Plugins

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Connects DeepSeek Harness to OOMOL-managed apps and services, with progressive Connector Action discovery and execution plus an in-app panel for managing Provider connections.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Route eligible shell commands through rtk to compress tool output and save tokens.

Git Bash shell tool for Windows: runs commands through the bash bundled with Git for Windows, with timeout, sandbox, output truncation, and background jobs, replacing the slow pwsh tool and the WSL-only bash tool.

Skin plugin for the DSH Web UI: 4 built-in skins plus custom image skins with the photo as a full-interface background and the palette following its dominant hue.

Bottom-right quota capsule that auto-discovers every configured provider (DeepSeek, OpenRouter, SiliconFlow, GLM, one-api/new-api, coding plans) and shows balance or rolling 5-hour and weekly usage, with per-provider visibility, alert thresholds and proxy support; also queries Volcengine Ark Agent Plan / Coding Plan usage via AK/SK-signed OpenAPI, and ChatGPT Plus/Pro subscription usage via in-plugin device-code login or the Codex CLI auth file.

A better fold bar: automatically folds tool calls and Think segments into step fold bars, and collapses each finished turn into a single turn header with live metrics (duration, TTFT, token, tok/s, cache hit) — only the final summary stays visible; customizable leading icons with animated poker cards built in (suit-cycling card animation while running, a deck when collapsed, a fan when expanded), a settings row for the official fold mode, compatible with both new and old DSH versions. Zero intrusion into DSH source.

Better streaming text animation for DeepSeek Harness.

Settings page for per-model capabilities: reasoning-effort levels with their wire spellings, input modalities, and token capacities, written as declarations or sparse catalog overrides.

Template for deepseek-harness plugin development.

DeepSeek Harness 独立社区插件商店：发现、安装并提交经过验证的插件、工具与扩展。 | Independent community plugin directory.

File explorer plugin for DeepSeek Harness: file tree, preview, markdown, syntax highlighting, in-panel editing, VS Code integration - DeepSeek Harness 全局文件资源管理器插件

Select browser elements directly during Vibe Coding and send structured visual feedback to the DeepSeek Harness Agent.

Plan review with anchored annotations and structured feedback back to the agent.

Skill pool manager in the Settings sidebar: enable/disable, folder batch import with rename-conflict prompts, state-driven one-click DSH-spec check & auto-fix, system/project scope labels.

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

Local-first four-bucket Token observability: persistent session/provider/model/day dashboards, trends, budget and anomaly signals, public-rate estimates, safe aggregate exports, and explicit opt-in usage or session-trajectory analysis.

Local-first learning mode: cross-session learning threads with per-source explanations.

Plugin coordination layer: plugins declare their capabilities, commands route to the owning plugin without a model call, tool schemas load on demand to cut prompt tokens, run history consolidates into long-term memory while idle, and failures are classified before any retry.

Zhihu search, agent tools, knowledge bases, and usage tracking for DeepSeek Harness.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Agent2Agent mesh.

Learning mode that explains each agent step (WIP).