Plugins

Configurable statistics row below the composer via a ${variable} display template — which segments appear and how they are labelled is fully user-defined.

Browse the skill library from a floating-ball panel: you choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin), skills are grouped into first and second level categories, descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and keeps a .bak-toggle backup, and disabled cards grey out until restored. A failure ledger separates automatic from manual entries and records skill successes and failures by listening to tools/result events, reusing an existing ledger file if one is found in the library and otherwise creating one under skill-master/references. The DSH settings page gains a floating-ball section that shows or hides the three balls and offers one-click restore of a ball dragged off-screen.

In-session "Files" tab (conversation.view, order 20) for dsh Web that browses the active session's workspace directory with breadcrumbs and previews files inline — sanitized Markdown (marked + DOMPurify), images, line-numbered text and PDF — served by read-only /dsh-files host routes registered on ctx.webServer; no write endpoints. Bilingual zh/en.

Adds lightweight selected-text references to DSH assistant replies: selections stay outside the editor as removable draft contexts, remain marked beside the source, and render as hoverable annotations after submission.

Adds a sidebar tab that folds a session into user turns (input, tool steps, output) with one-click jump back into the conversation.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Slash commands ported from other coding agents (setup, connect, install, trust, browse, doctor, status, model, memory, compact, resume, review, mcp, init, suggest, improve, refactor), a zero-dependency static scanner for plugin source, and an in-repo catalog of audited plugin report cards that cite file-and-line evidence.

Cost panel for DeepSeek Harness: meters every request from session events, prices it against a built-in catalog of 136 models across 16 providers, and shows the current model, account balance, session, today and month spend plus a monthly budget bar next to the composer. Bilingual zh/en.

Use DSH from your phone anywhere: a self-hosted relay plus a desktop host plugin form a token-authenticated tunnel (order-preserving HTTP reverse proxy + WebSocket bridging) with QR pairing, an admin console for device/token management, and an injected mobile adaptation layer (full-width chat, full-screen settings sheet, sidebar drawer).

Hard-stops further tool calls after a configurable per-session budget is reached.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Turns DSH conversations into reviewable community feedback and, after confirmation, submits it to the official DeepSeek Harness Discussions.

Uses a GitHub App to report open PRs and the latest Actions run for the current repo without returning secrets.

Reports the current WSL distro and warns about multi-distro setups.

Opens http(s) URLs from WSL in the Windows default browser.

DSH tools for operating a self-hosted Talebook library: search, download, upload and manage books and audiobooks, manage Legado book sources, and admin operations, with approval-gated writes.

Decision log for DeepSeek Harness: record key decisions (chosen option + why) into a versionable DECISIONS.md via decision_log / decision_list / decision_audit tools, and auto-inject the summary into future sessions so decisions stay traceable and are never re-litigated.

Ask a sidebar assistant about selected assistant text: an ephemeral right-side panel answers from a snapshot of the main conversation's LLM history with streaming Markdown, collapsible thinking and multi-turn follow-ups, without touching the main conversation.

Turns completed DeepSeek Harness public-content work into a browser-local visual magazine with explicit updates and reviewed one-article sharing.

dsh侧边HUD面板，包含多个信息展示模块（可自定义是否展示），集成压缩上下文、查看git graph等功能。DSH side HUD panel, containing multiple information display modules (customizable whether to display), integrating features such as compressed context, viewing git graph, etc.

Branching surveys in the web GUI: the ask_survey tool with per-option routing, hover insights, Mermaid diagrams, quick one-click answer templates, and resumable banked progress.

Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).

Scan a QR code in Settings to open the DeepSeek Harness web UI on your phone inside the active session via a cloudflared quick tunnel.

Cadence SKILL (Virtuoso Lisp) assistant for EDA engineers: official-doc-anchored API lookup (3557 entries across 5 IC6.1.8 manuals, signature confidence levels, never invents APIs) plus zero-execution static analysis driven by a lexical depth coordinate system — iterator-safe deletion with position-sensitive copy() protection, printf placeholder/argument reconciliation, in-loop nth O(N^2) detection, deprecated APIs with page refs, dangerous-intent interception and CIW error-log triage. Host half has zero third-party dependencies.