Plugins

Agent preset bundle for wish and task management: create wishes or tasks from conversation, opportunity-day check-ins, micro-actions, plus a memory store and progress charts in the web UI.

Windows minimal agent preset for DeepSeek Harness: fixed one-line persona, three tools, no runtime context.

Adds a subagent_routed tool that runs a one-shot subagent fully mounted on any agent preset from any session, with per-call model/provider override and a model-availability pre-check.

More agent presets for DSH, derived from other coding agents such as Qwen Code and iFlow.

Pi-compatible tool suite recreated inside DeepSeek Harness: installs lower-case read/write/edit/bash/find/grep/ls core tools while retaining DSH-backed web, task, plan, todo, think, and slash extensions.

Windows-adapted DeepSeek Harness coding-mode agent preset with a persistent PowerShell 7 shell.

Bounded, privacy-safe local scanner for Codex, Claude Code, WorkBuddy, and CodeBuddy metadata: atomically aggregates keyed evidence and deterministically advises built-in DSH presets and optional capabilities—without content retention, network access, or preset mutation.

DSH-Heros adds a bilingual loadout screen for Agent Presets, tools, and plugins. Preview capability changes, open the selected loadout in a DSH session, and earn XP and cosmetic rewards from completed work.

Plugin classes for DeepSeek Harness: installing a plugin is global, so every session sees every tool. This plugin splits installed plugins into mutually invisible classes and registers each composition as an ordinary @deepseek-ai/dsh-agent-preset, so a session mounts only the plugins of the classes it belongs to; classes are toggled from a chip next to the model selector. Deleting a class only hides it (its preset stays registered), so sessions already bound to it still open.

A TRAE-宝-style personal assistant plugin for DeepSeek Harness: cross-session long-term memory, auto-extracted candidate memories, first-time onboarding, a dedicated assistant agent preset, scheduled daily digest, desktop notifications, and a live overview panel.

面向个人的 AI 学习系统：多会话分工、文件记忆、学科插件（DSH 插件包）

Build presets for DSH Agents: package personas, prompts, skills, tools and runtime contexts into reusable capability bundles. Each task loads only the components it requires.

A six-stage development workflow preset for the Matt Pocock skill suite: grill, spec, tickets, implement, review, wrap-up. Adds a stage chip in the composer tool row and decision cards that ask up to three multiple-choice questions at a time.

Cleanup Mode agent preset for DSH: read-only scans of leftovers (including duplicate detection), a manifest before anything is deleted, trash-first removal only after confirmation, and a per-session audit log. Cleaning outside the workspace requires a danger-full-access session; under workspace-write it can only inspect and will ask you to raise the permission.

Task Center for the DeepSeek Harness Web GUI: create and manage Host-wide scheduled and webhook tasks from the right sidebar, delivered into a new session in any workspace or into an existing session, plus a 任务管理 agent preset.

Learning-mode agent preset for DSH with a topic knowledge base: answers retrieve from your own stored cards and cite the card they came from, mark anything not found as unverified, and only go online when verification is required. The sidebar panel browses topics, searches and edits cards, and every card can be AI-reviewed, verified, rolled back and versioned. Cards can reference each other with `[[title]]` links; the panel shows both outgoing links and which cards reference the one you are reading. New cards arrive as a preview you confirm before they enter the library; topic and card names are editable in the UI. The knowledge base is plain local files, not an automatic scraper.

Named roles, model route guards, native configuration, and request-model visibility for official DeepSeek Harness subagents.

A soul for DeepSeek Harness: an in-character Whale Chan agent preset with layered long-term memory and dream-like consolidation.

Ponytail port: a DeepSeek Harness agent preset that makes the model finish tasks with the least tokens, with lite / full / ultra levels.

Rebind running sessions onto a rebuilt agent-preset revision, so preset changes apply without restarting dsh.

Recursive delegation for dsh agent trees: a preset plus Host limits bound what each subagent may do, subagents work in separate _agents/ workspaces, and the parent decides which results to integrate.

Agent preset for DeepSeek Harness: the standard tool stack plus four working rules written into the persona prompt — a project keeps at most four documents (intro, decisions, change log, current state and next steps), those documents describe only the current state with no AI edit history or superseded decisions, no git commit or push or pull request until the user explicitly asks, and a careful-coding workflow (restate the goal and done-criteria first, surgical diffs, evidence before claiming success) with plain-language reports.

Optional JEV decision mode with deterministic project reads, bounded semantic selection, native authorization checks and desktop credential settings.

DSH plugin: a four-entry learning flow in the session input bar — scaffold a preset, collect candidates, merge reviewed changes, and run a read-only workspace audit.