Plugins

Project Development Mode preset plus an in-chat development board for DeepSeek Harness: the lead conversation clarifies requirements and delegates to an Agent Team, and the floating board tracks each user change request through dispatch, execution, testing and acceptance with 7 board tools.

A fork of Microsoft's official .NET/C# skills for AI coding agents, additionally packaged as a DeepSeek Harness plugin — covering development, testing, diagnostics, migration, and AI integration.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Reference search for DeepSeek Harness: refkit_search looks up image, video, audio and text references across 24 open sources and tags each result with its normalized license and a use verdict for the intended use; refkit_rights re-checks one license against another use. Source keys and search tuning live on a settings page. 11 of the 24 sources need API keys; the use verdict is returned only when an intended use is passed. Runs on DSH ^0.1.7-rc.2 || ^0.2.1-rc.2 (tested on 0.1.7-rc.2 and 0.2.1-rc.2).

A philosopher's way of thinking made executable: dialectics and practice-testing to govern hallucination and long-session drift, so done is a verifiable fact rather than a claim.

Treats the session as a mainland-China user (zh-Hans-CN, Asia/Shanghai, ISO dates, CNY currency) and generates a self-consistent test persona: five tools, six cross-checks, GB 11643 check digit, phone prefix matched to carrier ASN.

Connects the OpenCode Zen anonymous free lane to DeepSeek Harness: refresh the model list from upstream, tick which models the opencode provider exposes, test any of them with a real request that ends in one of seven verdicts, and order both the settings card and the model selector by a hand-written S/A/B/C capability rating.

Draggable floating card that follows background jobs: a progress bar and percentage parsed from wget/curl/apt/pip output, elapsed time, ETA when present, and the latest output line.

Novel generator: builds a world snapshot along a story timeline and, from the latest snapshot and the most recent chapters, deduces the next chapter. Requires DSH >=0.2.1-rc.2.

Windows floating status lamp outside the DSH window: a borderless always-on-top glowing orb on a fully transparent background — green with a breathing halo while tasks run, orange shaking for approval, blue floating for your input, dim grey idle, dark grey host offline; hovering lists each session's latest task, drag to move, and the lamp self-extinguishes within seconds when the plugin is switched off.

Live preview inside the sidebar session hover card: what the session is doing right now (running tool with elapsed time, thinking, last tool duration), an attachment thumbnail with click-to-enlarge, the latest user prompt and assistant reply with injected system scaffolding stripped out, a recent-tool icon strip, turn count plus token totals plus model name on one line, and a 12-item settings page (11 switches plus a slider) persisted to the profile.

Three-player LAN Dou Dizhu (斗地主) played from a floating window: one machine opens a room on its own port, the other two join with a six-character room code plus an address. Empty seats can be filled by computer players in four switchable strengths (easy, medium, hard, hell), so one or two people can still play a whole hand; the deal starts as soon as the three seats are filled. 54 cards in four suits, bidding of 1/2/3 or pass, the landlord takes the three bottom cards and holds 20, play runs clockwise, and the first-bid seat rotates clockwise between hands. The rule engine is pure and covers 11 legal shapes, with big joker > small joker > 2 > A > K down to 3, suits never compared, straights, pair-straights and planes excluding the 2s and the jokers, and a rocket that beats everything. The table itself is built to be read at a glance: three seat cards side by side in play order (you, then your next and previous seats) with role, hand count and a bar that runs out, one line that says whose hand is on the table and what would beat it, the bottom cards as text, an in-place play history that folds into a single summary line and unfolds into every trick including the passes, plus hint and auto-play buttons that pick the cheapest legal answer out of the local rule enumeration. Nicknames can be changed mid-hand (twelve characters, duplicates get a suffix). Computers run inside the authority and are handed only their own hand, the public record and the seat counts, so no hand can leak; the authority is the only place that decides which card ids leave it. Computers are driven by the room itself, so a one-person table keeps playing with nobody else on the LAN port. Humans have no turn timer, the collapsed floating pill can be dragged around the screen, and 179 unit tests pin the rules, the wire format, the theme tokens, the drag gesture, the history grouping and the computer seats.

