Plugins

ARIS research-workflow skills as a DeepSeek Harness bundle: 82 skills plus cross-model adversarial review through Codex.

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.

Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.

Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

A fixed-corner whale widget for the DSH web GUI — balance, today's usage and per-turn cost with peak/off-peak pricing, editable balance-alert and daily-budget bubbles, a module-based custom bubble queue with A/B weighted choices and random lines or images, 30+ vendor templates (OpenAI, OpenRouter, Kimi, SiliconFlow, Ark, Zhipu, MiniMax and more) with per-model balance and subscription quota, plus task-end sound, imported audio, custom roles and a resource manager. Local-only, no telemetry.

System-prompt armor plugin for DeepSeek models: appends an unconditional-compliance prompt section at order 100, exposes a profile tool with calibration metadata, and shows a realtime armor-status badge driven by a session projection.

DeepSeek Harness tool plugin that exposes BrowserSkill (bsk) browser automation to the model

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.

TongFlow studio plugin for DeepSeek Harness (dsh): film-crew style project model, agent-authored TongFlow workflows, deterministic media generation, embedded canvas.

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Connects dsh to a local SandBase Harness runtime over stdio MCP for managing agents and sessions, streaming turns, inspecting artifacts and cancelling work.

Authorized-security DSH collection: nine work modes (redteam coordinator, pentest, code audit, binary analysis, attack-defense, AV evasion, incident response, cloud security, CTF solving) and fifteen runtime plugins, managed from a settings page with one-click deploy, install, update and uninstall.

Interactive UI components rendered inline in replies: layout, charts, forms, quizzes, mermaid, 3D scenes, and an action event loop back to the model.

Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.

Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.

In-conversation generative UI: the model renders interactive HTML cards into the chat stream, with streaming preview and sandboxed rendering.

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

Adaptive reasoning slider skin that maps each model's available reasoning efforts onto a 0–30 visual intensity scale, with synchronized portraits, background, and interface colors.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model/tool policies; the main Agent dynamically plans each send as a bounded DAG with bounded reviewer/repair loops, while Run Center tracks retries and per-member tokens from official Harness usage events.

Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.

Reports which skills each turn invoked (loaded by the model, typed as /name, or none) and manages the local skill directory: install from a pasted repository, folder, SKILL.md or zip address, set a Chinese display name in the skill meta.yaml, and remove a skill while keeping a backup.

Let the model connect to databases and write SQL.

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file, readable in any editor. The `MEMORY.md` index has a hard 200-line / 25 KB cap enforced by `ctx.tools.guard()`: a write that would grow an over-cap index is denied, while a rewrite that shrinks it always passes, so an oversized index can be compacted step by step. The plugin never writes memories on its own — what is kept is decided by you and the model. The same store is also used by Claude Code, Codex, Kiro and OpenClaw.