Plugins

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.

Complete wuyun-liuqi (five-evolutions-six-qi / 五运六气) Traditional Chinese Medicine skill pack as a DeepSeek Harness Cordis plugin: annual and guest-qi calculation, clinical pattern differentiation, and pathogenesis reasoning.

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

Cost tracking priced from an online catalogue (models.dev + OpenRouter, 8000+ models, each call priced at its own instant): a per-turn cost line, a Cost tab attributing spend to tool output / model output / system prompt / commands, budget, monthly forecast, ~166 live-rate currencies, and a bill_stats agent tool.

A DeepSeek Harness plugin for real-time token tracking and highly accurate session cost estimation, featuring dynamic peak/off-peak pricing support.

Short-video sidebar: native player, series navigation, precise history replay.

SHOPLINE AI Toolkit: bridges the official SHOPLINE Developer MCP server and ships seven SHOPLINE agent skills (Admin REST, GraphQL, OAuth, webhooks, Sline) — the SHOPLINE counterpart of the Shopify AI Toolkit.

Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool that returns probability-distributed answers to typed questions (choice/score/boolean) in one call.

Wallpaper skin for the DSH Web UI: image background with opacity, mask and blur controls.

TypeSafe Jev as a first-class Cordis service and three model-visible tools for DeepSeek Harness — offline by default, egress disclosed, never default-on.

Tripo 3D generation skills driving the tripo-cli through the shell: text-to-3D, image-to-3D, rigging with locomotion clips, decimation and LOD chains, and export to GLB/FBX/OBJ/STL/USDZ/3MF, with headless device login for both China-mainland and international accounts; installable as `tripo-dsh`.

Remote development over SSH: pick a directory on a registered machine as the session workspace and the file, shell, bash, and search tools run on the remote host — the agent works there with the same local tools, and no extra model-facing tools are added.

DSH Desktop enhancement plugin: it puts verifiable facts on the table. Constraints are injected only when relevant, so idle chat costs no extra tokens; injection is layered (session-stable text in the system prompt, volatile content as a tail snapshot) and the prompt cache stays valid. Discipline: each turn is classified (question / research / discussion / diagnosis / execution) with boundaries enforced - no file edits on question turns, no unsolicited fixes on diagnosis turns; citing code lines not opened this session, negative claims about unseen symbols, requirements that do not match the deliverable, and dressing up “I did not check” as “waiting for your decision” are all called out; replies are written for humans - a code, field name or id must be explained in plain words the first time it appears. Memory and knowledge: 75%/90% context warnings plus an exported session recap (say "continue" in a new session); project knowledge accumulated across sessions by working directory, auto-captured and deletable by id. Inspectable artifacts: task contract / change record (auto-logged, unverified items flagged at delivery) / hypothesis record (conclusions must pass an evidence gate) / design decisions. Dashboard and personas: routing, trigger hits and block assembly are written to lume-metrics.jsonl and queryable via lume_metrics; personas are distilled from chat logs, novels, scripts or character sheets, with long-term and temporary memory, a memory star map and persona card export/import.

Token-efficient persona runtime for DeepSeek Harness with local catgirl rendering and progressive tool-schema disclosure.

Live token stats under the DSH Web composer: streamed tokens/s, output token and first-byte latency, plus per-step estimate-vs-actual reconciliation using the official BPE tokenizer, to tell a slow stream from a stalled one.

Academic literature search and citation tools for DeepSeek Harness: paper search via Crossref and OpenAlex with no API key, related-works discovery, and citation formatting in GB/T 7714, APA and BibTeX.

Learns what you leave unsaid in your prompts from messy turns and your own corrections, and injects the learned directives into the system prompt of every new conversation; the directives are editable in Settings and a composer button rewrites the current draft with them.

GitHub sidebar workbench for DSH: remote tree plus Issues, Pull requests and Actions tabs, with create/comment/edit/close, merge/squash/rebase, and rerun or cancel CI; mounts as a better-sidebar tab or a standalone right panel.

Recall, edit-and-resend and regenerate, plus in-conversation versioning: a timeline of every rewind, artifact rollback (git-first, snapshot fallback), a fork map of explored paths, session lineage, and a real-time watchdog that snapshots the log at the first sign of concurrent writes. Edits auto-stop the running agent (official cancel/whenIdle) so rewinds never corrupt the durable log or break /compact.

A content-aware PDF reading plugin for vision models: profiles each page for figures (vector and raster), tables, formula risk and double-column layout, then applies content-aware hybrid extraction, rendering figure/table/formula pages as high-DPI region crops. Provides a low-resolution preview to understand the page layout, and renders a specified region at high resolution. Packaged as multiple tools for agents.

Superself's self CLI as model-facing tools (project context, work units, reports, decisions) plus a /self command — cross-session, cross-project project state kept outside the code repo.

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Requires DSH 0.1.6-alpha.2. Annotate completed assistant replies, submit multiple drafts with official composer text and attachments as one Session message, navigate linked model replies, and use Settings to hide selected reasoning or tool details without changing stored events.

Game-style floating HUD: balance HP bar, context MP bar, official peak/valley pricing with countdown, auto-compaction under 5% remaining, and memory-carrying new conversation.