Plugins

Local-first knowledge base for DeepSeek Harness: imports Word/PPT/Excel/PDF (text or scanned), EPUB and MOBI/AZW3, builds Markdown parts with page anchors, OCR quality/confidence and column-aware PDF reading order; adds an LLM-maintained wiki layer (schema.md rules, auto index.md, append-only log.md, typed notes with sources and backlinks), adds source-trust labels (high/medium/low) with trust-aware ranking and low-trust warnings, and supports ranked search, cross-KB query, precise reading/editing, and md/jsonl/zip export. MOBI/AZW3 need Calibre; legacy .doc/.ppt need Word/PowerPoint (Windows) or LibreOffice (Linux); scanned-PDF OCR downloads models on first use.

Adds an Insight tab next to the conversation and trajectory tabs in DSH: calls a model to interpret tool calls turn by turn, and supports a custom prompt.

Opens .blend files in the right-Sidebar document preview: Blender headless exports a cached GLB with scene statistics, rendered by a dependency-free WebGL viewport. Requires Blender 3.6+ on PATH (or set blenderPath).

Hermetic composition lock: fingerprints the profile's dependencies, bundle order, lockfile and patch layer; booting a drifted composition warns, or fails under strict mode (the --frozen posture for CI).

Verified-progress ledger: three tools record a claimed step as progress only after an independent subagent with a fresh context confirms it against the workspace. The declared scope is fingerprinted before and after each verification, so a verifier that changed anything has its verdict voided and the round cannot become progress.

Provides 15 Superpowers skills for DeepSeek Harness, covering test-driven development, debugging, planning, and code review.

Session-scoped research evidence ledger with sources, linked claims, open questions, and explicit user review; provides a tool, slash command, and conversation panel, with selected-claim Markdown export that omits excerpts, review notes, and local paths by default; does not fetch sources or verify their truth.

Mounts the hosted Reaudit MCP server (https://mcp.reaudit.io/mcp) through the in-box @deepseek-ai/dsh-mcp-client bridge with a REAUDIT_API_KEY bearer token: 238 mcp__reaudit__* tools for brand visibility in AI answers (ChatGPT, Perplexity, Gemini, Google AI Overviews), competitor and citation analysis, site audits, content generation and social scheduling.

Liuyao divination in one click — ask a question, cast the six-line hexagram, and let AI interpret it for you; every cast is saved locally.

Full-duplex voice mode for DeepSeek Harness 0.2 desktop: streaming ASR to draft, sentence read-aloud, barge-in, live captions, plus an in-app settings page. An unofficial compatibility fork of dsh-voice-mode 0.7.15.

Ports the obra/superpowers methodology as 14 native DSH skills — brainstorming, writing-plans, executing-plans, subagent-driven development, test-driven development, systematic debugging, parallel agent dispatch, git worktrees, code review, verification before completion and skill authoring — served through the DSH skills registry with their scripts, references and cross-links intact (frontmatter folded into a manifest, prefixes realigned to DSH skill names). Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): the /superpowers slash command declares the producer-owned source kind plugin:dsh-plugin-superpowers.

Runs Superpowers as an agent preset and gives each skill its own subagent model from a Settings table, so TDD, debugging and verification no longer all inherit the parent model.

Drag-and-drop document reading for DeepSeek Harness: land PDF / Word / PowerPoint files in the workspace and give the agent outline, search and read tools so it can answer questions from them.

Cross-session full-text search over persisted DSH session logs: builds an incremental message-level index and returns sessionId, seq, and a short excerpt; exposes an agent tool and a standalone panel. Requires Node.js 23.5+.

DeepSeek Harness (dsh) plugin: live local LLM endpoint health in the web rightbar. llama.cpp slots (busy/TTFT/wedged, /metrics) + Ollama MODELS (loaded vs empty). Engine fingerprinted by response shape. Installable dsh.bundle.

DSH 插件工坊：一条命令装齐 7 个插件——MCP 服务器管理器、技能管理器、跨会话记忆、钩子排序、会话清理、代码知识图谱、Superpowers 方法论。

Obsidian daily notes, tasks and Day Planner time blocks in the DSH sidebar: a Monday-first month grid with per-day word-count and task dots, a compact timeline for HH:mm time blocks, the selected day's diary excerpt and task list, and write-back of checkbox state, task text and times to the Markdown files; a first-run wizard detects the vault or accepts a path.

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

Preventive content policy for DeepSeek Harness tool results: rewrite matched text with regex rules, or drop/truncate unpredictable payloads by field path before they are normalised, rendered, or persisted. The upstream counterpart to dsh-plugin-redact.

DeepSeek Harness plugin for CVE impact retesting: fingerprint a target, judge it against a CVE's affected range, gather passive evidence, and report a verdict with confidence and limitations.

Hard break on repeated tool calls: a synchronous ctx.tools.guard gate that counts semantic fingerprints (net/site/sink/cmd/exact) over a per-agent sliding window, ignoring decoy arguments such as description and timeoutMs.

Bundles the 14 obra/superpowers skills for dsh from a recorded upstream tag (v6.3.0), re-syncable with drift reporting; the skills trigger automatically.

A DeepSeek Harness bundle of 14 obra/superpowers engineering skills with a native agent preset, automatic session bootstrap, and Windows sandbox compatibility.

DeepSeek Harness Agent 团队的信任指数插件 —— 为 spawn 出的 teammate 做实时信任评分：四维 EWMA 信任账本（按 agent 类型指纹跨会话累积）DeepSeek Harness Agent teams plugin — live trust scoring for spawned teammates: a four-dimension EWMA ledger keyed by agent-type fingerprint (cross-session)