Plugins

Port of pstack to DeepSeek Harness: 58 agent-workflow skills plus a deterministic router that picks each subagent model from the models you checked for subagents.

Add your own parameters to the model requests dsh sends: OpenRouter provider routing and fallback models, reasoning, sampling and custom body fields, and headers, for OpenRouter or any other gateway. Parameters are organized by the channels dsh already has; a live preview shows what each request will carry, and a request log shows what was sent and what the gateway answered.

Connects 36 model sources (free and pay-as-you-go APIs, Codex and Kimi subscriptions, local Ollama and LM Studio) to dsh and gives other tools one authenticated OpenAI-compatible address and key. The free pool model free/auto combines free API quotas such as ModelScope, Zhipu Flash, Gemini and Cloudflare Workers AI, moves to the next provider when one is used up, and by default only uses quotas that do not charge. Models appear in dsh grouped by source; Cherry Studio, Cline and scripts can use the same address (HTTPS is set up automatically next to dsh-vps). Daily check-in for 10 services (Trae, Qoder, WorkBuddy, Doubao, MiniMax Code, WPS Lingxi, DuMate, AStudio, Huawei CodeArts, OfficeAce) with several accounts each, pasted credentials for checking in on a server, and custom check-in services described as JSON. Installed from the plugin market it sets itself up, and the engine ships as an npm package, so no GitHub access is needed.

Two-way Telegram remote cockpit for DeepSeek Harness: live progress tracking, screenshot vision, git diffs, shell execution, and tool approvals. Unconfigured chatId automatically claims the first sender as owner; voice-to-text requires local ffmpeg and BeeRouter services.

On-demand skill tools for DeepSeek Harness: registers skill_search / skill_load / skill_ref so the model searches a staged skill library first and loads a skill body only when it needs it, keeping the library out of the resident session catalog and out of every turn's context; adds a Skills tab to the conversation view ring that reads back the whole session and lists which skills were actually loaded, and in which turn. Zero dependencies, and the records render client-side only, never entering the model's context.

Discovers OpenRouter's free models, measures their real speed and context size, and writes them into the DeepSeek Harness model list fastest-first, with speed and context in each display name, plus a Settings section to configure and run it.

RTK (Rust Token Killer) extension for dsh-router: rewrites each bash tool call through `rtk rewrite` so the agent reads compressed command output, and falls back to the original command when rtk is missing or has no equivalent.

Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.

Adds subagent_route and subagent_fork_route delegation tools where the model itself picks the provider/model route for each child; the deployment only sets the spawn/fork backend, background policy and allowedProviders allowlist, while continuable children and background jobs reuse the official send_message / job_output tools.

Read-only GitHub access for agents, wrapping several tools. Inside the tool it automatically probes and selects whichever GitHub access method works locally, and tries network proxies on its own. That cuts down the network and parsing problems an agent may hit when accessing GitHub, and the overhead of it repeatedly trying different approaches.

DeepSeek Harness 多模型路由插件：让专业的事情交给专业的 agent——自定义视觉/翻译/语音/子代理等专业 agent 并绑定独立模型，多模态账号一键登录、账号池健康路由与实时用量统计

Multi-provider account balance display for the DeepSeek Harness Web GUI. Queries real billing APIs (DeepSeek, StepFun, Kimi Coding, OpenRouter, MiniMax, xAI) and shows balance/quota in front of the model selector. Providers without an API-level billing en

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

Registers FreeLLMAPI as a dsh model provider, with the router itself bundled in the plugin. It launches the vendored server with the host binary and exposes the freellmapi route; the sidebar panel starts and stops that process, lists the router catalogue, probes which claimed models actually answer, and ranks them by the stability, speed and intelligence scores the router computes for itself. Provider keys, routing strategy and usage remain in the router console, which the panel links to.

Sidebar leaderboard for DeepSeek Harness (DSH): LMArena blind-test ratings, Artificial Analysis intelligence index, LiveBench 2.0 capability, OpenRouter weekly/monthly usage and market share, price, speed and context — plus a local token-usage dashboard built from your own session logs (tokens, estimated cost, per-model ranking), model detail drawers and CSV export. Daily snapshot, instant open, no API key; locally configured models are highlighted.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

Run one deterministic skill-routing pass on every user instruction, so the skill catalog is consulted before the model answers instead of after it remembers. On the host it scores the live catalog from the instruction's keywords and the catalog metadata, with no LLM or embedding call, and appends a single producer-tagged message to the step: a ranked shortlist by default, the winning SKILL.md body once the score clears a threshold, or an instruction to call a named router skill exactly once. Unrelated instructions stay silent.

Shows what each completed turn cost in CNY on its own row under the turn, with a click-to-open breakdown naming the tokens per category, the unit rate, the matched price rule and the billing instant; per-model rates are edited on a settings page inside DSH — four token categories plus weekly recurring peak/valley rules with arbitrary multipliers and absolute time-window promo prices that override them. 0.2.3 adds account awareness: it reads the balance or remaining quota of 14 providers (DeepSeek, OpenRouter, Zhipu GLM, Moonshot, MiniMax, Kimi Coding, OpenAI-compatible relays and more) and shows today / this month / this session spend next to it; spend is accumulated in a local ledger (atomic writes, one book per API key, 1-24 month retention, JSON export), and a monthly calendar lets any day be corrected by hand - including days with no balance observation - with an optional note. Usage and rates are computed locally from what the provider reported; balance is read straight from the provider API with your own key, and nothing is sent to a third party.

Grounded web search for DeepSeek Harness through OpenRouter-compatible gateways: the built-in web_search tool runs on the same endpoint and key as your chat models, returns citeable sources, and is configurable from the Plugins settings page.

The built-in web_search bills a full model turn against DeepSeek's own endpoint; this runs it on an OpenRouter-compatible gateway instead, so search is billed where your chat already is, at the model and price you pick.

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the prompt.