Plugins

OpenCode Go in the DeepSeek Harness model list, providing subscription quota display, model discovery, session affinity, and more.

Picks a random installed skin on every DeepSeek Harness launch and enables exactly that skin, with an on/off switch and a shuffle action inside the Skins settings page. Skins the running host would refuse to load are excluded, and a manual switch still applies until the next launch.

Light/dark colour theme for the DSH web UI with an APTX capsule logo, browser tab title and icon branding, and optional Ai Haibara (Detective Conan) artwork panels, configured under Settings → General → Appearance with a no-decoration mode.

Turns an image folder into a frosted-glass global wallpaper for the DSH web UI, keeping the official palette.

Theme that pairs Windows XP-era scenery wallpapers with a modern frosted-glass interface: a fixed background layer behind the DeepSeek Harness web UI, panel styling applied through theme tokens, a wallpaper picker with custom image import, and a light/dark toggle. Works on desktop and mobile web surfaces.

Token usage panel for DeepSeek Harness: a bar above the composer opens billing token totals, trend charts, per-model and per-project breakdowns and a custom date range, read from local session logs of DSH, Codex, Claude Code, Trae and WorkBuddy. With a self-hosted portal URL and an app key it also reports usage events to that portal; with neither configured it collects nothing. It exposes token_usage tools plus a ctx.tokenReport service, and never collects conversation content.

Refines the built-in cache-hit percentage to three decimals in place across the composer stats row and the token-usage dialog.

Account-level DeepSeek platform usage inside the DSH settings page — 52-week token heatmap, per-API-key and per-model breakdown, live balance.

Live usage gauge injected into the system prompt every turn: session tokens and estimated spend, a next-turn estimate, and two predictions the model can act on — which step fills the context window and which step burns the budget. /qm panels, zero-config by default, optional price table, and it publishes a summary.json budget contract sibling plugins read.

Prompt optimizer for the composer: a button in the tool row rewrites your draft through a model channel you already configured, streaming into a panel that floats above the composer without taking up layout. Your draft changes only when you click Accept — and Accept is refused while the answer is still streaming, so a half-finished reply can never be written back. It asks first when the draft carries @ references or attachments, which a whole-draft replace would flatten into plain text. No global keyboard shortcuts, and no API key ever reaches the browser: the host half makes the call.

Turns file and directory paths in DSH chat into clickable buttons: click one to preview the file in the right sidebar, or open it with the system default application.

DeepSeek Harness plugin: show a provider + model icon in the sidebar for every session, updated live from the composer model selector with a last-request fallback for history sessions; aggregator routes render the provider logo with a 10px model logo in the corner.

One-button prompt optimizer: rewrites the composer draft via a configurable strategy, with an editable template, few-shot examples, pinned models and reasoning effort.

Displays account quotas, Git state, context usage, public API reference costs, Subagent activity, and streaming speed in DeepSeek Harness Web.

Full-screen boot animation for the DSH web client: the boot HTML paints a cover-fit artwork on its first frame, adds a slow settle, a scanning light sweep and a progress HUD, then hands the viewport over when the app mounts. Click or press Esc / space / Enter to skip.

Compact 56px app navigation rail with a separate conversation list and sidebar collapse control for the DSH web UI; also hides embedding, rerank and image/video generation models from the chat model menu and /model.

Switch providers and models, adjust reasoning effort; each model remembers its own level.

UI polish layer for the DSH web client: frosted-glass menu surfaces, a draggable reasoning-effort slider that replaces the level radio list, and model-menu navigation that reaches the model list in one click and closes on a single Esc.

Adds a refresh button to the conversation header in DeepSeek Harness, reloading the current page in one click without losing the conversation. Desktop-first, client-only, zero tokens.

Adds a Chinese-mode toggle beside the composer that opens a panel for switching reply, reasoning, and tool-narration language, persisted in the profile.

Right-side overlay panel for DSH sessions showing git status, background jobs, skills and MCP usage, artifacts and visited pages, with a commit/push dialog and one-click GitHub publish.

Deterministic goal-completion gate for DSH: a contract-first AC grammar with named failable check commands, a gate that re-runs every check itself (zero model trust), verdicts bound to a tree digest so file changes void passing verdicts, and a hard deny on false completion at update_goal via tools/pre-execute with a false-complete counter that blocks after two catches; scope-aware task-level claim handling (strict or goal-only) keeps multi-task Agent Teams loops from deadlocking.

Project-level memory built around a ledger whose structure the AI designs per project; the plugin only handles detection, injection, write-back, archiving and git. Memories are split by meaning: the active ledger holds current state, the turn journal is append-only, and decisions, the goal tree and lessons are one-card-per-file (with a multi-dimension index over the card folders); the fundamental principles file can be changed only by the user. There is a single compaction mode: before compacting, the AI sorts the work into three buckets - what must stay in context and is re-injected verbatim, what is written to the project's _stash/ for later lookup, and what is dropped. When a conversation is opened in a container workspace holding several projects, it can be locked to one sub-project (the lock lives in the plugin's own home and survives restarts; it leaves no marker in your project). Also an activity log with five levels, where L4 stores the user's own words verbatim (never injected, queryable on demand). Before each compaction a verbatim capsule (user quotes, raw errors, changed files) is written to disk, and both the capsule and its source material survive a restart; a handoff document lets a new conversation resume the previous one. 21 tools, 12 subcommands, 39 settings (one of them switches whether the settings panel or each project's manifest wins). Runs locally, no runtime dependencies.

Adversarial review for DeepSeek Harness: put one settled plan on the stand, send read-only red-team experts at it by dimension, then split their findings into single defects you endorse or reject one by one. It never rewrites the plan and never fixes code.