Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

177 plugins found

Q

dotfiles

qw457812/dotfiles

Expose Pi prompt templates as DeepSeek Harness slash commands

53 months agoSkills
D

dsh-plugins (agent-roles)

delthin/dsh-plugins

Manages reusable agent role templates (job prompt, model and reasoning effort, tool allowlist, skills) and starts role members through the native Agent Team interface to delegate and continue tasks.

44 days agoWorkflow & AutomationApache-2.0
J

qiaomu-cover-design-dsh

joeseesun/qiaomu-cover-design-dsh

Design covers on a canvas using templates and typography controls, and export PNG images.

44 days agoVision, Voice & MultimodalMIT
J

zgs-ppt

john-20260101/zgs-ppt

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.

415 days agoSkillsMIT
O

dsh-pages

orderg-x/dsh-pages

Lets the model turn an answer into a web page that lives right inside the chat. The show_page tool either fills one of 10 built-in templates (report, compare, checklist, dashboard, timeline, flashcards, quiz, flow, mind map, roadmap), where the model writes only the content and the plugin does layout, interaction and saving, or saves a full page the model wrote itself (calculators, games, custom layouts). The mind map spreads branches to both sides with collapsible nodes; the roadmap draws either a research-proposal style layered technical route, with links that route around boxes, or a quarterly swimlane roadmap with milestones. Hand-written pages get the same design as base styles inside a CSS @layer, so the page's own CSS still wins. The page appears under the reply at its content height, interactive and following DSH's light/dark theme. The page's localStorage is stored in DSH per page, so what users tick or type survives reopening and new versions, and the same page open in the chat and the right sidebar stays in sync. Each edit is saved as a new version you can flip back to. After saving, the page is checked in a hidden local Chrome or Edge (script errors, horizontal overflow, dark mode not applied) and problems go back to the model. The right sidebar shows the page full-size with versions, a gallery of all pages and export to PNG, PDF or HTML. Pages run in a sandboxed, separate-origin frame with a strict CSP: no access to DSH data and no fetch, XHR or WebSocket. Works on phones with dsh-mobile.

44 days agoUI EnhancementsMIT
P

dsh-notify-desktop

paleech0/dsh-notify-desktop

Windows native toast notifications for DSH desktop sessions: turn ends, approvals, questions and a reminder for an unanswered wait — each with its own sound and popup text (up to three named templates per situation), three delivery modes, previews, and imported custom sounds. Clicking a toast raises the DSH window.

43 days agoIntegrations & RemoteMIT
T

dsh-dpia-workbench

the-data-galaxy/dsh-dpia-workbench

Adds a versioned DPIA workbench to DeepSeek Harness for source-linked facts, follow-up answers, reassessment, and reviewable reports. Needs Python 3.9+ with `python-docx`, `pypdf`, and (for PDF templates) `reportlab` + `pdftoppm`.

423 days agoWorkflow & AutomationAGPL-3.0
J

dsh-delivery-board

jerryxff26-alt/dsh-delivery-board

Delivery board for client-project teams: stage pipeline (default or governance template, or custom stages), cards with owner, due date, acceptance criteria and DoD, an automatic handoff audit log when a card changes stage, a progress/risk/blocker/decision log, a weekly Markdown client report, a loopback-only drag-and-drop board and a read-only HTML export; state lives in delivery.json in the workspace (11 delivery_* tools plus a /delivery command).

45 days agoWorkflow & AutomationMIT
R

dsh-plugins (session-title-template)

redheartsecretman/dsh-plugins

Configurable template-based session titles with a type vocabulary, AGENTS naming guidance, historical backfill, and explicit rename and refresh tools.

3yesterdaySessions & MessagesMIT
A

lit-report-ppt

ashenseeker/lit-report-ppt

Turns one journal paper PDF into three deliverables by default — a Chinese group-meeting literature report deck (.pptx) in the Nanyang Normal University physics template, a matching Word speaker script, and a two-colour defence-prediction Q&A HTML (ten-odd questions with short direct answers). Requires Python 3 with python-pptx, python-docx, Pillow and pymupdf (pypdf fallback); install them with pip install -r requirements.txt.

38 days agoSkillsMIT
E

dsh-thinking-guard

ethanwong-hk/dsh-thinking-guard

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

32 months agoDev & Plugin ToolsMIT
K

dsh-input-list

konglong87/dsh-input-list

DSH prompt library and reusable snippets plugin: save, edit, delete, and append prompt templates, workflow instructions, and reusable text from a button beside the composer without sending.

32 months agoUI EnhancementsMIT
H

dsh-custom-instructions

huanghai-lab/dsh-custom-instructions

Manage global AGENTS.md in DSH Web with Markdown preview, reusable templates, version history, import/export, failed-import rollback, and revision-conflict protection.

