Plugins

A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.

Drop-in enhanced fork of the official todo_write tool: priority tags on each task, full checklist rendering in the conversation, and a draggable in-session floating task panel with position memory, double-click reset and a live indicator of the action currently being executed.

Floating panel for the DSH web UI managing MCP servers and skills: per-server deferred tool loading (ToolSearch, off by default) keeps a server's tools out of every turn's context — the prompt lists tool names only, and a tool's full schema enters the list once the model finds it with the built-in tool_search, so a turn stops paying for schemas it never calls. MCP servers live in a global scope or a project's own .dsh/mcp.json, with per-server enable/disable, a 47-service market and import from ten other clients; skills are auto-discovered across their real scopes with shadowing, and model auto-invocation versus manual-only is a switch per skill.

Zero-dependency toolkit: time / encoding / json / calculator / csv / regex / markdown / diff / stat / schema — ten deterministic tools in one install.

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.

Zero-dependency tool suite (calculator/csv/diff/encoding/json/markdown/regex/time).

Connect Google Antigravity OAuth accounts to DeepSeek Harness with smart multi-account quota rotation, multi-model LLM routing, and Nano Banana 2 image generation.

Auto-expands newly arrived tool-call cards in the DSH Web UI, with a sidebar toggle cycling no-op/expand/collapse and the state persisted to localStorage.

Load only basic DeepSeek Harness tools by default and activate other tools on demand.

Hermes-style tool search & slimming: progressive disclosure, semantic search, describe, and call long-tail tools on demand while core tools stay eager.

Loads only the basic DSH tools by default and activates the rest on demand, with a per-tool switch list in the plugin settings.

Per-round reasoning_effort optimizer for dsh — auto-downgrades reasoning for simple tool calls and lifts back for heavy work, cutting thinking time between tool calls.

A web-novel writing engine for DeepSeek Harness: parallel drafting, outlining and brainstorming with a separate DeepSeek key, lore and foreshadowing management, semantic vector retrieval, a corpus library, usage ledger, mechanical proofreading, and a local serialization plan.

A self-healing layer for tool calls: missing params, wrong fields and out-of-range paths are fixed before they reach the model. Measured visible error rate fell from 7.95% to 2.20%.

Switchable backends behind the native web_search and web_fetch, chosen per session from a composer menu or /setup-search and /setup-fetch: DeepSeek, Exa, Firecrawl, Tavily, Tinyfish, OpenAlex, Semantic Scholar and server-side model search for search; local HTTP with a private-network allowlist, the DeepSeek Fetch API, Exa, Firecrawl, Tavily and Tinyfish for fetch.

Cordis /hongtou command: two-phase pipeline (LLM structured JSON + deterministic Word 2003 XML template rendering)

Safe math expression evaluator, zero-dependency recursive-descent parser.

Send local images or HTTP(S) image URLs to a configured OpenAI-compatible vision endpoint with the inspect_image tool and return its text response to the conversation.

Manage tool availability and groups for each Agent Preset, load tools on demand like Skills, and reduce model context usage.

web_search provider for DeepSeek Harness with switchable search backends; installed through dsh-tool-web-enhanced-profile

Tavily search with multiple API keys, key rotation and failover, a usage gauge, and a settings card.

Codex-style tool call folding, collapsing multiple tool calls into a single line.

Chrome and Edge browser control that drives the real logged-in profile, tabs and cookies through an MV3 extension and a loopback Bridge, exposing browser_* tools, a Skill and /chrome commands.

Provides the see_image tool for DSH: send an image file to a configurable OpenAI-compatible vision model and relay its description back to a text-only model.