Plugins

Ambient UI for DeepSeek Harness Web: a glassmorphism balance/token floating widget plus a pixel-art agent-trail animation.

A DeepSeek Harness Web GUI appearance kit: 32 preset themes, custom backgrounds (wallpaper / glass / texture), per-zone text depth, and a keyboard desktop pet.

Custom background (images / GIFs / animated wallpapers) plugin for the DeepSeek Harness (DSH) Web GUI: an enable switch plus a local asset library, with separate display mechanisms for the official theme and skin-center skins.

Fail-closed LLM-assisted approval reviewer for DeepSeek Harness

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Test-stability tools: repeatedly run vitest/jest/pytest/node:test suites, classify flaky cases, keep history, maintain a quarantine manifest and health self-check.

Contract regression harness for plugin authors: a scripted LLM adapter drives the real pipeline in isolated child processes with session-event assertions (load/contract/behavior/fault layers); zero API key, CI-ready.

`describe_image` tool: a vision bridge that sends images to mimo-v2.5 through the opencode Zen API (credential `OPENCODE_GO_API_KEY`, free route first with paid fallback) and returns text descriptions for text-only models, with native passthrough and ImageMagick transcoding of SVG/TIFF/HEIC formats.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Ecommerce operator workbench: CSV batch preview with marketplace column adapters, reproducible profit/six-dimension scoring, public product-page snapshots, Chinese skills, and a replaceable store-policy KB.

Mojibake guard bundle for DSH: feature-based garbled-text detection before writes with review-then-release (an identical retry passes), plus pre-execution pwsh encoding audit (ANSI/GBK/UTF-16/Default), Windows and Chinese first.

Stage-gate governance tools: model-callable gate_open / gate_check / gate_list / gate_close for in-memory, per-session acceptance checks with PASS/BLOCK conclusions.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

Create/modify/inject test assistant messages and import/repair session.jsonl(.zstd) session logs into new sessions.

Floating API-balance badge for DeepSeek Harness: live balance for DeepSeek, Moonshot, OpenAI and custom endpoints; draggable, resizable, frosted-glass look, with text color adapting to the content beneath.

Pin assistant replies from the Web action strip and recall them into the next model turn (`/pin` `/recall`, with optional wake).

The authority layer for agentic AI, as a DeepSeek Harness plugin. Governs every tool call against your business rules via the TapPass /v1/govern policy decision point.

Independent read-only acceptance layer: spawns a read-only verifier before each top-level turn closes and steers non-pass gaps back into the agent.

macOS only: holds a PreventUserIdleSystemSleep assertion (caffeinate -i -w <host pid>) while any DSH session runs, and releases it when the last one stops, so a long turn is not cut off by idle sleep. The display may still turn off. It keeps holding through the maintenance phase, where Agent.status reports idle and a long manual /compact runs, via the compaction/start and compaction/end events. It reconciles against ctx.agents.list() every 60s, so a session already running when the plugin is hot-reloaded is picked up at once instead of at the next turn boundary. A failed hold retries with exponential backoff capped at 60s and never gives up; release escalates from SIGTERM to SIGKILL after 2s, and -w lets caffeinate exit by itself if the host dies. No browser half — configured through the profile patch. 51 tests, including two that read pmset -g assertions on real hardware.

Generate images from the agent on the user's own GPU by queueing a workflow on a local ComfyUI install over its HTTP API: Z-Image-Turbo for fast drafts and Qwen-Image-2.1 for final assets and legible in-image text. Registers comfyui_generate and comfyui_status plus a skill covering model selection and prompt craft, has no runtime dependencies, and starts ComfyUI headless when no server is listening.

Read, write, convert and retime a subtitle track across SRT, WebVTT and ASS, audit it for over-long or unreadable cues, and transcribe audio through a configured speech recogniser.

Read, audit and diff Protocol Buffer definitions without installing protoc: a zero-dependency .proto parser exposing six tools (status, outline, describe, diff, audit, next_number). diff classifies every change as breaking, risky or additive and names the wire-format consequence; audit catches what protoc accepts but a reviewer should not — duplicated or illegal field numbers, reserved-range collisions, unresolved types, and unreserved gaps below the high-water mark.

Turn a raw recording into a published podcast with a local ffmpeg — detect chapter boundaries from silence, cut at those boundaries, normalise loudness to a broadcast target in two passes, and write an iTunes-compatible RSS feed whose enclosure byte lengths are measured from disk.