Plugins

Frontend aesthetics engine as 17 native tools — a 118-palette evidence library matched by register, cross-register whole-page design directions, four mechanical gates (WCAG contrast, color-blind simulation, AI-slop detection, scorecard) with digest-bound verdicts, plus semantic design tokens, existing-page audit, CVD-checked chart palettes, CJK type scale, render-vs-tokens reconciliation and measured-numbers rationale. Fully local, zero network. Requires Python 3.8+.

Read, edit, export and verify Excel VBA projects through a real Excel COM instance: modules, UserForm code, procedure lists and .frm/.frx exports. Windows only, with desktop Excel installed, Python 3.10+ with pywin32, and AccessVBOM=1.

Release gate for AI answer quality. Two channels: replay an existing VeriScope archive through the original Python quality gate, or run a threshold gate over a Ragas per-row export with Node only — no VeriScope, Python or pandas. Returns PASS, FAIL or REVIEW with source evidence and a re-checkable receipt; supports per-row thresholds and exact decimal comparison. It never re-evaluates and never calls a model, and REVIEW never becomes PASS.

Code retrieval engine exposed as an MCP server: four tools (code_search, code_outline, code_index, index_status) over a SQLite FTS5 index with BM25 ranking, CJK bigram indexing, declaration-aware tree-sitter chunking, incremental reindexing, and a three-layer secret filter. The bigram index matches Chinese-language queries against English code, and the default path needs no vector store or embedding model. Requires a local Python 3.10-3.12 engine installed by scripts/install.sh, and CODERAG_ROOT set in the profile patch.

Sweeps AI byproducts (scratch files, backups, logs, caches) into a reversible trash per project, and on project close classifies deliverables, archives reference results and writes a cleanup report. Requires Python 3 on PATH (the cleanup engine is a Python script; python3 / python / py are auto-detected, and without one cleanup cannot run and says so).

Replaces the built-in bash executor so every command gets an environment resolved from its own working directory: configurable PATH prepends, Python venv activation and mise shims, with a dedicated section in the Web UI settings.

Registers the project-cross-migration skill for DSH: five-layer agent project migration (conversations, memory, persona, tools, environment) with entry validation, JSONL integrity checks and readable restore. 1,418-message real migration verified across three platforms; pure Python stdlib, MIT.

odoo-lint for DeepSeek Harness: lint and fix Odoo addons, and lint every addon file the agent edits

Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start and repair autonomous test generation in a local Python backend, poll the task until review, and keep PR, skip and cleanup actions behind explicit user consent.

浏览器控制插件：把 browser-use / browser-harness 的 Browser Harness 注册为 DSH 会话工具，让 agent 直接写 Python 驱动真实 Chrome（导航/点击/输入/取无障碍树/截图），支持独立专用浏览器与附着系统浏览器两种模式；配置 TypeSafe key 后条件启用 browser_autopilot（Jev 目标式自动化）。

端到端内容智能采集与调研工作流：多源嗅探→四维评分门控→4级深度抓取→键控事实槽矛盾检测（GA11）→网络边界门控（GA12）→跨源融合→结构化 Markdown 报告。DeepSeek Harness (dsh) skill bundle.

Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start and repair autonomous test generation in a local Python backend, poll the task until review, and keep PR, skip and cleanup actions behind explicit user consent.

Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run ser

Decides whether Python code is original or a derivative work: reports the longest identical expression span against an upstream tree, an exemption rationale per finding, and a risk list. Pure stdlib `ast` analysis — offline, no model calls.

`dsh-workflow-designer` 是面向 DeepSeek Harness 的提示词优先工作流设计插件。它收集当前 Agent 可见的本地 Skill、原生 Tool 与 MCP Tool，提供必要的可视化编排和约束编辑能力，并导出稳定的 YAML 中间表示。后续可由大模型及对应框架把 YAML 生成 Python、`workflow.mjs` 或其他代码工作流。

DeepSeek Harness 插件：语音 + 通知出口——agent 通过云端 TTS（火山 seed-tts / 小米 MiMo V2.5，失败自动回退 SAPI）/ 桌面通知 / 提示音主动联系用户。融合 dsh-plugin-notify 的 DSH 原生深度集成与 agent-voice-mcp-minus 的云端 TTS 调优，零 Python 依赖，Windows 原生。

Bridges the agent to a persistent OKF memory vault over MCP stdio: a Python server (SQLite FTS5 + Markdown) with 10 tools for searching and storing decisions, facts, learnings, conventions, profiles and sources.

Legacy code modernization workflow (preflight -> assess -> map -> transform) with a Cordis mount plugin, offline Python scripts and smoke tests.

Linux X11 computer use for DeepSeek Harness: 9 tools (screenshot, move/click/drag/scroll mouse, type, key combos) driven by a zero-dependency Python XTest helper — native-pixel coordinates, per-action verification, optional auto-observation screenshot.

OI 出题工作台：知识点锁定、数据构造、本地评测，打包 Hydro/HOJ 原生题目包，发布/管理 Hydro 与 HOJ OJ，提供 Python 外部管理 UI 与系统斜杠命令。Opt-in skill-first plugin for DeepSeek Harness.

A stateful, Agent-controllable Jupyter workspace for DeepSeek Harness: a persistent ipykernel runtime the DSH agent can read, edit, execute, and inspect, with VS Code-aligned cell UI and .ipynb save/load.

Native dsh (DeepSeek Harness) Cordis plugin adapter for vision-translation: grounds images into <vision-context> via the Python CLI (PROTOCOL v1). Spawns cli.py, never re-implements core logic.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

DSH project scaffold preset: strict 5-phase init runbook, engineering standards and six runnable starter templates (node-ts / react-vite / python / go / spring-boot / monorepo).