Plugins

Grok-compatible web search with retained source pagination, Context7 and Exa documentation lookup, bounded page extraction, site mapping, offline research planning, and read-only diagnostics.

Preset-mode badge embedded in the "New Session" button: click to pick the default agent preset for the next session (long names truncate with ellipsis so the label stays readable).

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

Durable citation-thread learning companion for DeepSeek Harness conversations

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Alternative plugin market for DSH: curated catalog plus live GitHub browsing, zh/en cross-language search, a fail-closed pre-install static security audit with an install-hook block, and per-plugin README viewing with garbled-encoding repair.

Registers `list_profiles` and `export_profile`, so the agent can show what setups exist and hand back a whole profile — bundle order, plugin versions and patch — as one portable file to share. Read-only.

macOS Dock badge and bubble chime: shows an unread badge on the Dock (dot while running, count when done) and plays a chime while the app is hidden; clears on return, built on the Badging API.

PR evaluation and improvement consultant: assesses PR success probability based on historical anti-patterns and success patterns, with one-click scoring and actionable suggestions.

Shut down Windows automatically after DeepSeek Harness tasks complete — a floating arm button plus a cancellable countdown banner (shutdown /a), zero runtime dependencies.

WeChat Official Account content studio: anti-homogenization rotation writing, low-creativity remediation playbook, blessing-image visual baseline, gpt-image pipeline with OCR acceptance, and the measured xiaolvshu draft web API.

Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.

Agent-callable vision tool that describes local images via any OpenAI-compatible vision endpoint you configure, with an optional multi-model cross-check and no built-in keys.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

SSH remote ops for DSH: pair servers over SSH or a one-time-code remote-hostd, then run commands, manage background jobs, and read or write remote files with reviewable changes (host_pair/host_bash/host_jobs/host_read_file/host_write_file/host_review_changes).

Docker tools for agents: ps/images/logs/inspect/exec/manage/health with JSON output, env-configurable CLI path, approval-gated exec and zero runtime dependencies.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

Evidence-first vulnerability research workbench for DeepSeek Harness: native audit views, 29 OMV tools, Evidence.v1 findings, reproducible runs, Campaign workflows, and isolated PoC evidence.

Session hotkeys for the DSH Web GUI: switch sessions like browser tabs (positional Alt+1-9, pinned slots, previous/next, new/archive/rename), keyboard model switching via Alt+M, alternate send, Esc focus hand-off, and Alt+W to close or restore a dsh-split-screen workspace — all rebindable with Windows/macOS presets. Verified on DSH 0.1.1 and 0.1.5.

Incognito sessions: a standalone ephemeral sub-agent with its own preset (no parent context) and full toolset, draggable floating window, burned to zero traces on close.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

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.

Shows DeepSeek API account balance and Volcengine Ark Coding/Agent Plan quota windows (5h/weekly/monthly with reset countdowns) in the settings panel, composer dock, and a draggable floating refresh button.

Settings usage dashboard: tokens, requests, output tokens, and cache-hit rate from session logs, with a stacked chart and a breakdown table by provider, model, or workspace.