Plugins

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.

Projection-driven live DAG for a Session's subagents and durable workflows: status and navigation, deterministic deep-chain layout, fit/pan canvas controls, and current-session node rearrangement.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Use plugins from ecosystems such as Claude Code and Codex in DSH: add Git plugin sources and marketplaces, upload plugins and skills, add MCP servers, automatically discover and toggle local skills, and manage plugins, skills and MCP in one place, including plugin-provided subagents, Hooks and LSP.

Register locally-defined custom agents as callable subagents in dsh: the main conversation invokes any agent by name via use_agent, each running as a real dsh subagent with its own persona. Supports breakpoint resume for interrupted runs.

Replacement web interface for the unmodified official DSH release: collapsible reasoning groups, a turn timeline with adjustable reading width, cards for tool calls, a model and reasoning-effort picker, an Agents view that shows subagents as a tree, optional chart and diagram widgets in answers, light and dark themes, and a phone layout. Installs from npm; uninstalling restores the official interface. An optional jev_presentation_advice tool, enabled only once you save a TypeSafe key, sends up to four recent user messages and a short outline of the planned answer to api.typesafe.ai.

Desktop side of a native Android DSH phone app: scan a QR code to pair, then chat, approve tool calls, answer questions, drive subagents and follow background jobs from the phone over an end-to-end-encrypted channel; one device at a time.

Task panel for the DSH Web sidebar: publish tasks, auto-distill related sessions, and drive plan/develop/review stages with subagents plus in-panel acceptance.

Adds Delete to the DSH sidebar session menu, moving the session — and its whole descendant tree when it has subagents — into a recycle bin that relocates the directory on disk (an atomic rename, never a copy), plus a sidebar bin panel with title and full-text search, workspace filter, sorting, per-session chat-log viewer, restore and permanent delete. Deleting also clears the workspace slot, the pin, the archive flag and the projection-cache row, so a restore puts the session back at its original sidebar position; permanent deletion also clears the schedules bound to it and removes the emptied project directory. Verified on DeepSeek Harness 0.2.1-rc.2, with a whole-profile residue scan coming back clean.

Expert roster for DeepSeek Harness: 636 experts across 22 divisions with full Chinese names and bios, summoned as subagents from the @ menu or by the model through list_t_experts / summon_t_expert / summon_t_experts, plus custom experts and a skill on/off switch.

Composer and sidebar helpers in one plugin, each switchable in Settings: a git Changes panel, Turn rollback, Resume after an AIProxy outage, Project memory (notes per project that later chats read, off by default), a Task board (kanban board of chats by their live state), Assistant (one lasting chat named Damon that sets reminders with dsh scheduled tasks and reads your other chats; it changes a chat only after an approval) with Assistant callouts, Assistant always free (long steps go to background subagents) and Assistant news from chats (off by default), Remote computers (another Mac's dsh over Tailscale, off by default), 11 extra UI languages and Automatic updates.

Splits New Session in the DSH web sidebar into two modes: a 日常聊天 row opens a session on the `daily` agent preset the plugin installs into the harness home (persona, web search and fetch, ask-user and compaction — no files, shell, plan mode or subagents), inside its own daily-chat workspace whose sidebar region lists only those chats, while 开始工作 keeps the shipped coding agent; the built-in New Session button is hidden and every other New Session entry point follows the active mode, which is remembered in localStorage.

Kanban task board for DeepSeek Harness sessions: the main agent dispatches tasks to one-shot worker/verifier subagents, with dependency scheduling, file-level exclusion locks, arbitration hold/freeze, milestone progress reporting, and per-task token usage stats.

A thinking level stored per provider and model, so reasoning effort outlives the session it was set in and also reaches subagents, which dsh never asks. The in-session picker still wins, and a model with no row keeps its provider default.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/, plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via an in-memory IR that keeps .claude as the source of truth and writes back only when you opt in. Also surfaces Claude Code auto-memory in the system prompt, read-only by default, with a write-back switch in the /cc-memory panel. Eight packages: one bundle that installs the whole set, plus the loader and six adapters (skills, permissions, agents, hooks, mcp, memory).

Engineering workflow agent preset for dsh: five gated phases (requirements clarification, plan approval, TDD, parallel subagents, verified finishing) with six workflow skills adapted from obra/superpowers.

Office workspace & session dashboard: a floating 6-column sprite panel visualizing workspaces, sessions, token usage and subagents, plus Agent Mail and an office log tab. Feishu/Lark views (message feed, meeting schedules, transcripts) additionally require the `@larksuite/cli` tool installed and authenticated separately.

Three tools that let any agent, including a team member, list, steer and stop the subagents it started.

A customizable widget rail for the right side of DeepSeek Harness: 61 cards covering session stats, tokens and cache, context, background jobs, subagents, machine metrics, OpenCode Go and Command Code quota, session cost, peak pricing and the GitHub review queue. Cards install from an in-rail market into 1-4 column grids and 2x2 or 2x4 tiles, with per-instance settings, a magnification wave under the pointer and a one-click hide. Works on DSH 0.1.x and 0.2.x, web UI and desktop app.

Named subagent roster: manage role entries (model, persona, tool filter, depth, background mode) from a hot-reloaded settings page; the model picks one with list_subagents and dispatches by id with delegate — foreground, background, or continuable.

Multi-agent orchestration preset: a lead agent dispatches subagents from a built-in role roster over separate read and write lane pools with per-role model binding, and collects each subagent report on a shared board; adds go_work/continue/need_help/forward tools, a tree-view panel and a settings page.

Dispatch subagents with named profiles (model, reasoning effort, and tool scope per task), safety checks, cost estimation with savings comparison, and a full dispatch decision ledger.

Search, monitor, interrupt, and batch-archive workspace subagents, featuring real-time activity streaming and an active-agent floating panel.