Plugins

Web interface enhancements for DeepSeek Harness with session rename/fork shortcuts, a searchable model picker with provider filters, mobile layouts, global font scaling, context usage alerts, DeepSeek balance and tariff rates, sent-message navigation, and conversation summaries.

Huawei HarmonyOS assistant-today (负一屏) task-completion push for DeepSeek Harness: hiboard_push / hiboard_verify tools post Markdown task results to the phone card feed, wire-compatible with the OpenClaw today-task skill, with the authCode managed from the dsh settings panel.

Push vague or rich, user-configurable DSH interaction states to the local Discord client as Rich Presence — real-time, content-free, with a user-editable status list and an optional rich-mode toggle in Settings.

Reusable subagent definitions managed from a Settings page and dispatched through a single delegate_agent tool; ships with a built-in read-only Explorer preset and a nested-delegation policy toggle.

Durable DAG workflows for DeepSeek Harness with Agent authoring tools, SQLite persistence, resumable runs, and a visual Canvas Studio.

A document preview / edit / management plugin for DeepSeek Harness. It provides a VSCode-style "Document Center" workbench inside the DSH Web GUI: a file tree on the left, click-to-preview, editable code & Markdown with Ctrl/Cmd+S save; and exposes three document tools (doc_read / doc_edit / doc_create) to agents, letting models read and write workspace documents through natural language.

Pokémon-style skin for DSH Web with GBA frames, HP-bar status, effort level panel, and customizable color palettes.

Full-screen lightbox for chat images: click any image to open the full-resolution original with zoom (wheel, buttons, shortcuts), drag panning, prev/next paging, filename caption and download, plus keyboard-arrow and touch-swipe navigation. One "image display control" popover next to the composer collapses every image in the conversation into a thumbnail grid whose column count (1-12) is configurable and remembered, or hides them entirely so the space closes up and restores them later; images are styled in place and no node is ever moved or reparented. The host-side display_image tool takes a local path or directory (TIFF/HEIC transcoded, originals still saved on download), a remote URL, or a keyword search over Bing, Huaban and Sogou that samples loadability before picking a source, re-saves images blocked by hotlink protection and drops dead links after a magic-byte check, returning paste-ready Markdown. It also keeps a system-prompt rule that every delivered image must appear in the reply body as  markdown, because collapsed tool rows are invisible to the reader.

Layered long-term memory MCP server: raw turns → task fragments → daily summaries → topic indexes, local MiniLM 384-dim embeddings or OpenAI-compatible API backend, semantic + Jaccard-fallback search, one-command DSH plugin install.

Fourth permission preset for dsh: unconfined, GPU-capable sessions (danger-full-access) with per-operation user approval for writes outside the workspace or to protected paths (.git/**, .env*); implemented purely as a bundle over the official tools/pre-execute ask hook, no core edits.

Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.

Turns session context into a deep-sea moyu (slack-off) game in a floating window — your hand sinks as context grows, touch a fish and server-rolled dice decide the mint of a holographic collectible card across five oceans, with a fish pond and a GitHub-linked leaderboard.

One-click health check for DeepSeek Harness: 0-100 score, plain-language issue list, and safe reversible fixes via the profile's cordis.patch.yml.

IDE-style run configurations for DSH: save LLM prompts and shell commands as reusable run configs (global or per-workspace), run them from the session header or the new-session page, and manage them via the task_run_config tool with approval-gated writes.

WeChat Reading (WeRead) multi-target export for DeepSeek Harness via the official Skills API gateway: browse your bookshelf, export highlights & thoughts to flomo, a local Markdown file, or Notion, optionally reworked by a configurable LLM prompt.

Source-aware prompt injection guard for DSH: tracks untrusted turn context, detects injection signals, scores sensitive sinks, and blocks high-risk tool calls with explainable audit logs.

Sends a desktop notification and chime when a DeepSeek Harness run completes, errors, or waits for approval, with a configurable duration threshold.

Agent-managed procedural memory: a skill_manage tool that creates, patches, disables and deletes the agent's own skills in user or project scope, with delete guards (agent-created marker, pin, path confinement) and a trigger-discipline prompt.

Safe, audited SQLite/PostgreSQL/MySQL access for dsh agents: schema introspection, enforced read-only queries, a write approval gate, and a durable JSONL SQL audit trail.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

See how you have been using AI: `/session-insights` reviews your DSH sessions over time, shows what worked, which problems kept coming back, and what results were actually produced, then creates a retrospective report on your machine.

Adds OpenAI Codex (ChatGPT) as a selectable DSH provider via the local Codex App Server.

Import, install and invoke Agent Skills in DeepSeek Harness from Codex, Claude Code, OpenCode, GitHub or npm — composer-side ⚡ picker inserts /skill-name into the draft, and a Skill 管理 settings page offers per-source/per-skill import, expandable source paths with skill counts, uninstall and one-click restore from .trash.

Conversation query map for dsh web: a left rail with one bar per sent question, hover wave + preview, click-to-jump with older-page backfill, and tunable bar length/spacing.