Plugins

Registers a wrapper provider that gives delegated subagents their own LLM route — one-off spawns through provider.start, Agent Teams members through a hook on startActivation — while the main agent keeps its model. Ships a Settings section for picking that route, a per-expert override file, a capability flag reporting which seams the hook caught, and a readiness record written at mount.

Live CNY cost of the current session under the composer, priced per assistant message by the model that produced it and the peak or off-peak window of its own timestamp, with a Settings page that edits the six prices of every model and marks a model with no rate card with a leading tilde because it is costed from the Flash rates.

Explicit, project-scoped memory handoff: when you open a new conversation, one model call that you confirm curates the project's earlier conversations into a bounded brief and injects it into the conversation's first step. No silent background calls; a Memory panel shows the brief and lets you edit notes.

Routes DeepSeek Harness model API requests through a system, custom or SOCKS proxy; requests outside the configured domains stay direct.

Forked from j62268781-alt/dsh-skills-mcp-manager (MIT) at its 0.5.6 baseline and substantially reworked since; it registers the same plugin id, so it cannot be installed alongside the original. Adds lossless cordis.patch.yml writes (JS expression values preserved), save-gated per-tool filters, skills governance over the DSH roots plus 10 external agent directories with per-skill/per-source switches enforced through the agent-scope skills provider (disabling actually hides a skill from the model), categories and a restorable trash, GitHub-repository install/update/rollback, zip and SKILL.md import, skills.sh/ClawHub market, workspace view, sidebar panel, dark/light contrast fixes, and update checks against the published npm package (same source as market installs; npm publication carries OIDC provenance).

Feishu/Lark bridge for DeepSeek Harness (dsh): one Feishu topic = one dsh session, in-card approvals and questions, streaming cards, model and permission switching, Web settings page, long connection with no public endpoint.

Connect a DSH Agent to Minecraft Java servers with Mineflayer, a live game view alongside native reasoning and tools, configurable personas, server-scoped notebooks, and optional local survival knowledge retrieval. Reuses the host model; installation does not connect to a game or start inference.

Session-level autonomy gears for DSH: a rail on the edge of the conversation area switches P/R/NT/NC/NE/M-/M+/D/A and injects the active gear's behavioral prompt into every request; the model's set_gear tool can only downshift, and handbrake H blocks all tool calls. The set_gear tool can downshift on its own; upshifts need user approval.

Lists the skills in the shared skills directory with their source and version, installs and updates them from a GitHub repo, removes them to a recycle bin kept for 7 days, and controls which agents can see each skill and whether the model may invoke it.

NURBS BRep solid modeling studio with natural-language input, live 3D viewport (measure/wireframe/fit), STEP export, and agent tools driving NVIDIA usd-brep through a managed CPython venv. Needs CPython 3.12; usd-brep wheels cover 64-bit Windows and Linux only.

Records DeepSeek Harness runtime errors and coding retrospectives as an interactive GPU graph, and feeds the recorded lessons back into the model's context.

Adds Regenerate and Edit and resend to each message you already sent: Regenerate re-answers the same text in one click without going through the composer; Edit and resend retracts that message and everything after it in place — out of the transcript and out of the model context, in the same session with no new branch — then puts its text and images back into the composer, so the edited send rewrites the conversation from that point. Messages carrying files rather than images stay disabled.

Connect several OpenAI-compatible gateways at once: each one is its own group in the model picker, can be hidden without losing its settings, and can fetch its own public info from its address, alongside per-gateway model management, model tests and optional quota reporting.

Set the provider, model and reasoning effort delegated subagents run with, from one chip beside the composer: a per-conversation override and a profile-wide default share the same two controls, and the chip always shows the effective route. Applied on the agent/request hook to every in-process child; no settings page, no preset edits, no model-facing tool parameters.

Named subagent presets bound to model-route allowlists, where an out-of-list child model is refused before a delegation starts and each child conversation shows the model its last request actually used.

AI animated themes, computer control, standalone windows, attachment previews, Git management, session pop-outs and annotations, cross-app file drag-and-drop, and AI prompt suggestions. Computer control is enabled from the settings; on macOS it needs Screen Recording, Accessibility and Input Monitoring permission, Windows standalone windows need the Edge WebView2 runtime, and prompt suggestions and AI themes consume extra model usage.

Adds an Optimize prompt control next to the composer send button that rewrites the draft into a structured prompt (plain, sections, or role-task-goal) streamed from the session model, with Use, Undo, Copy and Close.

Model picker control for the DSH composer: a settings section beside the built-in Models page renames model display names and provider group names, adds a short coloured suffix capsule after a name, groups models from different providers into a new partition, reorders provider groups by drag or keyboard, sorts models inside a group by catalog order or name, and hides a provider or a single model without removing it from the catalog. Edits stay in a draft until you press Save, and the built-in 1017 tag and a custom capsule can be shown side by side.

DeepSeek Harness plugin that stops shell commands that would hang a turn (editors, REPLs, pagers, watch modes, dev servers, tail -f, interactive logins, git commit without -m) and tells the model the non-interactive alternative.

多模型圆桌辩论插件：让 DSH 里已配置的多个 AI 带着各自人设围绕同一话题多轮互喷，共享上下文，裁判按六维（攻击性/逻辑/人设还原度/趣味度/策略/深度）加权打分，性价比另用 dsh-cost-meter 真实账本单列，输出 Markdown 战报与 docx。Multi-model roundtable debate plugin for DeepSeek Harness.

Reminds the agent to speak up when it runs several model steps without emitting any text, so long tool runs stop going silent.

Database access for DeepSeek Harness through the DBHub MCP server: configure MySQL, MariaDB, PostgreSQL, SQLite and SQL Server connections per workspace and environment, then let the agent configure, list, query and search SQLite objects through four fixed tools. Passwords and full connection strings are entered in the settings UI and never accepted as tool arguments, so the model only sees metadata such as mysql://host:3306/db; each environment can be read-only (the model may enable it but not clear it) or reached through a manual SSH tunnel. Every call runs its own short-lived dbhub process and dbhub installs itself when missing.

DeepSeek Harness 插件：把本机已登录的 WorkBuddy / WorkBuddy AI / Hermes Agent 大模型接入 DSH 模型库，显示与 Agent 一致的模型名称、积分倍率与免费额度。

A photo-real desk pet for the DSH window: five personas with five expression sprites each, whose dance, hair-flip and walk actions play as 24 fps VP9 alpha video clips, plus a single-shot stage clip that walks to the centre, dances and walks back without cutting; proactive lines with an optional edge-tts neural voice, ink / confetti / cloud / fog / bomb effects, a right-click menu and a /dsh-pet command, plus a small chat box that answers through a one-shot host model call without writing to your session. UI text ships in en, zh, es, pt and hi.