Plugins

CCReach capability-search provider for DeepSeek Harness, letting agents discover data sources, tools, APIs, MCP servers, skills and workflows.

Keeps a per-turn receipt that later turns do not clear (final todo counts, goal id and phase, end reason, and a fail-closed pass/fail/inconclusive plan verdict), plus a read-only tool to read recent receipts. Stores counts and ids only.

One standing system prompt for every workspace: a Custom instructions page in DSH's own Settings panel whose text is added to the system prompt of every session, subagents included, and stored in the profile instead of any project.

Per-request cost ledger covering retries and subagents, holiday-aware peak/off-peak pricing, shared pricing/usage/balance/budget services, and DeepSeek bill reconciliation.

DSH Desktop control center: one-click app updating (progress dialog, unattended install, resume), plus Skills / MCP / Agents / Import settings pages — import agent presets and chat history from Codex, Claude Code, TRAE and WorkBuddy, search remote sources by address, and push notes straight into the composer.

Connect multiple decision providers and models through one interface: Jev via TypeSafe, Clef via Cloudflare, Drex via Nace, Decider via meraGPT, self-hosted Laya, and compatible custom providers. Agents and plugins can classify content, filter candidates, score against criteria, or locate objects in images, then use structured results in their workflows.

Move a session to another folder, permanently delete it, or AI-rename it from the Web UI — by dragging a session row onto a folder title or from the session menu. Moving rewrites the session header cwd, relocates the persisted log and updates workspace accounting so history travels with it; deleting stops running agents and removes the log, projection-cache row and workspace accounting. The same three operations ship as agent tools: workbench_session_move, workbench_session_delete and workbench_session_rename_ai.

Project-less chats for dsh: a session created without a workspace gets its own directory under ~/Documents/DSH/<date>/chat-NN, reused whenever the chat is reopened and left in Ungrouped rather than made a sidebar project; the new-session hero gains a hover clear badge and a "work without a project" row, and a client-only sentinel workspace keeps that hero and its composer usable.

Runs /single-turn and /multi-turn answers in isolated sub-agents so results stay in the current chat and never enter the main model context.

macOS only: holds a PreventUserIdleSystemSleep assertion (caffeinate -i -w <host pid>) while any DSH session runs, and releases it when the last one stops, so a long turn is not cut off by idle sleep. The display may still turn off. It keeps holding through the maintenance phase, where Agent.status reports idle and a long manual /compact runs, via the compaction/start and compaction/end events. It reconciles against ctx.agents.list() every 60s, so a session already running when the plugin is hot-reloaded is picked up at once instead of at the next turn boundary. A failed hold retries with exponential backoff capped at 60s and never gives up; release escalates from SIGTERM to SIGKILL after 2s, and -w lets caffeinate exit by itself if the host dies. No browser half — configured through the profile patch. 51 tests, including two that read pmset -g assertions on real hardware.

Notes workspace in the right sidebar: a notes tree beside a live-preview Markdown editor with tabs, split panes, outline and trash, over plain .md files and a thin per-workspace index. Agents organize it through one `knowledge` tool; `embed` fences render an interactive HTML page in a sandboxed iframe (scripts run, no network).

基于 DeepSeek Harness 的 GitHub 插件静态安全审查预设，该项目代码由ai生成，主要框架由我搭建，通过“侦察员+审计员”双 Agent 协作、通过实验性ai自测攻防。主要功能有防死机上下文裁剪，有效防御投毒与提示词注入。包含21条安全红线、依赖树连坐排查与自动 YAML 校验，这是一名20岁非科班大学生的AI安全探索，欢迎大佬指导。本项目不能代替人工审计。请勿在生产环境或敏感凭证环境中使用。

Connects DSH to shared multi-agent rooms on roomcomm.xyz through a remote MCP server and a coordination skill.

Atomic OS interaction layer for DeepSeek Harness. A stable verb set replaces shell string concatenation — explicit argv, byte-exact encoding/BOM/EOL handling. Native Windows & POSIX implementations, zero runtime deps, MIT.

Runs Superpowers as an agent preset and gives each skill its own subagent model from a Settings table, so TDD, debugging and verification no longer all inherit the parent model.

Project-level AGENTS.md loader for DeepSeek Harness: injects .dsh/AGENTS.md (and custom paths) into the agent system prompt, with a settings page.

Global on/off switch for injecting workspace instruction files (AGENTS.md / CLAUDE.md) into the model context · 全局开关：是否把工作区指令文件注入模型上下文

为短上下文窗口的对话提供更轻量的 Agent 预设，能降低78%的固定开销。由 Deepseek 制作

DeepSeek Harness plugin: host-owned process & port lifecycle for local agents. start/stop/list/logs/wait-ready, tracked port reclaim, Processes rightbar + dock chip.

DeepSeek Harness plugin: host-owned long-horizon task board for local coding agents. Next≤3, in-flight, done+verify, inject file + STATUS.md + rightbar/dock chip.

DeepSeek Harness plugin: bounded-file memory for local agents. ME.md + project MEMORY.md vault, cache-stable inject, plain-line inbox, Memory rightbar. No embeddings, no LLM calls.

Retrospective agent-session evaluation — grades the sessions that already happened: deterministic grade cards, regression diffs, /eval-history trends, and /eval --report straight from exported artifacts; no benchmark runs, no LLM judges.

The child-scoped report tool for continuable in-process subagents on DeepSeek Harness: installs `report` plus its usage guidance into every continuable child scope, so findings reach the parent before the child finishes.

Session-aware mesh relay for DSH agents: an Ed25519-signed receive route and delivery policy, plus outbound sending, a peer directory and a mesh-peer-registry client.