Plugins

DeepSeek Harness plugin: Cursor models as the `cursor` LLM provider, with one Cursor agent per DSH session

Java efficient development plugin for DeepSeek Harness providing deterministic auto-fix for .java files, token-saving template intents, and cross-platform JDK/Gradle/Android SDK/FFmpeg/LWJGL/IDEA discovery with persistent caching.

Claude Code (the official, unmodified binary, via the Agent SDK) as a model provider and subagent inside DeepSeek Harness

DeepSeek Harness sandbox provider backed by MXC (Microsoft eXecution Containers): wraps ctx.sandbox.confine() argv as `wxc-exec --config-base64 <policy> -- <command>` on the BaseContainer backend. One runtime dependency (@microsoft/mxc-sdk, for the wxc-ex

A chibi whale maid desktop pet for DeepSeek Harness who eats white rice while the model generates, lives inside the DSH window or anywhere on a macOS or Windows desktop, and dives for treasure between turns. On Windows the desktop overlay is compiled at install time and skipped when swiftc or the .NET SDK is unavailable, so the pet stays inside the DSH window.

DeepSeek Harness LLM adapter for Qoder CN and Qoder International subscriptions, built on the official Qoder Agent SDKs. Reuses the local qoderclicn / qodercli login, shows the account quota the Qoder clients display, and exposes a fully configurable sett

Skills and MCP management console in the settings panel: merged skill catalog across every provider (hierarchical browse by source, online create/edit, independent model and user invocation switches, recoverable trash), GitHub install with multi-select batch install and update checks, MCP server add/edit/remove and enable/disable through the profile patch layer, cross-agent import from Claude Code, Cursor, Codex, Cline, Roo Code, Continue and Windsurf, and an independent SDK connection probe.

Bridge DeepSeek Harness agent sessions into Feishu (Lark) chats over the official SDK long connection, with a streaming reply card, many bots per instance, and mention-gated group replies.

DeepSeek Harness LLM adapter for Qoder CN subscriptions, built on the official @qodercn-ai/qodercn-agent-sdk. Reuses the local qoderclicn login, and exposes a fully configurable settings page (per-model context window, session pool, timeouts, model deny l

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

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.

DSH Web GUI 日本語ロケールパック: registers the 日本語 language into the shared locale catalog and carries the ja dictionaries for every dsh-web-all family plugin namespace (missing keys fall back to English through the SDK chain).

Windows-only DSH sidebar preview and Dart hot reload for configured Starcompanion / Operit2-derived projects; requires the project preview scripts, a prebuilt debug APK, Android SDK, Flutter and scrcpy 3.3.3.

Requires Claude Code installed and signed in on this machine. Delegates coding tasks to the local Claude Code agent through the Claude Agent SDK, reports which files changed, supports one-command revert, and adds a Claude Mode toggle to the composer.

Turn a GitHub repository's raw counts into a defensible judgement — contributor concentration and bus factor with single-author files, merge time reported as a median beside the mean so an outlier is visible rather than hidden, and an issue backlog with pull requests and drafts filtered out. Reads the public REST API with no SDK, and never claims a truncated page is the whole answer.

Packaging pipeline for uni-app x projects: reads the local HBuilderX version, recommends and one-click installs the matching iOS / Android / HarmonyOS offline SDK (panel card with official download links), then drives the HBuilderX CLI to build, sign and upload apps from per-project config files; the engine also ships as list / doctor / check / build tools for the agent.

Packaging pipeline for uni-app x projects: reads the local HBuilderX version, recommends and one-click installs the matching iOS / Android / HarmonyOS offline SDK (panel card with official download links), then drives the HBuilderX CLI to build, sign and upload apps from per-project config files; the engine also ships as list / doctor / check / build tools for the agent.

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.

Gear-based autonomy governor for the DeepSeek Harness agent: the entropy-sdk EntropyRuntime core (gear ladder G0-G4, utility gate, slow-up/fast-down policy, tamper-evident audit chain) bound to the Harness tool registry, with a live Web UI and paper-ready

Use a Claude Pro or Max subscription as a DeepSeek Harness model provider, by driving the Claude Code CLI through the Agent SDK.

A DeepSeek Harness provider backed by the official GitHub Copilot SDK and CLI

Multi-bot workbench for DeepSeek Harness: bridges the sdk-bots orchestration gateway (group chats, single bots) into the dsh web shell with official-styled UI.

Explains which layer killed a failed turn: times every model request (first byte, longest silence, total) and combines that with the error to name the culprit (dsh idle watchdog vs Node undici timers vs SDK timer vs server crash, context overflow, gate queue, tool timeouts, failed compactions) and the exact setting to change; verdicts in the DSH terminal plus a /why command, subagents included.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.