Plugins

Cut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)

Cross-session long-term memory: captures durable facts from each turn, auto-associates them by shared entity and tag, and recalls with BM25 plus spreading activation over the link graph.

Project-isolated long-term memory for DeepSeek Harness that keeps one bank per project and adds a cross-project view; it can also seed a project's memory from its git history without opening a session there.

Realtime model usage panel: tokens, cost, requests, trend and composition, with editable pricing.

DSH plugin that pushes agent progress and human-attention events to a Feishu (Lark) custom-bot webhook

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

DeepSeek Harness agent tool (session_search) for full-text search across historical sessions backed by core SQLite FTS5 engine without memory overhead.

DeepSeek Harness (dsh) host adapter for anysearch: thin Cordis bundle — hooks layer only, all business logic stays in the anysearch server over 127.0.0.1 HTTP IPC

dsh plugin: unattended approval gate — subagent/scheduled/cron approval requests get a bounded answer window, then settle with a fail-closed default instead of hanging forever (per origin or per session)

Automatic bounded test runs with persistent recent results.

cc-switch-style global prompt for DeepSeek Harness (dsh 0.1.5): one user-editable block injected into the system prompt of every conversation, mirrored into each session project's AGENTS.md, and naming the harness's user-global AGENTS.md by absolute path

DSH 插件：Mermaid 流程图 → GB/T 1526-1989（等同 ISO 5807）国标流程图 SVG，符号合规、正交走线、超 A4/A3 自动分页。DeepSeek Harness plugin: Mermaid flowcharts to GB/T 1526-1989 (ISO 5807) compliant flowchart SVG with A4/A3 pagination.

dsh 插件 · 使用量仪表盘：离线扫描会话日志，统计每日/每周/每月 token、估算费用、模型/工具/技能/命令榜、输出速度、工作时段与质量指标；gridstack+ECharts 卡片可拖拽编排，支持自定义公式与 AI 编排（提示词往返导入）。

Git worktree isolation for DeepSeek Harness: create a worktree, register it as its own project, and start the session inside it

MCP server management for DeepSeek Harness: author composition rows, choose when an allowed server loads, and filter which of its tools a session may call

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.

Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.

Worktree Space: puts a workspace task that spans one or more Git repositories in its own task space directory - each repository in it gets its own worktree on one shared task branch; the space is registered as a DSH Workspace so sessions start right there, and multiple tasks run side by side without interfering. Finishing a task can merge the work back into each repository's target branch, remove the worktrees, and file whatever Git does not track in an archive directory you choose.

Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the op

Free OpenCode Zen models in DeepSeek Harness through native HTTP requests. No OpenCode installation, login, API key, server, container, or LiteLLM is required.

A theme gallery for DeepSeek Harness (DSH): JSON-defined skins with full-screen coverage and sidebar scenery, a 15-swatch palette-picker card, a pet-widget card (7 registry-driven pets playing by the chat input), a mood-greeting card (a scrolling greeting

Unified @ mentions in the DeepSeek Harness web composer: five built-in categories (file, folder, skill, past chat, plugin) plus a data-source seam any plugin can register through, references to absolute paths outside the workspace, and a candidate menu that can be scoped by a folder named earlier in the draft and pages with PageUp/PageDown instead of hiding rows.

Local TXT reader in a right-sidebar tab plus a spoiler-safe AI reading companion: the model only sees what you have already read — the current chapter, the tail of the previous chapter, and a per-book background file it grows as you go. Excerpts, thoughts and the companion replies become structured Markdown notes exportable to Obsidian; raw text unlocks only for a book you mark as finished.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.