Plugins
Browse, filter, and install DeepSeek-Harness plugins.
113 plugins found
dsh-sidebar-more
meiyuxuan2007/dsh-sidebar-more
Fold left-sidebar panel entries into a More menu on demand, freeing height for the workspace and session list; entries can be opened from the menu, restored in one click, and the choice persists across reloads. Nothing is folded on first install; entries that appear later are folded by default (switchable).
dsh-matt-flow
yuwang/dsh-matt-flow
A six-stage development workflow preset for the Matt Pocock skill suite: grill, spec, tickets, implement, review, wrap-up. Adds a stage chip in the composer tool row and decision cards that ask up to three multiple-choice questions at a time.
dsh-better-choice
tlewa/dsh-better-choice
Adds two enhancements to DSH ask_user_question choice cards: right-clicking an option expands a per-option note that is merged into the submitted custom answer, and a footer field asks a side question answered by a fork subagent from the session context, read-only, with no write-back. Keeps left-click, skip, paging and the countdown working as before, and only claims generic choice cards, not plan review or approval cards. Supports DSH 0.2.x from 0.2.0-rc.1 (verified on 0.2.2-rc.1) and Node.js 20+. Derived from buaaflyaway/dsh-question-note (MIT) and inspired by MichengAI/dsh-btw (Apache-2.0); do not install it together with dsh-question-note — both take over the same ask_user_question card.
dsh-snail-memory
snaiheihei/dsh-snail-memory
Layered global and workspace memory for DeepSeek Harness, with a web panel to browse entries and tune distillation and consolidation, an index kept in context with records loaded on demand, and a per-session choice of layer.
dsh-models-router
imzl-zl/dsh-models-router
Transparent cross-provider failover for DSH Agent main requests: named fallback chains, per-session chain choice, per-route retry overrides.
dsh-sidebar-overflow
cxv117793-blip/dsh-sidebar-overflow
Puts a More row at the end of the sidebar main panel list and lets you decide, entry by entry, which panels stay visible and which move into it: a menu lists every entry with a one-click switch in either direction, a search box filters long lists, and a single Restore all clears both kinds of key. Also hides the footer action buttons, keeps the plugins entry un-collapsible, and writes each choice to the profile config so it survives a restart.
dsh-whale-writing
azonda/dsh-whale-writing
Adds a writing console above the composer with four style tiers (T1-T4) and five rigor tiers (L1-L5), selectable by hand or left to automatic choice; keeps project terminology and banned phrasing in .mem/config.md with a read-only human section; and provides a whale_polish tool that rewrites expression without changing facts.
dsh-ai-providers (dsh-ai-typesafe)
firefox2100/dsh-ai-providers
TypeSafe AI Jev decision provider for typed probabilistic choices and scores in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.
dsh-persona-plugin
gulagala001/dsh-persona-plugin
Create, import and manage personality presets with global and per-conversation choices.
dsh-lucky-block
lyhtakeashot/dsh-lucky-block
Adds a draggable lucky-block button to the DeepSeek Harness web UI. Single-click plays zero-cost little performances (popups, a fake blue screen, daily fortune, trivia, cold jokes, music, and a set of visual stunts); a 1.4-second long-press mines the block open and starts a new session to write a random paper, read the news, invent something, or spin a short story. It also appends a "lucky block" choice to the model's multiple-choice questions and rolls a random pick, reversible by saying "rollback". Block appearance and event weights are adjustable in settings.
dsh-skill-writing-plans
linlin539/dsh-skill-writing-plans
Adds a writing-plans skill that generates a structured implementation plan document before coding, then executes simple tasks inline or offers an execution choice for complex work.
dsh-zvec-grep
jayyuen666/dsh-zvec-grep
Semantic workspace search: three model tools (`zg_search`, `zg_index`, `zg_status`) drive the `zg` CLI for hybrid BM25 + vector + RRF retrieval, with a search-first gate that refuses `grep`/`rg` in an indexed workspace until a successful `zg_search` re-arms a time-windowed quota, and a settings card for embedding choice, gate values and job-backed index rebuilds.
dsh-ui-design-toggle
yukoz1227/dsh-ui-design-toggle
Requires the ui-ux-pro-max design skill to be installed; this plugin only gates it. Adds a switch to the DSH sidebar footer that enables or disables the ui-ux-pro-max design skill at runtime; the choice is stored in the profile settings.
dsh-window-size-keeper
ecbob/dsh-window-size-keeper
Keeps the DSH desktop window the size you left it: records the last outer frame of the main window in physical pixels and restores it, centred on the work area, on the next start - and it acts before the window is ever shown, so the boot animation plays at the right size. The settings page offers 12 presets (1024x768 to 3840x2160), free-form custom width and height, a centre-on-restore switch and an apply-now action; a choice takes effect immediately and persists. Resizing goes through a small helper executable compiled on the user's own machine: the C# source ships inside the plugin, is built on first run with the in-box Windows csc.exe (measured ~110 ms once, cached next to the state file, ~90 ms to start), and falls back to a short-lived powershell.exe process when that is not possible. The package ships no binary, declares no npm dependencies and makes no outbound network request. Windows only.
