Plugins

🌹 Port all 38 opencode themes into DeepSeek Harness, light and dark alike: quiet Tokyo Night, soft Catppuccin, easy on the eyes Zenburn. Plus 25 IP theme capsules: Genshin, Kuromi, Doraemon, Hello Kitty, Harry Potter, Cyberpunk 2077, Dragon Ball, Naruto, One Piece, Pokémon, Sailor Moon, Star Wars, Transformers, Ultraman, Zelda, Super Mario, Evangelion, LEGO, Marvel, DC, Disney, four of them in a second light/dark take, each with its own soul. And every theme is fully editable, so you can craft one that is entirely your own.

Fluid streaming rendering and smooth scrolling for the DeepSeek Harness Web UI.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

Word alternatives and underscore-gated fill-ins in the composer. End a line with _ and it is filled; misspellings are flagged as you type. Routes through the model dsh is already configured with, so it needs no API key.

The DSH plugin-development knowledge base as an on-demand agent skill: official constraints, task workflows, API reference and community gotchas, installed with the bundle so the agent can look things up while building a plugin.

IM webhook and local notifications on turn completion, errors, or approval (Feishu/WeCom/DingTalk/Slack/Discord/custom).

Shared multi-agent task board (create/claim/transition/query) over a Cordis service key.

In-app plugin store for the DSH Web UI: browse, search, one-click install, compat badges.

Export the append-only session log as human-readable Markdown or HTML, grouped by trajectory source.

Engineering-discipline guard: requirements grill before the first edit, red/green test-evidence gates, forked adversary review, and a delivery report with a per-dimension verification workflow.

Data quality checking for DeepSeek Harness — profiling, cleaning, and verification pipelines with structured reports.

Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.

Normify · DSH 插件：把项目架构写成归一化的分形模块树，三层校验（写时 / 校验 / 冻结回执）、30 个 normify_* 工具 + normify-gen 技能，一键渲染单文件交互式架构图；支持伴随式开发（change_open → brief → check → 实施 → refresh → change_close）。

DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill toggles, zero tools, zero-cache-miss.

All seven Kimi ask/review/challenge/rescue/pursue/swarm/swarm-write providers through the local Kimi Code CLI, with managed hooks, jobs, budgets, and artifacts; also supports Claude Code and Codex.

Rewind a DeepSeek Harness conversation and its workspace together, without touching Git: every rewind is a fork, /redo reverses it, and a Rust engine snapshots in milliseconds.

SkillRoute by JEStats: skill routing for DeepSeek Harness agents.

A fixed-corner DeepSeek balance whale widget for the DSH web GUI: three switchable skins (default / bowl-on-head / bowl-in-hand), balance with today usage, per-turn cost popups, peak/off-peak price conversion, press sound effects and random talk lines. Modified from MeteorNOX/DeepSeek-Balance-Whale-Widget.

LSP action surface for DSH: diagnostics, formatting, completion, code actions, symbols, signature help, inlay hints and rename, all backed by real language servers.

DeepSeek Harness (dsh) bundle wiring SkillRoute's skill router into your agents.

DeepSeek Harness (dsh) bundle wiring SkillRoute's skill router into your agents.

Cross-device session sync for DeepSeek Harness — syncs sessions and settings between machines through git.

OpenCues for DeepSeek Harness — LLM word alternatives and `_`-gated blank fill-ins in the dsh composer.