Tool-surface snapshot and drift gate: baselines the full visible tool registry (name/description/parameters, MCP tools included) into a committable JSON file and warns loudly when an upgrade adds, removes or reshapes a tool.

Signed chain-of-custody for sessions: every watched tool result appends a hash-chained, ed25519-signed record, with commits bound into the chain — tampering with any line or truncating the tail fails deterministic replay verification.

Daily brief for DeepSeek Harness. Every day at a fixed hour it ranks the plugin market by real install counts and stars, cross-checks it against your own agent memory and working conventions, and proposes two kinds of item: concrete deltas on the plugins people actually use (original does A, the proposal does B) and directions nobody has built yet. The popularity numbers come from the catalog the market itself publishes and are quoted into the prompt rather than guessed; an entry the market has not measured is shown as unmeasured, never as zero. Approving an item opens a new session named after it and hands that session a fixed delivery contract — implement independently, never fork, test green before publishing. Rejected sources are remembered so they stop coming back.

Provides 15 Superpowers skills for DeepSeek Harness, covering test-driven development, debugging, planning, and code review.

Adds an Omni-modal settings section to DeepSeek Harness that points the harness at any OpenAI-compatible image and video endpoint: switchable config profiles with separate endpoint, API key, model, path and size for each side, free-form extra request parameters, a connectivity test that does not spend generation quota, and three model-visible tools — generate_image, generate_video and check_video — with async video tasks that survive restarts.

Folder time machine for DeepSeek Harness: snapshot any folder, browse its timeline, roll back with one click — Git-like history without needing Git, for folders that never had a repo (game saves, app config dirs, loose documents). Snapshots are content-addressed and deduplicated, and unchanged files are not re-hashed. Automatic snapshots come in two modes: realtime (fs.watch — one version ~8s after the last change, so a save-all or a build counts once) and timed (checks every N minutes, stores only when something actually changed; identical content never adds an empty version). Empty folders are recorded and recreated on restore. Every restore takes a safety snapshot first, so a rollback is itself undoable, and exact-mode cleanup only removes files and empty folders — a non-empty folder is never deleted. Ships a folder_timemachine model tool (status/history/diff need no approval; writes ask first) plus a floating panel with the timeline, one-click restore and mode switching. Pure JS, zero runtime dependencies, 110 tests included.

A delivery receipt panel for a project hand-off. One trigger collects the branch and commit, the test and build results, screenshot dimensions with sha256, and the secret-scan verdict, then assigns every line to one of three zones by evidence alone — verified, local-only, or unverified. A claim in the unverified zone keeps its label and prints an explicitly empty slot instead of the claim itself, because a confidently worded sentence with nothing behind it is the exact thing the receipt exists to catch. Test failures and secret-scan hits are still evidence, so they land in the verified zone with a red tone rather than being quietly dropped.

Cross-session long-term memory: a hybrid-retrieval memory store (BM25 plus CJK bigrams), chunked long-document search, chat-log extraction and distillation, and context-summary archiving and browsing, with important memories and the latest summaries auto-injected into the prompt.

Registers OpenCode Zen free models as a native provider: the catalog is discovered live from opencode.ai intersected with models.dev pricing, and a detail page can re-fetch it or test which models answer. Declares no dependencies, so the host's pi-ai stays the only one.

质疑与投诉期限核对（按公开的政府采购质疑投诉规定核对期限与台账自洽，仅提示差异，不作出定性结论）

Knowledge-point notebook for DeepSeek Harness: turns a Markdown notes folder into a card canvas — folder = chapter, file = section, body = knowledge points — with masked-answer questions for self-testing, KaTeX formulas, Mermaid flowcharts, a mind map view and in-panel editing.

Adds a "Check updates" tab to the Built-in plugins settings: one row per installed bundle, with its latest npm version and an update button. Each row also reports DSH-runtime compatibility. The registry is read through the .npmrc chain (environment, then profile, then user, first hit wins); with nothing configured it races a mirror against the public registry, and a private registry is never raced against a public one. A version is installed from the registry it was read from.