dsh-bifenggang
ccccwwwxx/dsh-bifenggang
Time-based model routing: a settings panel defines weekday peak and off-peak windows and the provider/model each one uses, the choices are read from the harness registry (API keys and subscription logins alike), and a global switch decides whether that policy sets the model and reasoning effort of every request. The switch is independent per session, each session row carries a light showing its own state, and the settings panel names the model in force right now and why. A day no window matches — every weekend and holiday — uses the primary model of the first plan; the advanced thinking model is a separate axis, used only when a session itself asks for max reasoning.
dsh-peak-hours
lion231226/dsh-peak-hours
A composer switch between running always and running only in off-peak hours, set per session: a task is judged by the session that owns it, so changing one session no longer changes the others, and a session without its own choice follows a default. In off-peak mode every task, including one already running, is held at its next agent step or tool dispatch when a Beijing peak window starts (Monday to Friday 09:00-12:00 and 14:00-18:00, statutory holidays excluded), and one timer releases it at the boundary; weekends and holidays are idle all day. The holiday calendar lists every statutory day off in 2025 and 2026 from the State Council notices, and a year with no data is reported as unknown rather than assumed to be a workday.
dsh-websearch
imroc/dsh-websearch
Multi-engine web search for DeepSeek Harness: an aggregated ctx.web search provider (auto-routing + sequential fallback, free engines keep search alive) plus a web_search_pro model tool with per-query engine choice, fan-out, batch and verticals — Brave, B
dsh-wsl-jev
173787247/dsh-wsl-jev
Call TypeSafe Jev / OpenRouter System One for noul, choice, and score (jev_ask / jev_check / jev_rank).
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.
dsh-model-accordion
lakabuji-arch/dsh-model-accordion
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
dsh-desktop-notify
chengzhi43/dsh-desktop-notify
Sends a desktop notification when a turn finishes or the agent waits for your choice, and a click returns to that conversation.
dsh-vertical-kit (dsh-adr-check)
zjukop3/dsh-vertical-kit
Architecture decision record hygiene: a status, the context that forced a choice, the decision itself, consequences that include the cost, and the alternatives that lost. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-octagon-alerts
hexa-center/dsh-octagon-alerts
Plays a synthesized chime when a Session needs a choice, needs approval, or finishes while you are away, with a pickable chime and a volume slider for each moment.
dsh-plugin-trim
haidai233/dsh-plugin-trim
Trims the tool surface per session. Each session owns a profile — a tool whitelist — applied through `agent.ctx.tools.restrict({ allow })` on that agent scope only, and switching one session never touches another; `full` is the built-in no-restriction profile. The provider only picks the default: a session created or switched onto a local provider (explicit `localProvider`, `routes`, a loopback/private baseURL, or a local-ish id) gets the `local` profile, a cloud one gets `full`, and the re-plan runs on model-selection events plus one delayed pass because the projection can land after the event. Profiles are editable from the panel and persisted under `~/.dsh/plugin-trim-state.json`; an explicit per-session choice overrides the provider default until cleared. A separate, opt-in layer physically disables whole plugin entries through `pluginManager.setPluginEnabled` — that one is profile-scoped by API and the panel labels it as such rather than pretending it can be per-session. A `tool_trim` tool exposes list/status/profile/set/apply/restore to the model. The panel is served by a loopback-only HTTP server the plugin starts on its own fixed port — `http://127.0.0.1:12256/` (auto-bumps on collision, configurable) — because the DSH port changes on every restart and a locally linked package gets no market card in the sidebar; it lists live sessions with their profile and tool count, an editor per profile, a provider picker limited to providers declared in the profile or currently in use, and the full plugin list with search and paging. Two implementation details worth knowing: `tools.restrict()` is an intersection and cannot widen, so the old restriction is released before the visible set is read — otherwise switching to a bigger profile would shrink instead of grow; and every disposer is registered on `ctx.effect`, without which a hot reload leaves an unremovable restriction behind. Measured on a 12GB laptop GPU with a 27B model and a fully resident 256K cache, same conversation: 105 tools / 56,306 prompt tokens / 22.5 tok/s decode, 62 / 34,207 / 43.0 after disabling three tool-heavy plugins, 14 / 12,890 / 66.8 after a session moved to the local profile, with prefill rising from 487 to 1,310 tok/s. Restricting also drops the skill catalog injection, roughly 4.3K more tokens. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.