Plugin

Policy-layer guard that checks tool calls before they run: a read whitelist, a sensitive-path deny list (credentials, browser profiles, chat history, other users' home directories), dangerous-command blocking, subagent isolation, and a static scan that quarantines executables. Every denial is appended to an audit log. It is a text-and-path filter, not a sandbox or antivirus: dynamically built paths, encoded payloads and packed binaries can get past it, and it does not replace the OS antivirus.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Compares installed plugins against a downloaded DSH update and reports which interfaces they use that the update no longer exposes. Runs before you install, with a dry-run diagnose command for when it declines to act. Windows only, on the DSH desktop app, with Node.js 18+.

Multi-channel push notification plugin supporting Bark (iOS) and ntfy (Android/iOS/Web/Desktop) for turn completion, approvals, questions, and quota halts.

GitLab panel in the DSH right sidebar: commit graph, branches, changes, merge requests (inline diffs, review submission, pipelines), issues, and agent tools with an approval queue for triage and batch actions. GitLab data needs a personal access token or a logged-in `glab`; local git data works without either.

Config-driven lifecycle hooks for DSH: block or observe tool calls, and react to completed turns, messages, and title changes with shell commands.

Plot decision gate for novel writing: five beat_* tools register each node that changes the story into a decision point with 2-4 divergent options, beat_gate returns pass:false until the author picks, and beat_compile turns the picks into a chapter outline.

HarmonyOS delivery orchestration for DSH: freezes a four-dimension acceptance pack whose measurable criteria carry machine-checkable assertions, runs an adversarial pre-review before dispatch, hands the work to DevEco Code in Goal mode, then audits the delivery with independently gathered evidence (screenshots, UI tree, logs, hashed evidence bundle), recomputing assertion verdicts against measured values and filing rework orders; includes a cited rule catalog, a user-confirmation state and a gate calibration ledger.

Deck-generation skill for the National College Student Career Planning Competition. It takes a contestant's profile, materials and photographs, drafts a page-by-page outline for confirmation, then renders a 15-20 page reading-type PPTX (under 15 pages is flagged as a page-count error) using 17 page types, three built-in themes or a user-supplied template; the build audits the estimated layout (text overflow, per-page word count, missing evaluation dimensions, material gaps) and the rendered PDF is checked again for out-of-bounds and overlapping text. Requires Python 3.9+ with python-pptx, python-docx and Pillow; LibreOffice (soffice) and pdftotext are optional for the PDF layout re-check.

Group skills into named sets, toggle any combination, drag to reorder, and preview each group catalog token cost.

Whole-PDF paper translation for DSH on top of a BabelDOC installation you provide (Python CLI, with an OpenAI-compatible API key in its config.toml): bilingual dual-page output, a token cost estimate before running, a per-domain glossary reused across papers, and the server-side thinking overhead disabled for translation.

An AI reading buddy: it sits next to you while you read, and only knows the pages you have already reached — so it cannot spoil the rest, and it never summarizes the whole book for you. Highlight a sentence and ask about it, or just ask about what you finished; it usually restates what you seem to mean and asks one concrete question back. What you work out can be saved as a takeaway and later becomes a review card that jumps back to the sentence. EPUB, MOBI, FB2, TXT, Markdown, HTML, CBZ.

Compiles a repository into a source-grounded code map: structured pages where every claim carries a verifiable path:line citation, an interactive dependency graph, knowledge cards, four model tools and the /codemap command. Deterministic, no model calls, zero dependencies.

GitHub Trending radar inside the Harness Web UI: fetches the daily, weekly or monthly board (optionally filtered by a language), analyzes each repository into description, star gain, tech stack, highlights and risks, renders the result as a filterable card panel with paging, and registers the github_trending tool plus the /github-trending command.

Answers Dark Souls III questions from your own Windows PC save (default `%APPDATA%\DarkSoulsIII\*\DS30000.sl2`): level and stats, current area, bonfires/rings/spells/covenants counted by family, kill state for the 24 bosses, and Steam achievements when Steam is installed - exposed as model tools plus a progress pill beside the composer and a 19-area sidebar page with next-step suggestions. The save stays read-only and is parsed locally by a bundled Python 3 script; Python 3 and the `cryptography` package must be installed, and the game data ships with the plugin.

Publishes and reads QQ Zone posts through SnowLuma's OneBot qzone_* actions (SnowLuma 2.2+ signed in to QQ), and lets the agent understand images with a local vision model (OpenAI-compatible gateway) or Windows OCR.

Crea video esplicativi narrati da uno script. Per impostazione predefinita usa schede di testo (rapide e precise per i tutorial) oppure riprese generate dall’IA per segmento (serve AGNES_API_KEY). Include 14 voci neurali cinesi online e 3 voci offline per Windows, più un pacchetto di campioni da generare con un comando per scegliere ascoltando. Richiede ffmpeg. Per le voci online, copia lo skill video-remix incluso in `<workspace>/.dsh/skills/video-remix` ed esegui lì npm install.

Compila LaTeX con TeX Live installato sul computer. Lo strumento `latex` impagina formule in SVG, PNG o PDF e documenti interi in PDF (per il cinese passa a xelatex con ctexart), salva il file nello spazio di lavoro e restituisce un riferimento Markdown. Una sezione del prompt di sistema chiede al modello di usare `$...$` e `$$...$$` invece dei blocchi di codice. Se TeX Live non è presente, un banner sopra il compositore propone l’installazione con un clic di BasicTeX o TinyTeX.

Memoria persistente compatibile con Claude Code: all’avvio della sessione l’host inserisce l’indice MEMORY.md e il modello gestisce i file con normali strumenti di lettura, scrittura e modifica. Una pagina delle impostazioni elenca i ricordi salvati. Usa lo stesso formato su disco di Claude Code; la modalità claude condivide esattamente la stessa cartella della memoria.

Un interfono tra finestre DSH già aperte. Niente team o nuove sessioni: solo messaggi peer-to-peer con un limite di passaggi.

Precalcola in background il riepilogo della compattazione e conferma il risultato trattenuto quando scatta quella per pressione, eliminando un passaggio del modello in primo piano. Si registra come motore di compattazione della sessione, blocca l’intervallo riepilogato affinché l’impronta del payload coincida al momento della conferma, elimina prima i risultati degli strumenti e torna al flusso standard in primo piano se il payload cambia o il contesto trabocca.

Esporta in sola lettura una conversazione di chat.deepseek.com in una nuova sessione DSH: il pacchetto di passaggio mantiene testuali i turni selezionati e riduce quelli precedenti a una riga ciascuno, poi precompila il compositore senza inviare. Secondo quanto pubblicato, solo Windows; servono Edge o Chrome e un primo accesso a chat.deepseek.com.

Riavvolge sul posto un turno terminato: un pulsante accanto al tuo messaggio lo rimuove, insieme a tutto ciò che segue, dal contesto del modello e ne rimette il testo nel compositore per modificarlo. Facoltativamente ripristina i file modificati dal turno tramite DSH filesystem service.

Trasforma il menu dei modelli nel compositore in un elenco a due livelli (prima il provider, poi i suoi modelli), mostra insieme il modello attuale e il provider, chiede il livello di ragionamento dopo la scelta e permette di nascondere nelle impostazioni interi provider o singoli modelli.