Plugins

Notifies you about 11 configurable DSH agent events (task completion, questions, denied approvals, background subagents/goals/jobs, team tasks, context compaction, triggered schedules, plugin startup and permission changes) as browser Web Notifications through a bundled service worker, falling back to Windows toast or Linux D-Bus, with three silence levels and click-to-open.

Turns a local Obsidian vault into a dedicated RAG chat panel: a sidebar page with the note browser, the retrieval-augmented chat and the cited source side by side, answering from fully local BM25 plus CJK-bigram retrieval over your notes and streaming through the DSH model channel, with clickable \[n] citations and mtime-based incremental indexing.

Three switchable low-glare themes (Warm Paper, Sage Green, Warm Grey) for the DeepSeek Harness GUI, each a full alias-token layer with a light and a dark face.

Ollama Cloud provider for DeepSeek Harness: adds the chat route on install, publishes each model's own thinking levels for the composer effort control, keeps the model list current from the endpoint (/api/tags and /api/show, cached for offline boots), shows the account allowance with an API-key field in the Models page and sidebar, and offers Ollama's web search and fetch as selectable DSH web providers.

Stop paying for your agent's web search. dsh-searchhub is a pluggable search hub for the DeepSeek Harness — swap in mainstream search providers behind ctx.web, with a beautifully polished native Settings card. Ships with Tavily (1,000 free credits/month)

A fake-ip-aware ctx.web fetch provider that takes over the stock http provider id: a hostname is accepted when every DNS answer is a placeholder inside the proxy's fake-ip block (198.18.0.0/15 by default), so web_fetch works under mihomo/Clash TUN mode without disabling fake-ip or setting proxy environment variables. IP literals and private, loopback and reserved destinations stay blocked.

Gaokao countdown blackboard: counts down the days to the gaokao on a desktop blackboard widget that collapses into a slim bar on double-click, and quizzes random knowledge cards while the agent works; open Markdown knowledge-card framework — drop .md files under subject/category folders and they load automatically, with cross-links, favorites, priority subjects and importing your own knowledge base.

Six engineering skills for Claude Code and DSH: research, architecture scouting, implementation orchestration, three-axis diff review, complexity audit and mutation testing. Skills delegate through the host’s generic subagent tools when available.

Select text in the DSH web UI to stream a translation and an explanation of what it means in that specific context, read against the conversation it came from; the panel keeps a replayable history and can be promoted into a full session.

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.

Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool that returns probability-distributed answers to typed questions (choice/score/boolean) in one call.

TypeSafe Jev as a first-class Cordis service and three model-visible tools for DeepSeek Harness — offline by default, egress disclosed, never default-on.

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

Image generation tool for DeepSeek Harness over any OpenAI-compatible images endpoint, with an inline Web UI gallery.

Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Hot-switchable brand skins for the DSH Web UI: an OpenBMC skin, a UEFI skin and an unofficial fan-made skin based on A Record of a Mortal's Journey to Immortality, each with light/dark schemes, plus a personal wallpaper gallery, per-skin tagline and transparency controls, and a one-click path back to the official look.

Goal mode and autonomous execution plugin for DeepSeek Harness: a sticky top banner keeps the current goal visible across turns while the agent works toward it autonomously.

Interactive chat table of contents with bookmarks, turn pinning, global shortcuts, and heading extraction.

Stops a streaming model call when the same string repeats ten times in a row (threshold configurable), keeps the partial answer as a normal assistant message, and shows a stop notice with the workspace, session name and the repeated string. Repeat counts can vary by unit length through a piecewise table or a JavaScript module, and code regions (fenced, inline, indented) use a relaxed threshold.

Freshness gate for the agent's test, typecheck, lint and build claims: each verification run becomes a receipt on tools/post-execute, file edits are tracked, and on agent/turn-stopping a claim whose latest receipt is stale, failed or has no readable result steers one more step naming the receipt and the files edited since.

Blocks edit/write writes that contain characters matching configurable regex rules, executed before the tool runs, with configurable messages and same-turn pwsh propagation; default rule matches full-width parentheses.

Watches agent execution traces and fires an LLM review at every successful turn end when signals trip, crystallizing reusable workflows into registered skills that improve progressively with later runs.

Injects durable user-set must-do and must-not requirements into the model at conversation start.