Plugins
Browse, filter, and install DeepSeek-Harness plugins.
37 plugins found
humanizer-ru (dsh)
vladimir-human/humanizer-ru
Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).
dsh-cuigengji-plugin
mistnest/dsh-cuigengji-plugin
Cuigengji, your fiction-writing assistant and editor: organize settings, develop plots, draft chapters, and revise prose with AI. Share plot canvases, character cards, and worldbooks while you choose the direction, style, and what stays in the story.
novel-writer
sailoumili/novel-writer
Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.
dsh-LorebookMD
609476965/dsh-lorebookmd
Import SillyTavern/TavernAI character cards and world books, save them as local Markdown lore documents, and generate novel prose from your prompts with the world settings as reference.
dsh-token-caveman
wode25500/dsh-token-caveman
Terse prose for DeepSeek Harness — compress the agent's own output so every reply costs fewer tokens (layer 4). Style, never substance.
dsh-tidychat
bananasoldier01/dsh-tidychat
Fold completed turns into their final conclusions, split thinking from prose with a divider, and jump between turns from a rail dockable left or right with line or dot marks, an optional ring and hover summaries; it can hide the host right-edge TurnNavigator, load earlier history, and open a pre-filled diagnostics issue.
dsh-tidy-display
drscrewdriver/dsh-tidy-display
Honest merge of two community plugins into one calmer display: the streaming reading view from dsh-better-display (fork) and the message rail from dsh-tidychat. For theme lovers it wraps reasoning prose and tool-call output in translucent message bubbles, so text no longer sits directly on busy wallpapers or skins where it is hard to read. Cross-version rc adaptation attempted across DSH 0.1.0-0.2.0 (all rc); no obvious problems so far.
InfiniteDSH
vdnight89/infinitedsh
Literary DSH plugin: one session is one book. Cover-card /new opens one of 19 realms, a prose-only 诸天万界DSH preset keeps the model writing fiction, keyword worldbook entries ground each turn, and /export-story typesets the session into a Markdown novel.
no-ai-style
01ngvi-qingyi/no-ai-style
Prose-editing skill for academic and professional writing. The composer offers three modes: Check — review and suggest without editing, with a verdict when readiness is asked; Polish — improve the wording while keeping the meaning, facts and citations; Draft — draft from the supplied material without adding facts.
dsh-prompt-polish
jinhuoooo/dsh-prompt-polish
One-click ✨ polish button for the composer: rewrites prompts and drafts with WorkBuddy humanizer-style rules (kills AI-flavored phrasing, varies rhythm, mode-aware for instructions/questions/prose) via free Zhipu GLM-4.5-Flash or any OpenAI-compatible API, falling back to offline local rules.
dsh-narrator
asza-other/dsh-narrator
Watches a turn for long silences and, once the threshold passes, injects a user message asking the model to state in prose what it is doing before carrying on, so the turn keeps going. The same text is mirrored in a lower-left overlay above the composer. The silence threshold and the minimum gap between reports are set in minutes, the prompt can be replaced wholesale, and it runs with no runtime dependencies. Requires DSH 0.2.1+ and Node.js 18+.
dsh-session-find
fomalhaut1998/dsh-session-find
Ctrl+F find-in-session for the conversation, powered by the session store rather than the DOM - labels every hit by source (you / assistant / reasoning / tool call / tool result / system), groups results by turn, merges identical snippets, offers prose-vs-everything scope, regex / case / whole-word options, highlights all matches, and copies or exports the result set as Markdown.
dsh-visual-intelligence-engine
alccs/dsh-visual-intelligence-engine
Visual Interactive Engine — interactive graphics with native Harness prose; structured input, local repair and shared controls
dsh-visual-intelligence-engine (package)
alccs/dsh-visual-intelligence-engine
Render interactive diagrams, charts and staged learning visuals alongside native prose in DeepSeek Harness.
dsh-novel-beat
drizzlegig/dsh-novel-beat
AI should not decide the key plot turns of your novel for you. Beat pauses at pivotal forks and presents 2-4 genuinely different directions, each with its own costs and consequences. You choose the direction, and the decision is recorded in a book-wide ledger for later chapters. Writing proceeds segment by segment, each segment recorded, and the story structure is checked when the chapter is done. Off by default; it never writes your prose.
dsh-dsml-guard
jessicaisleep/dsh-dsml-guard
Strips DSML markers that leak into assistant prose and resumes a turn only when a "continue" genuinely helps — a no-output marker leak, local or upstream network blips, a single-reply output token cap (max-tokens), and empty or stream errors — with message-level classification for codes upstream miscategorises and a default cap of 3 consecutive failures that any normal reply resets; quota, rate-limit, auth and context-window errors, and user aborts, never resume. Requires DSH 0.2.1-rc.2 or newer, below 0.3.0, and Node 20 or newer.
dsh-jev-guard
7starsseeker/dsh-jev-guard
Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.
formalswarm
fashionmascherine-svg/formalswarm
Runs a thesis-antithesis-seal debate whose verdict is computed from real command exit codes and case counts, never from agent prose.
cot-lint
yuanyuanma03/cot-lint
Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs and comments (dead design citations, PR vantage, change narration, review choreography), shipping the cot-trim fixing skill as the installable bundle.
deepclear-ui
kun-nnn/deepclear-ui
Dot-matrix appearance plugin for DeepSeek Harness: a halftone welcome page (portrait and deepseek/harness wordmark on one dot lattice), a dot-matrix launch splash, a reasoning-level badge printed in dots inside the composer (MAX in whale blue), a spinning dot sphere with an English status label while the model thinks, a fading caret dot trail, and a hover dot field with a whale-blue rail on sidebar buttons. Also re-inks the quieter chrome: frosted composer glass, a grey focus halo, whale-blue bold prose, whale-blue diffs, reading layout and a low-saturation code palette. Fifteen preferences live in the profile config and can be switched off one by one. Requires DSH >=0.2.2-rc.3.
dsh-style-detector
grq6414-hash/dsh-style-detector
Chinese prose "AI-flavor" detector in the right sidebar: a local rule engine scores and highlights template phrasing, uniform sentence rhythm, vague imagery and repetition, with a separate typo-check page; the score is always computed locally. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-yubagu
ericenyan/dsh-yubagu
Pre-send self-check for model prose: collides the exact sentence against a phrase list of delivery-receipt tics, then asks for the whole sentence to be re-thought rather than reworded. Three tiers, a per-turn prompt hook, and a ledger panel.
dsh-colorlab
ruegg114514/dsh-colorlab
Colour engine for the chat UI: ships the Mariana palette as the default preset, exposes 18 colour slots and 9 Markdown prose roles, lets you save up to 12 presets, and colours LaTeX blocks by running Sublime's own LaTeX syntax.
dsh-jev-verify
xienda/dsh-jev-verify
0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.