Plugins

Per-session cost & usage report cards: tokens, cache hits, duration.

Persistent provider-reported token usage totals with per-session, per-model, and daily activity statistics.

Token usage and cost tracking with daily/session budget alerts and a usage_report tool.

Git-aware write guard plugin for DeepSeek Harness: blocks whole-file writes that would overwrite the user's uncommitted changes, and reports what happened to protected files at turn end

Single-cell RNA-seq workbench usable from the Harness UI or from agent tools: imports h5ad, 10x, loom, Seurat RDS and archive files, runs QC, filtering, normalisation, highly variable genes, PCA, neighbour graph, clustering, UMAP/t-SNE, marker genes and cell-type annotation, offers resolution scans and saved marker panels, and exports h5ad, result tables and reports.

Query MES production progress, work orders, reports, and existing bills of materials with read-only Zhixing Ark authorization.

Find existing GEO projects and reports and review sample coverage, competitors, and citations with read-only Zhixing Ark authorization.

One sidebar panel that shows the remaining credit balance and today's check-in state of every freebie platform already configured on the machine (Loomy, MiniMax Code, Trae, Qoder, Raccoon, WorkBuddy, CodeArts, WPS Lingxi, MobileClaw), read through the plugins that own each platform plus two bundled read-only readers. Query and manual check-in only: no login UI, no stored tokens, and a manual check-in is reported as successful only when the measured balance actually increased.

Stable local-first workspace health audit for DeepSeek Harness: Git, tests, CI, size, security hotspots, baselines, and bilingual handover reports.

Right-sidebar novel studio that treats a chapter as a pipeline with checkable artefacts instead of one long prompt: scaffold a project, inspect the exact context pack a chapter gets, generate 2-6 parallel candidates and keep the one you pick, then run chapters in sequence with per-chapter progress on disk so it survives an engine restart. Length band, cross-chapter Jaccard and drift ratio are enforced in code rather than by model self-grading; rejections come back as repair evidence for up to two rewrites. AI-fingerprint metrics are reported against a 3956-chapter human baseline but never block, because the distributions overlap. Ships 7 agent tools. The writing engine is a separate Python package that the plugin installs on first use. Needs Python 3.10+ on PATH (or a path set in the plugin settings).

Sidebar panel for Kaipu: shows which reviewer seats a workspace has, which scenes they serve, and the history of past sessions. Installs on its own (no package dependency); it reads seat data from the Kaipu gateway, so with no Kaipu endpoint configured it honestly reports "channel not ready". Removable: uninstall it and nothing else is affected.

Download task panel for the DSH Web UI: a bundled download_file tool streams the file itself and reports exact byte counts, shell downloads (curl -o, Invoke-WebRequest -OutFile, pip install, git clone) are recognised from host job events, and every task shows its name, real percentage, transfer rate and remaining ETA in the bottom-right corner.

Reverse-engineer an image style into a reproducible prompt: measures palette, brightness, contrast, saturation, colour temperature, sharpness, grain and aspect with pure algorithms, fills only the semantic slots you confirm (subject, action, mood, camera, style), and reports which slots are still missing. Shipped with a negative prompt derived from the measured deviations.

Runs N serial speedtest rounds in one unchanged environment from the plugin detail page, then reports per-round tables with median, min, max and MAD, and keeps each batch as an archive that can be renamed or deleted.

Grok-bot-style AI organization in the sidebar: a chief-of-staff agent creates departments, roles and per-department group chats, dispatches each task to child agents running on this machine, and reports finished work back as one assistant message. Its HTTP routes have no DSH access check, and they can create agents and dispatch tasks to them.

Douyin for DSH: bounded autonomous watching with storyboard frames and danmaku sampling, persona and interest memory, a daily watch report, plus direct-message auto-reply and one daily greeting for a whitelisted set of friends. This is a maintained fork of dafeiyu1314520/dsh-douyin-agent 1.4.7 that fixes follow-list read timeouts, unclickable conversations, missed replies, and greetings that stopped scheduling after a single send. Windows only (a dedicated Edge window, Node.js 22.13+). Replies and greetings are sent as ordinary messages with no “automated reply” label, and once you have enabled them they restart by themselves each time DSH launches until you stop them by hand. It registers the same bundle id as dafeiyu1314520/dsh-douyin-agent and LockyBee/dsh-douyin-agent, so it replaces them rather than running next to them.

macOS only. Shows a live badge in DSH and an optional SwiftBar menu-bar item reporting what the Yunshu (Eagleyun SASE) endpoint agent is doing on this Mac right now — TCC permission requests, its own agent logs (screen capture, clipboard, browser URL reads, browser window counts), DLP scan paths and the process table. Read-only: it never blocks, disables or modifies the agent, keeps the last 60 events in memory only, writes three state files locally and makes no network calls. Requires the Yunshu agent to be installed; SwiftBar is optional.

Track source lineage for web excerpts and structured Agent reports, fold repeated text with recorded provenance, and export auditable evidence through DSH tools.

Turns the QQ groups you follow into a Chinese daily digest. Pulls chat history through a local NapCat/OneBot 11 service into SQLite, summarizes each group, and renders an HTML/Markdown report with an opportunity radar that surfaces repeated complaints, tool requests and unmet needs as product ideas; can push a card to Feishu on a schedule.

Shows a Kobe iced-tea side popup and reports per-turn costs or token counts with bundled offline audio. Uses dsh-cost-meter first, or estimates each request from native usage and public prices. Includes twenty cost phrases, four token phrases, CNY/USD, three-decimal rounding and custom previews; no runtime TTS service or API key. The bundled voice clips are pre-synthesized offline and the portrait is a fan-made image; the package declares UNLICENSED. When it has to estimate a cost itself it fetches a public price table from raw.githubusercontent.com (Han-1413141/dsh-cost-meter) and the USD/CNY rate from open.er-api.com, at most once a day, and sends no session data.

Codex quota card at the sidebar foot, styled like the Command Code panel, plus a quota dashboard: a ring, one row per quota window with reset time and remaining percentage, and a dashboard with credits, spend-limit and reset-credit tiles. Reads the ChatGPT quota that dsh-codex-subscription reports over its bridge.

Deep research for DeepSeek Harness: multi-query search, source fetching, evidence extraction and a cited evidence report, through the host ctx.web service. · DSH 深度研究插件：多查询检索、正文取证、交叉印证，产出可引用的证据报告。

Read-only diagnostics for a DSH install — boot-crash logs and the cause named in them, config drift against a recorded fingerprint, backup freshness, workspace growth, plugin updates, host-version compatibility, duplicate client ids, and model availability — plus an action layer that always shows a plan first and needs a single-use fingerprint and explicit confirmation before anything is written. A checkup also runs 45 seconds after every host start; when the 3-hour probe cache is stale it sends a one-line test prompt to the default model and a few models of each configured provider (model.probeOnReport can switch this off). Registers the agent tools dsh_steward_report and dsh_steward_act (clean caches via dsh-disk-cleaner, backup via dsh-config-manager, disable or enable a bundle, set the default model; execute takes the plan's hash plus confirm: true) and a system-prompt section telling the agent to run the report first when something crashed.

Team presets for AgentTeams: ships audit6 / impl5 / lite2 rosters with seed task DAGs and a per-role report contract, plus a captain doctrine section, so a fresh session opens the right team in one approval instead of a pasted prompt. Needs the engine @nanmicoder/dsh-agent-teams added to the same profile first; the team patch targets that engine's entry by id and replaces its whole agent-teams config.