Plugins

Auto-migrate Codex desktop-pet skins into DSH: an animated corner pet that mirrors agent state (thinking, tool use, awaiting approval, failed, done), with per-session frosted-glass dialogs and a full settings panel.

Pixel-art whale desktop companion with 29 frame-audited states — taps the glass and flashes the tab title when an approval waits, speaks a completion report when a turn ends, and adds a slash-command palette to the web client.

Solarized theme plugin: the classic low-contrast, eye-friendly dual palette system — Ethan Schoonover's Solarized plus Selenized (its refined take), dark and light each, built for long sessions with canonical syntax colors.

Laya typed decisions (`noul` yes/no, `choice`, `score`) as a first-class Cordis service (`ctx.laya`) plus the model-visible `laya_ask` and `laya_plan` tools. The plugin itself installs and downloads nothing: it is a client of a `laya-mcp serve` sidecar you start yourself, and it reports that the sidecar is not running instead of failing obscurely at the first tool call.

Slides out a Monaco editor plus a lazy-loaded file-tree panel in the DSH Web conversation, so you can edit the local workspace inline without switching to an external editor.

Publishes the DSH Web GUI to LAN or internet with dsh kept on loopback. Every source must sign in for an HMAC session cookie unless passwordless LAN is opted into. Adds self-signed or custom TLS, a secureCookies override for plaintext-HTTP proxies, and a UUID shim for plain-HTTP origins.

Adds an approval-mode toggle next to the permission selector: default approval keeps per-call confirmation, bypass approval auto-approves every tool call while staying in Workspace Write.

Manage conversation records from the DSH web GUI settings page: delete a whole session (archive plus physical log removal) or a single message (deleting a user message cascades to its assistant replies and tool results). Running and current sessions are protected.

CC-style auto-approval for DeepSeek Harness: deterministic deny/allow rules plus a two-stage allow/reject classifier with a circuit breaker and denial guidance.

OpenCodeGo quota monitor for the DSH Web GUI: a breathing indicator at the input's bottom-right (green/yellow/red by remaining share), a liquid-glass panel with rolling/weekly/monthly usage windows and reset times, auto-refreshing every 30 s; API key read from DSH credentials.

Office workspace & session dashboard: a floating 6-column sprite panel visualizing workspaces, sessions, token usage and subagents, plus Agent Mail and an office log tab. Feishu/Lark views (message feed, meeting schedules, transcripts) additionally require the `@larksuite/cli` tool installed and authenticated separately.

A 60-frame theme-aware monochrome whale-dive animation with reactive water for the DSH Web turn status: embedded assets, seamless closed-loop playback, a reduced-motion PNG fallback, and lifecycle-clean removal.

Local-first hands-free AI voice assistant plugin for DeepSeek Harness (DSH), with speech-to-text, text-to-speech, voice commands, and local speech engines.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config from the Reviewer 配置 tab in the conversation view ring above the composer (对话 / 轨迹 / 记忆系统 / Reviewer 配置), from a 127.0.0.1 HTTP server, or from an optional right-sidebar tab via dsh-better-sidebar.

Smart session titles for DSH: after each conversation turn an independent auxiliary LLM call summarizes the full user+assistant transcript into a title that follows the session's real topic instead of echoing the first message; the first message is titled instantly, failed built-in titles auto-retry on later turns, manual renames are never overwritten, and subagent/fork sessions are skipped.

Chinese writing de-AI plugin (AI-isms / AI writing / humanize): say "去掉AI味" to rewrite text, "写的不错" to auto-learn new AI words into the avoid list. Free from the Zhihu "去AI味写作技巧" community.

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.

Context Assembler plugin for DeepSeek Harness: topic-block context assembly, water-pressure topic splitting, tool trace/rewrite, reality recall injection and handoff planning.

Custom background image for the DSH Web UI: upload a picture or paste an image URL behind the whole app surface, with opacity, theme-aware scrim, panel transparency, frosted-glass and wallpaper blur, live preview and persisted settings, plus an optional DeepSeek-style timeline rail with per-question bookmarks for long conversations.

Adds per-Workspace category trees to the Web sidebar, with nested categories, drag-and-drop session assignment, category-scoped session creation, and category deletion that archives contained sessions.

Caddy forward_auth administrator login for DeepSeek Harness Web, with Argon2id passwords, revocable sessions, bilingual UI, and a native sidebar sign-out action.