Plugins

Windows UI Automation from WSL: enumerate top-level windows, read a bounded element tree, and wait for or trace the path to a named element.

Windows desktop automation for dsh: 14 tools that enumerate apps and windows, capture window screenshots that still work when the window is covered by other windows, read the accessibility tree, and perform real input — click, type text (CJK included), press key combinations, scroll and drag. Loads the official computer-use runtime (@oai/sky) already installed on the machine, discovering it by enumerating vendor directories, so vendor upgrades that change hash directories do not break it.

DeepSeek Harness 插件合集（整合包）：按人群一键装齐整套插件。Curated persona plugin bundles for DeepSeek Harness.

One-tap connect Agnes language, image and video models into DSH (off by default), with image recognition and thinking level filled in automatically. After signing in to the Agnes console (re-login uses AGNES_PASSWORD), you can see the quota windows (5-hour requests, weekly requests, daily images, video), account-wide cumulative usage, and a usage pill beside the input box. AgnesCode desktop models can be connected too (Windows only), re-reading the desktop app login when the token expires, with rate-limit hits backing off on their own.

Shows whether the DeepSeek API is currently billing at the off-peak or peak rate in the sidebar brand row, with the Chinese statutory-holiday calendar built in and zh/en copy.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Session cost in rubles in the composer dock — the tariff in effect with its countdown, the API cost at that tariff, the CBR rate, the total including subagents, cache savings, and DeepSeek Platform balances.

Cut LLM costs: a Jev (System One) classifier vets each turn against a declarative policy and recommends the subagent model route, so routine work runs at flash rates while the main model keeps the hard parts; explicit /route trigger, runtime delegation-capability gate, credential redaction, and offline policy replay over the verdict log.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in two fixed report files at the workspace root.

TypeSafe Jev (modelo de decisión System One) para DeepSeek Harness, de principio a fin: jev_decision (choice/score/noul, en paralelo, respuestas tipadas + confianza), una tarjeta en Ajustes > Plugins para la API key y los conmutadores, vistas de herramientas en línea que muestran cada decisión en la conversación (respuesta, confianza, latencia, coste), un autoguard (comprobaciones deterministas + de riesgo/bucle con Jev), un panel local /jev y un benchmark de verificación en línea (96,3% en 27 preguntas etiquetadas, mediana ~283 ms en jev-latest, 2026-09-21). Honesto por diseño: solo API real, sin fallback simulado.

Automatically highlights key points, definitions, warnings, and questions in completed assistant answers using one separate model call.

English word bank for one or more children, built for DSH 0.2 and newer (0.2.0-rc.1 and 0.2.0-rc.2 verified, including the desktop shell; 0.1.7 through 0.2.x all work). 1.10 added pronunciation: in the memory cards and in the online quiz every word and every example sentence has a speaker button that reads it aloud with the built-in Windows voice - offline, with no network call and no model call - and the whole batch of audio is pre-rendered in the background whenever cards or an exam are generated, so a click starts instantly. 1.11 adds: pick words in bulk straight from the library (10 at a time, top-down, up to 50 selected, with a live counter); turn the words a child got wrong in a quiz into a one-click review set - an online card page that speaks plus a printable PDF; and every card example sentence now carries its Chinese translation underneath. Words marked on textbook or workbook photos (highlighter, red pen) are found by their marks, then translated and stored in a local SQLite bank with an occurrence count; the clipboard picker, the photo route and dictation all land in the same bank. High-frequency words surface by count, three correct answers in a row flag a word as learned, and any selection prints as a memory card set (a word split into chunks, real IPA per chunk, a grade-7 example sentence, a mnemonic hook, an A4 sheet of eight) in HTML, PDF or Word, with a print-and-answer exam page whose four options are set against each other for meaning. On 0.1.5 the settings panel does not appear - install dsh-word-vault@1.0.2 instead.

Agent billing and usage observability for dsh web: session-log direct-scan recording (zstd, per-event timestamps, watermark + lastSeq double dedup), multi-account rate profiles per provider and model, per-window live badge reading the window session id via React fiber, full glassmorphism dashboard with 14-day sparkline, budget alerts, relay-station balance queries and a 332-model official price library.

Dense translucent-glass Universal Palette for DeepSeek Harness Web — federates Commands, Models, Sessions and Conversation Hits with deterministic ranking and verified public-contract interoperability.

Literature search for DeepSeek Harness: pubmed_search, pubmed_paper and pubmed_related over the official NCBI E-utilities (including elink related-article ranking), plus scholar_search and scholar_cite (MLA/APA/Chicago/Harvard/Vancouver/BibTeX via SerpApi). Both backends return one paper shape, and a settings card configures the API keys, the Scholar backend and the rate/result limits.

Keeps an unfinished task list visible across turns. DSH clears the todos projection at the start of every turn and expects the model to rewrite the whole list, so when a turn is interrupted the plan is durably in the session log but permanently gone from the UI — and todo_write is write-only, so neither the user nor the model can read it back. This plugin registers one ordinary session/event listener, remembers the last list per session, and when a turn/start arrives whose remembered list still has unfinished work, re-appends that list so the projection stops reporting an empty plan. No fork of tool-todo and no waterfall: a plugin cannot replace the projection (the registry throws on a stateVersion mismatch), so appending the event the fold reacts to is the reachable seam. Deliberately narrow — only unfinished lists, at most one event per turn start, fails open. Verified by a controlled A/B on real sessions: identical runs differing only in whether the plugin was installed, folded through the real projection definition. Zero dependencies.

Ten live-data tools over eight keyless public APIs: FX rates, weather, npm/PyPI versions, GitHub repo stats, Bilibili video stats, A-share/index/gold quotes, and IP geolocation. Tool defaults are configurable in settings.

Composer readouts for the DeepSeek Harness: CJK-weighted draft token count, session spend at official peak/idle rates, context occupancy, and what the same usage would have cost on the costliest other model; client-only, with no host half and no credential access.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Shows DeepSeek peak/off-peak pricing status, a countdown to the next rate change, and the estimated session cost as inline text beside the model selector.

Repairs legacy DSH session logs that the current build refuses to migrate, recovering missing tool-call ids and names from the log itself and verifying each repair against the real v0 to v3 migration chain before writing.

Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.

WeChat login watchdog for DSH: surfaces dsh-wechat session loss as a Web UI banner instead of silently dropping queued messages. AI-generated, educational use only.

Adds a mood-aware Japanese kaomoji to agent replies, picked from a curated kaomojiya.org whitelist and configurable from Settings → General.