Plugins

DeepSeek Harness universal preset enhancement plugin: an editable preset editor (system/user/assistant entries + camouflage model output prepopulation)

VSCode-style editing experience for DeepSeek Harness: a Monaco-based central file editor (tabs, Ctrl+P quick open, status bar) and interactive diff review of agent edit/write results with per-change Keep/Undo, rollback and archiving, persisted across restarts.

Use a ChatGPT/Codex subscription in DeepSeek Harness with GPT models, image generation, web search, subscription quota reporting, model and feature controls, and browser or device-code OAuth sign-in.

Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-over model pool (multi-account rotation, live credits, and a model catalog showing per-model credit multipliers and free/night-discount tags).

Project file explorer in the details column (multi-select, drag-move, upload, download, rename, trash, system-open) with an in-session read-only preview tab for Markdown/HTML/JSON/CSV/notebook/PDF + code highlighting, a live model throughput badge, and a multiline GoalBar.

Port of DietrichGebert/ponytail v4.9.0: always-on lazy senior mode with a 7-rung ladder (YAGNI to minimal code), 6 skills for review, audit, debt, gain and help, with no empty tools.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

Runtime-switchable model output styles with Claude Code outputStyles parity, plus the output.render.* presentation protocol: a /style command, per-session persistence, systemPrompt injection, six built-in styles, a web picker, and a renderer registry with per-session/per-tool rules and /export.

Detailed model usage and cost analysis, with per-session usage stats and usage queries for GLM, MiniMax, OpenCode Go, DeepSeek and more.

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog management for long-session stability.

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.

AI image and video studio as a floating DSH panel, so creation runs alongside the conversation instead of replacing it: text-to-image, image-to-image and multi-image composition at 1K-4K across eight aspect ratios; text-to-video and image-to-video with first-frame control at 4-12 seconds; short-drama mode that imports a script (.txt/.md/.json), breaks it into storyboard shots for preview and batch generation; and a prompt-expert workspace. Zero runtime dependencies.

Free model provider plugin for DSH with 20+ models including Gemini, MiMo, GLM, etc.

DSH bundle 插件：V4 Flash 神模式（opencode-go）agent preset 分发包，dsh plugin add 安装后自动同步 router-flash preset。DSH agent preset bundle for DeepSeek V4 Flash godmode.

A lightweight, selectable smart-routing mode for DeepSeek Harness.

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog management for long-session stability.

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.

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.

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.

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.