Plugins

Subagent model control: a Jev classifier labels each turn, and the subagent request itself is rewritten to the provider, model and reasoning effort that the label maps to, at the agent/request hook; a per-session inherit/auto/manual selector, one prompt per role injected ahead of the task, and offline replay of past verdicts.

EIA technical guideline applicability and execution-standard check.

Drops a bowl of white rice from the top of the DSH window for every N tokens you spend; the bowls fall and bounce under gravity, can be dragged and thrown, and a vortex button (with a sound effect) inhales them all — or just the one you drop on it. Threshold, bowl size, on-screen cap, auto-righting and artwork are adjustable in an in-app panel.

Blocks AI coding agents from editing files without evidence and from running unapproved high-risk commands, and tells quoted dangerous strings apart from commands actually being executed.

Graph-based code context, impact analysis, review workflows, interactive graphs, and permission-controlled refactoring for DSH using the code-review-graph engine.

Self-organizing multi-agent clusters with no orchestrator. Real DSH subagents coordinate through a shared append-only log that each agent reads and writes on its own schedule, with no topology and one dispatch per agent; a snapshot mode is also included where the harness freezes each neighbour view into the prompt and drives a ring/mesh/swarm cluster to convergence.

Gives DSH the full 33-tool browser surface (ctx.browser seam -> a self-hosted headless moli browser over CDP: one 127.0.0.1 daemon with Bearer-token auth, request-path whitelist and WebSocket rewriting, no root/GUI/Electron needed; single-engine moli serve with auto LD_LIBRARY_PATH/FONTCONFIG_FILE injection and a persistent profile dir for logins), plus a web panel — a real page you can click, scroll and type in, operation/console/network logs with one-click cleanup, a customizable window (border color, transparency, glass, fit-to-picture with no black bars, top-inset and self-centering) and an adjustable page size (1920x1080 by default) — plus a collapsed pill that can be dragged to any spot on the screen (free position), a live view that auto-resumes when you switch back to the web tab, and a 1920px default max edge for the live frame — and two bundled skills (browser, browser-runtime) served through the plugin built-in skill provider, so the skill centre lists them as system-level by default without writing into $DSH_HOME/skills.

Read and write Apple iCloud Calendar over CalDAV through five tools: list calendars, read a window with recurring events expanded, create an event, and delete behind a dry run that must confirm the exact object count. Credentials come from DPAPI, Keychain or libsecret, or from an environment variable.

Cross-session memory as plain Markdown per workspace: weighted injection, bi-temporal invalidation, TTL review with stale markers, credential redaction, error and session retrospectives, SOP skills, and approval-gated self-improvement proposals.

Injects the exact current local time and the timestamp, day relation and recency gap of the previous user message into every prompt, and adds a /time command that prints the injected block.

OpenCode Go in the DeepSeek Harness model list, providing subscription quota display, model discovery, session affinity, and more.

Deep-sea whale-blue reskin for the DSH Web GUI: 14 theme tokens in light and dark, five whale-tail-maid placements, a clock and weather card, and a collapsible hardware readout (CPU, memory, GPU, per-drive temperatures via HWiNFO). No backdrop image is bundled; drop your own in. MIT code, MIT character art.

Token usage panel for DeepSeek Harness: a bar above the composer opens billing token totals, trend charts, per-model and per-project breakdowns and a custom date range, read from local session logs of DSH, Codex, Claude Code, Trae and WorkBuddy. With a self-hosted portal URL and an app key it also reports usage events to that portal; with neither configured it collects nothing. It exposes token_usage tools plus a ctx.tokenReport service, and never collects conversation content.

Copying rendered math from the chat puts the formula's LaTeX source on the clipboard instead of KaTeX's visual glyph text.

Turns file and directory paths in DSH chat into clickable buttons: click one to preview the file in the right sidebar, or open it with the system default application.

DeepSeek Harness plugin: show a provider + model icon in the sidebar for every session, updated live from the composer model selector with a last-request fallback for history sessions; aggregator routes render the provider logo with a 10px model logo in the corner.

One-button prompt optimizer: rewrites the composer draft via a configurable strategy, with an editable template, few-shot examples, pinned models and reasoning effort.

Compact 56px app navigation rail with a separate conversation list and sidebar collapse control for the DSH web UI; also hides embedding, rerank and image/video generation models from the chat model menu and /model.

Switch providers and models, adjust reasoning effort; each model remembers its own level.

UI polish layer for the DSH web client: frosted-glass menu surfaces, a draggable reasoning-effort slider that replaces the level radio list, and model-menu navigation that reaches the model list in one click and closes on a single Esc.

Deterministic goal-completion gate for DSH: a contract-first AC grammar with named failable check commands, a gate that re-runs every check itself (zero model trust), verdicts bound to a tree digest so file changes void passing verdicts, and a hard deny on false completion at update_goal via tools/pre-execute with a false-complete counter that blocks after two catches; scope-aware task-level claim handling (strict or goal-only) keeps multi-task Agent Teams loops from deadlocking.

Injects conclusions already established in the previous reasoning block after each tool result, so the model continues from them instead of re-deriving the same conclusions.

Diving-Fish score lookup for MaimaiDX inside QQ, plus qq-bridge chat extensions. #查分 renders a B50 with song artwork from an OAuth authorisation that any member can use, and works without the bridge running; the extensions cover balance and auto-shutdown, reasoning tier switching by billing peak hours, holiday-table coverage, start/shutdown greetings, and an in-QQ feature toggle.

Adversarial review for DeepSeek Harness: put one settled plan on the stand, send read-only red-team experts at it by dimension, then split their findings into single defects you endorse or reject one by one. It never rewrites the plan and never fixes code.