Plugins

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.

The Engramory curated-memory discipline as an installable plugin ([npm: dsh-engramory](https://www.npmjs.com/package/dsh-engramory)): a deterministic 200-line / 25 KB cap on the `MEMORY.md` index via `ctx.tools.guard()` — growth denied, a shrinking rewrite always passes — plus the protocol registered as a runtime skill. The store is plain markdown, one file per fact, shared with Claude Code, Codex, Kiro, and OpenClaw.

Web search bridge for text-only agents: ask the web or X, get structured JSON evidence (search, fetch, citations).

Desktop pet for the DSH Web UI with 25 transparent animations, screen wandering, click reactions and drag, plus a reproducible asset-generation pipeline.

GitHub-topic-driven plugin & skill marketplace: a Settings page that browses the auto-collected registry (the whole dsh-plugin topic plus the skills index, CI-refreshed every 2 hours) with one-click install, type detection, install-script and host-shadow-dependency safety confirmations, env-key management, and the STANDARD.md recognition spec.

OpenPencil design preview and editing plugin.

Per-session and daily API cost, budget with usage %, official balance, history dashboard, and one-click official price sync with peak/off-peak pricing.

Skills and optional MCP rows for ten Russian marketplaces: price comparison across Wildberries, Detsky Mir and Yandex Market, plus per-source search, product cards and reviews. The 13 skills load on install; both MCP rows stay disabled until RU_MARKETPLACE_MCP_DIR points at a local clone, which needs Python 3.12+ and uv.

Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.

One-command skin plugin: 8 original themes, translucent wallpaper with opacity/blur, per-user accent, and shareable theme-pack import/export, favorites and surprise-me — purely native on DSH's token system.

Ecosystem infrastructure: a thin browser console for managing official repository plugins (zero patches) plus a make-dsh-plugin skill for guided plugin development.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model/tool policies; the main Agent dynamically plans each send as a bounded DAG with bounded reviewer/repair loops, while Run Center tracks retries and per-member tokens from official Harness usage events.

Unified notification & remote control for DSH: one `notify()` API, 25+ channels (Telegram / DingTalk / Feishu / WeCom / QQ bot / WxPusher / PushPlus / ServerChan / Bark / Discord / Slack / ntfy / webhook...), level routing (timeSensitive / active / passive) with tiered retry, multi-channel inbound approval (Telegram buttons, Feishu cards, QQ, WxPusher, WeChat iLink), official QR login for QQ/DingTalk/Feishu, a local web admin console, multi-agent routing, desktop notifications — and a mobile command center: `!status` / `!stop` / `!retry` agent control from your phone plus actionable notifications (view result / retry / logs buttons that call back into the agent). Secrets redacted, tool rate-limited, zero runtime deps — plus an open event source: other plugins can inject the notifier service (ctx.notifier) and subscribe to dsh-notifier/sent events, reusing notification without coupling — and an identity system (v0.7): pairing codes (/pair in any DM, first redeemer becomes owner), composite-key bindings, member roles, and a guided bootstrap state when the whitelist is empty.

给 HR / 猎头的 AI 招聘工作流：岗位标准梳理、Boss直聘 + 猎聘双通道寻源初筛、市场人才盘点、简历评估、约面试、候选人台账与日报。可装成 Claude Code 插件或 DeepSeek Harness (dsh) 插件——后者自带可直接上手操作的「招聘浏览器」面板；也能配合任意读 AGENTS.md 的 AI 编程助手使用。

DeepSeek Harness control center for official balance monitoring, per-session costs and tokens, third-party token totals, completion alerts, official recharge, flexible layouts, and agent-assisted session controls.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

Install safety net for DeepSeek Harness: pre-install snapshots, one-click/automatic rollback, guarded boot, and incident reports that auto-trigger agent analysis. 中文: DeepSeek Harness 插件安装安全网（安装前自动快照、一键/自动回退、守护启动、事故报告自动触发 Agent 分析）。

Codex-style skin switcher plus a custom wallpaper layer with opacity and blur controls.

PiUI-style diff viewer replacing the stock DiffBlock for write/edit tool calls.

Free, keyless web search for DSH: 7 engines (DuckDuckGo/Bing/SearXNG free + Exa/Perplexity/DeepSeek paid), auto-failover, settings-page UI with API key inputs and official links, web_fetch, and an engine test tool.

Recall any user message: rolls the conversation (official session fork) and workspace files (per-message shadow git snapshots) back to before it, with a diff-preview confirmation panel.