33 months agoUI EnhancementsApache-2.0
T

dsh-session-notify

telosmaylx/dsh-session-notify

Notifies you with a browser notification and toast whenever a session turn ends, with 5-language templates and custom presets.

3last monthIntegrations & RemoteMIT
R

l123-harness

reatcat/l123-harness

Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.

33 months agoMemoryMIT
B

dsh-testgen

bujue600-arch/dsh-testgen

Automated unit-test generation: a /testgen command and generate_tests tool that scaffold, run, and fix tests until they pass (LLM + offline template generators; vitest/jest/mocha/node:test).

33 months agoDev & Plugin ToolsMIT
Z

dsh-boot-nexus

zeki520/dsh-boot-nexus

Combines an intro video, the suite six-act cold start and a screensaver into one boot animation: a single overlay, state machine, clock and config file, with a glass-panel settings card holding every option. The suite engine, its templates and a full-quality set of intro clips and screensavers (720p–4K originals, ~197 MB) ships inside the package, so a fresh install animates immediately and keeps playing after the original plugins are removed; enable it instead of dsh-boot-suite or dsh-boot-animation, not alongside them.

22 days agoUI EnhancementsMIT
A

dsh-mind

ashenseeker/dsh-mind

Adds a mood system to DeepSeek Harness — 33 named moods judged every 3-6 hours with small per-message adjustments, plus cross-session memory, an aesthetic taste library and an encrypted diary. The mood, memory, taste and diary tools are all callable by the model, and each of the five modules has its own switch. Flat by default: every mood starts at 0, so a quiet day reads as calm instead of an always-on mood. The diary is written only by the model; no summary template is generated. A trimmed fork of JMX-4869/dsh-mood; install either this or upstream dsh-mood, not both, because both register the same mood/diary/taste/memory tool names.

28 days agoIntegrations & RemoteMIT
V

dsh-prompt-optimizer (bundle)

viewway/dsh-prompt-optimizer

Prompt optimizer for the DSH composer. One click runs rewrite then self-review rounds over the draft with per-round diff preview, and a rejected result rides into the next round as a prior attempt. Five fixed re-run directions (more concise / more detailed / more technical / restructure / stronger acceptance); a 164-role library ships in the package, roles recommended by draft or picked explicitly; matched installed skills fold into the meta-prompt under exact-name constraints; results save to a prompt library (browse, insert, re-optimize, two-step delete); mechanical acceptance criteria carry an executable check-command template; output language follows the agent UI language.

24 days agoUI EnhancementsApache-2.0
W

lit-report-ppt

wld12314/lit-report-ppt

Turns one journal paper PDF into a Chinese group-meeting literature report deck (.pptx) in the Nanyang Normal University physics template, plus a matching Word speaker script. Requires Python 3 with python-pptx, python-docx, Pillow and pymupdf (pypdf fallback); install them with pip install -r requirements.txt.

29 days agoSkillsMIT
L

dsh-local-trim

leonlee114514/dsh-local-trim

One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider. From 0.4.9 the panel can no longer vanish. It used to be possible for the whole section to disappear from the plugin detail page while the host stayed up, the HTTP bridge kept answering, and no crash log appeared. The cause was a scope error: a helper was declared inside one component and referenced from another, which is valid JavaScript and passes a syntax check, so it only threw at render time - when the user pressed the scan button and React ran the state updater. The host wraps every slot entry in an error boundary whose fallback is an empty anchor, so the throw was contained silently: the panel was not uninstalled or crashed, it was replaced by an empty div. The helpers now live in the module scope both components share. The client half also gained its own test - a minimal React stand-in loads the real panel module, really calls the components, really runs the state updater at render time, and presses the scan button, so this class of error can no longer reach a release.

23 days agoModels & ProvidersMIT
L

dsh-artifacts

lucagiftzek/dsh-artifacts

An Artifacts tab in the DSH sidebar that lists the files an agent produced and previews them in place with live reload, plus artifact template tools for agents.

216 days agoUI EnhancementsMIT
Z

DSH-javadev-enhance

zxj0306/dsh-javadev-enhance

Java efficient development plugin for DeepSeek Harness providing deterministic auto-fix for .java files, token-saving template intents, and cross-platform JDK/Gradle/Android SDK/FFmpeg/LWJGL/IDEA discovery with persistent caching.

223 days agoDev & Plugin ToolsMIT
W

dsh-mind

wld12314/dsh-mind

Adds a mood system to DeepSeek Harness — 33 named moods judged every 3-6 hours with small per-message adjustments, plus cross-session memory, an aesthetic taste library and an encrypted diary. The mood, memory, taste and diary tools are all callable by the model, and each of the five modules has its own switch. The diary is written only by the model; no summary template is generated. A trimmed fork of JMX-4869/dsh-mood; install either this or upstream dsh-mood, not both, because both register the same mood/diary/taste/memory tool names.

28 days agoIntegrations & RemoteMIT