Plugins

Ultra-lean daily coding agent preset for DeepSeek Harness (dsh) that strips heavy orchestration for fast, direct tool execution.

Schedule a message into a dsh chat for later: a Schedule button in the message box with a date and time picker, a sidebar panel of pending messages across chats, delivery as a normal user message even with the browser closed, and schedule_message, list_scheduled_messages and cancel_scheduled_message tools so the model can come back to a chat on its own.

A native reasoning-effort control for the composer: a blue-to-violet tier bar with a starfield and a sheen sweep. It owns the model seat and drives the official model-directories service, so the ladder comes from each model's own reasoning declaration and no other plugin is required.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

WeChat Official Account channel for DSH — WeChat messages run agent turns and the answers are pushed back through the customer-service message API, with signature-checked callbacks and an openid allowlist.

Model-visible SSH file tools read_remote, write_remote and edit_remote: read a remote UTF-8 file with line-numbered paging, create a new remote file (an existing target is refused, there is no overwrite branch), and apply literal replacements with unique-match checking — all addressed through a single "alias:path" field whose alias comes from ~/.ssh/config.

Customer-machine access plugin for deepseek-harness-gateway: opens a single outbound WebSocket to the gateway and relays the machine local dsh web UI over that tunnel using pairing-code + HMAC auth, so no inbound port, port mapping, or public IP is needed.

Plays a short synthesized ding in the browser tab the moment an agent finishes a turn, built entirely with the Web Audio API; no backend audio and no OS notification.

One-click launcher for DeepSeek Harness: detects whether the backend is running, starts dsh web if needed, waits until ready, then opens the main page in a new Chrome window. Ships a cross-platform CLI (dsh-launcher start / open / status / make-shortcut) and the harness_launch agent tool.

Sidebar session-title icons: an auxiliary model call on the same route as title generation draws a 24x24 monochrome SVG metaphor shown before each session row title, with disk caching.

macOS desk pet forked from anneheartrecord/dsh-desk-pet, in a real always-on-top window that covers fullscreen Spaces: the pose follows whatever the local DSH is doing across six states, the right-click menu is a real AppKit one carrying quiet mode and a session list, and seven skins ship with it. Two of the seven are drawn from geometry by a script in the repo rather than generated, so making a skin needs no image model and no API credits; the bundled skill still expands one photo into all eighteen poses on your own image tool and credentials. There is no Electron and nothing to install alongside it: the window is driven through ctypes on the Python that ships with macOS.

Approval sound effects from the movie NiuLai: plays 「妈妈」 when user confirmation is requested, interrupts it and plays 「牛来！」 the moment the user approves; native Windows playback, zero external dependencies.

Keeps a local task-outcome ledger for DSH, verifies acceptance criteria from deterministic evidence, records user disposition and token usage, and supports digest-bound export.

Self-learning loop for dsh: record lessons, draft and promote skills, periodic curator review that corrects, consolidates, and retires skills.

Life-story skill: capture moments and fragments, build a user profile and generate novels, scripts or autobiographies.

Token usage and cost metering for dsh: per-session and aggregate statistics with configurable pricing and reports.

Security and governance for dsh: rule-based tool denial, full tool-call audit trail, and governance reports.

Native A2A (Agent-to-Agent) server for dsh: expose this dsh as a callable agent over HTTP with JSON-RPC tasks.

Econometrics research assistant: 6 tools covering method selection, data preparation, model specification, empirical analysis with Python/R/Stata code templates, robustness checks, and result reporting.

Animated and video live wallpaper for the DeepSeek Harness Web GUI — GIF, animated WebP/APNG and static PNG/JPEG images, plus MP4/WebM video backgrounds, with auto format detection, a dim slider, and UI chrome tone matching.

Registers the remove-pdf-background-gray skill for DSH: whitens gray/off-white scan backgrounds in image-based PDFs while preserving resolution, page geometry, and anti-aliased text edges (lossless Flate write-back), via a single Python script (pypdf + Pillow + numpy).

Conversation outline for DeepSeek Harness: the Markdown headings of the whole session, grouped by turn, in a side panel or a full-width curtain; hover previews can be pinned for comparison, bookmarks keep the places you come back to, and a right-click jumps to a section or copies a heading and the levels below it. Six theme colours and a translucent material, title/prompt/full-text/cross-session search, reading-position follow and a Chinese/English interface.

Capability transform & assembly engine (Qian Xuesen cybernetics/systems framework): static resident layer manages the skill/MCP/plugin registries, auto-absorbs skills and tool metrics, and drives a negative-feedback evolution loop (scan Sick/Weak → mutate → select promote/reject → 30s rollback); includes a Web UI panel and a GitHub dsh-plugin store bridge.