Plugins

Token usage and cost analytics for DeepSeek Harness, with daily token and cost charts, model and workspace rankings, a sortable table with CSV export, account balance and per-session cost.

Adds a sidebar entry that opens a full-screen 3D gallery of four procedural landmark models — the Eiffel Tower, the Great Wall, the Forbidden City and the Taj Mahal — plus a second entry with five quiet rooms.

Floating DeepSeek API time-of-day pricing window with Chinese legal-holiday awareness, account balance and estimated project spend; includes a green/orange 24-hour timeline and collapsible model, billing-rule and holiday sections.

Compact macOS strip above the composer showing CPU, GPU, RAM, swap, memory pressure and local Ollama model ON/OFF status. Tested on Harness 0.2.1-rc.5.

Rearranges the panel entries at the top of the DSH sidebar: drag to reorder or sort alphabetically, hide an entry without unloading its plugin, and split entries into named groups that render as titled separators; group headers collapse on click. A layout guard caps the entry list height and makes it scroll, so a growing list no longer squeezes the session and workspace panes out of view. An optional switch lets the profile's default model propose groups, and the host whitelists the returned ids and labels before they are stored locally.

Shows which provider the composer's currently selected model belongs to, and stays silent for providers another plugin already presents.

Hide the duplicate DeepSeek account / official API entries, sidebar items and the Feedback / Sign out items; on DSH Desktop, add Reload / Restart to the application menu with a one-click patch to the app shell main.js (needs an app restart, and a DSH update reverts the patch); pin a reasoning level and auto-fill new providers and models.

Video workbench for DeepSeek Harness that parses a link, downloads the source, transcribes it, trims or merges clips and exports GIFs. Requires ffmpeg/ffprobe and yt-dlp; whisper.cpp plus a model is optional for videos without subtitles.

Follow list above the sidebar conversation list: a status dot per conversation (unread, waiting for you, running, failed), newest reply first, running ones last, and a follow toggle beside the model selector.

Measures what your assembled system prompt is actually made of - rules, identity, workspace policy, tool descriptions - in bytes and percentages, then moves the operating protocol ahead of the rule block so the model reads who it works for before it reads the prohibitions. Config-driven via ~/.dsh/prompt-balance.json; two hooks, no build step, no dependencies.

DeepSeek Harness 的轻量 CAD 插件，用自然语言创建和修改简单零件 | A lightweight CAD plugin for DeepSeek Harness. Create and modify simple parts with natural language

Rewrites every prompt into a Mechanicus prayer before the model sees it, then lets you pick prayer or original to send.

Turn installed MCP servers on or off per conversation, from a picker in the session header.

Per-conversation tool kits for DeepSeek Harness: pick one kit and only its tools reach the model, with three bases (All, built-in only, or a saved kit), add-ons for one-off combinations, and a token ledger estimating what the kit saves.

A model-driven desktop pet, derived from PC2005-cloud/dsh-pet (MIT): an always-on-top companion that follows your agent sessions, races the Web UI to answer approvals and questions, keeps a per-pet affection ledger, speaks through pet_say/pet_do tools or an autonomous inner voice, and can read those lines aloud through BreezeBlue TTS with your own BreezeBlue API key. It uses its own /whale598 route and ~/.dsh/whale598 data directory, so it is a separate pet from dsh-pet rather than a replacement for it.

File-based environment registry for DSH: manage environments, services, deployments and operation-to-Skill bindings through a panel and model-facing tools.

Adds an UpdateNotify tool and a live progress panel docked above the composer in the DSH Web UI, so the model can narrate what it just did, found, or is waiting on while a turn runs.

Sends desktop notifications when a DSH turn finishes or fails, and sends 继续 automatically after the model-retry budget is exhausted.

Adds twelve chain_* tools that turn a multi-agent role chain into a round state machine with one frozen baseline, per-signature failure counts, role-tagged evidence, blocking approval gates and one audit file per round; also adds a settings card that routes each role to its own model and thinking effort. Requires the sibling l1-presets bundle (plan/work/code/review) - without those presets every chain_* tool returns ROLE_DENIED.

Sidebar node canvas for DSH where each node is an agent task and each link a dataflow dependency. One deterministic import (no model calls) produces both a task pipeline and a file-level module graph; file nodes carry a coupling score, and every run is snapshotted so it can be undone as a whole.

Scheduled Agent tasks for DSH 0.2.1-rc.5 with per-task models, workspaces, independent or persistent sessions, run history, and file artifacts.

Runs an approved OpenSpec change to completion while the model stays a mechanical forwarder: a bundled Python CLI computes the ticket DAG frontier, claims tasks atomically, prepares one git worktree per assignment, and returns exact actions. The session delegates each action with the DSH subagent tool and reconciles the completion notice against a hash-bound receipt produced by re-running verification commands on a clean, advanced HEAD, so free-text "done" never counts. Runtime scope changes are plain tasks.md edits. Requires Python 3.10+ on PATH and a git project that uses OpenSpec.

Adds an ARIS agent preset that loads the 84 ARIS research-workflow skills and runs their reviewer as an in-harness subagent from a different model family than the session model. Other presets are unchanged. A fork of wanshuiyin/Auto-claude-code-research-in-sleep's dsh-aris branch: install it instead of the upstream dsh-aris plugin, not alongside it - both register the mcp__codex__codex reviewer tools and the same ARIS skills.

Logic-risk review before rewriting: audit the source, decide each fix, generate several drafts in parallel, and export with a per-draft audit report. Bring your own OpenAI-compatible API endpoint and key - the plugin ships no model and returns 403 until one is configured.