Plugins

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Read-only Claude Code compatibility bridge for DeepSeek Harness: Skills, Rules, command Hooks, and Agents from .claude as SSOT.

OpenSpec 流程的 Agent Team：面向实施阶段的多 Agent 工作流编排。

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log.

Multi-root workspace plugin for the dsh web GUI: attach several independent folders to one project workspace, manage them in a sidebar panel, and let agents read, list, write, and glob across every registered root through gated host-side tools. Hot-plugga

Completion sound + on-demand music playback for DSH agents (Host afplay/aplay/ffplay/mpg123, Web settings tab)

Git source-control sidebar for the DeepSeek Harness web UI: repo init, staging, commit/push/pull, branch & remote management, AI-generated Conventional Commits messages, and a commit-history graph.

Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.

Composable working, reasoning, and quality controls for DeepSeek Harness Web.

Project stack detection and capability recommendations for DeepSeek Harness.

A structured work-state protocol for DeepSeek Harness agent handoffs

Native DeepSeek Harness (dsh) plugin: hybrid local and XMemo cloud memory for Cordis-based agents.

Map dsh workspaces onto Discord — watch every session live, drive and steer agents, and reach the harness's own commands from anywhere, with no inbound port.

Evidence-backed, human-approved project memory for DeepSeek Harness

Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness

A desktop-style project and AI workbench for DeepSeek Harness

Pokemon-style catch-em-all: your real work is the tall grass — turns, tool calls and errors spawn wild encounters; throw balls, fill a 28-slot dex, walk a team of six. Zero tokens, invisible to the model.

Blocks agents from reading or writing sensitive files (.env, credentials, key material), masks leaked secret-shaped values in tool results, keeps an audit journal, and exposes safe sg_* inspection tools that never print raw values.

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

Keeps what the agent builds at runtime: turns a `cordis_define` dynamic package into a real installed plugin that survives restart, writing the bundle and registering the profile layer with no pnpm, no network, and no build authorization.

Metadata-first runtime profiler for DSH agents: turn/step traces, model and tool wall-time timelines, provider usage, retries, errors, and live or historical sessions.

GitHub REST API tools + browser sidebar panel: repos, search, issues, PRs, comments, account binding (credential-store), and one-click clone-as-workspace.

Minimal prompt x Web PTC capabilities: one-line persona, run_code SDK, subagents, Ralph, web search/fetch, and Windows Git Bash; the general-purpose workflow tool stays hidden.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.