill.

macOS computer-use tools backed by a plugin-owned Cua Driver runtime.

DSH plugin: hands a long session over to a fresh session in the same workspace on /handoff or at a token threshold, carrying the preset, model, permissions and plan mode across; the brief is written by the session's own model and the switch waits for a step boundary instead of interrupting running work.

Uses a dedicated model for context compaction rescue and adds manual compaction to the native context popup.

Adds configurable reasoning levels for third-party models and a model-strength picker in the composer.

Edit reasoning effort levels and thinking formats for models that declare none.

Adds an Appearance switch to the DSH sidebar with a three-second time-stop transition, synchronized sound, and light/dark theme switching.

Restyles the DeepSeek Harness welcome area and composer, with workspace, mode, and skill shortcuts.

MDSM (Male DeepSeek Mascot) appearance layer for the DeepSeek Harness web GUI: wears the bundled mascot character as the GUI background (surface-token fade with opacity, blur, scrim and position controls), seats the matching square avatar as the sidebar and conversation brand mark, and edits it all from a Settings section; the host serves the artwork and config locally under /api/MDSM, and the config lives at $DSH_HOME/MDSM.json.

Zhipu coding-plan sign-in, quota, usage and reset panel for DeepSeek Harness.

A T3 Code-style New Session screen for the composer: a "What should we build in <project>?" headline whose project name opens a workspace menu, a reasoning-effort picker in the composer tool row, and a git branch strip under the card that searches local and remote refs and switches with git checkout.

Composer prompt polisher: a button in the input tool row rewrites the current draft through the session model (workflow engine, enabled automatically) or an OpenAI-compatible standalone API with host-side key storage, backfills the rewritten text with a replace/give-up dialog when the draft changed mid-run, and ships concise/structured style presets, custom templates with a {draft} placeholder, one-click restore from the status dock and reference-chip protection.

Adds text selection annotation tools and annotation chips to the dsh web composer.

Suggests the next user reply in an empty composer after the assistant finishes, using the session model and rolling context summaries, with Tab to accept.

Local-first DSH Web work checklist with rich-text notes, categories, folding, drag reordering, search, JSON import/export, and a restorable trash.

Localizes the DeepSeek Harness approval panel in the web client and translates authorization reasons from English to Chinese, with a built-in phrase dictionary first and a model-router fallback for reasons the dictionary does not cover.