Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1191 plugins found
dsh-import-agents
chang-tong/dsh-import-agents
Import pi / opencode / codex / claude-code sessions, chat history, and agents into DeepSeek Harness — one-click Sync button, slash commands, session-start migration prompt
dsh-plugins (dsh-prompt-notes)
kp-z/dsh-plugins
Notes pad in the right sidebar for standing prompts, skills and MCP servers: each note has a scope (all sessions / one workspace / one session) and a pin that switches it on; MCP notes can only be pinned by a human. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-plugins (dsh-mermaid-comm)
kp-z/dsh-plugins
Makes the AI default to Mermaid diagrams in development conversations: a composer checkbox controls prompt guidance, mermaid_validate checks syntax, a gate repairs or drops broken diagrams, and a vault versions them. Rendering is provided by dsh-mermaid. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-prompt-enhance
surfishs/dsh-prompt-enhance
Prompt enhancement in the composer: fills a draft out into a complete, ready-to-use prompt — goal, constraints, steps, output format and acceptance criteria — then lets you fill it back, copy, regenerate or undo. Intent is preserved, and missing details are marked as placeholders rather than invented.
LoopPrism (dsh-loopprism)
atlasmarkz/loopprism
Sends DeepSeek Harness session start, prompt, tool result and stop events to the local LoopPrism app, and registers LoopPrism's session-review tools (the ones lpa mcp serves) as loopprism_* tools for the agent.
dsh-yanfield
zzimar/dsh-yanfield
A long-form fiction writing desk inside DeepSeek Harness: a shelf of books, a three-column editor (chapter tree, prose, AI assistant), outlines, character/world/foreshadowing notes, story archives, and an AI assistant whose prose and note edits are reviewed before they are written. Interface and AI prompts are bilingual (Chinese and English), manuscripts stay local in SQLite, and the model uses the DeepSeek service already configured in Harness.
dsh-english-cards
aoilang/dsh-english-cards
Save English learning cards while interacting with DeepSeek Harness. It adds a line to the system prompt on every step telling the model to check your English and call english_cards_capture first; cards stay on this machine unless you turn on the sync switch (off by default), which after an OAuth login in your browser sends your original and corrected sentences with their cards to aoilang.com.
dsh-prompt-prediction
qingj01/dsh-prompt-prediction
Unofficial DeepSeek Harness plugin for next-prompt ghost text; Tab or ArrowRight fills an editable draft without sending it.
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.
dsh-lite-memory
regrevia/dsh-lite-memory
Nothing stays in the system prompt: a hit returns titles only, a body loads only when read, and project rules can grow themselves.
dsh-novel-workbench
shanjun-pro-max/dsh-novel-workbench
A full-screen novel-writing workbench: chapter board, draft candidates reviewed and merged paragraph by paragraph, plot summaries carrying an index header, and a writing pack assembled from the outline, character cards and earlier chapters. It also reads a shelf of finished books you import, extracts their writing habits in one run, merges them into a single style standard, and puts that standard in the prompt for every later generation.
dsh-language-guard
58fly/dsh-language-guard
Locks the model's reasoning, replies and tool-call descriptions to a chosen target language (Simplified Chinese by default) with system-prompt sections at the head, middle and tail of the prompt, offering three strength levels, an auto mode that follows the DSH interface language, a settings panel that shows the language currently in effect, and a sidebar quick switch.
dsh-prompt-predict
ferrisching/dsh-prompt-predict
Predicts the user's next prompt after each assistant reply and shows it as gray ghost text inside the composer; Tab accepts it, ↓ generates the next suggestion, ↑ returns to the previous one, and Esc dismisses it. Each assistant reply triggers an extra call to the session's model, carrying the most recent user and assistant text.
dsh-rules
ndsanes/dsh-rules
Discovers rule files from every convention OMP supports and injects them into the system prompt as an always-apply layer plus a rulebook index, then enforces them with time-traveling stream rules that abort violating output mid-turn, deny a matching tool call, fold a reminder into that call's result, or ask a judge model about the finished reply. The same tool lets the model write new rules, and an audit panel on the Plugins page says why each rule is in force.
dsh-pixmart
mirror9933/dsh-pixmart
E-commerce product image generation for DSH: 24 prompt modules covering main, detail and ad images, style transfer from a reference shot, batch runs, and a project gallery with live preview.
dsh-skills-manager-plus
appthin/dsh-skills-manager-plus
Manage DSH skills and commands from Settings: list, enable/disable, edit, delete and add skills across global and project scopes, and save reusable prompts as slash commands.
tripo3d-plugin-dsh
vast-ai-research/tripo3d-plugin-dsh
Tripo 3D skills for DeepSeek Harness — generate engine-ready 3D assets from a text prompt or a reference image via tripo-cli, with texturing, rigging, retopology and format conversion in one pass.
dsh-tweaks (prompt-history)
converk/dsh-tweaks
Recalls prompts sent earlier in the current session with the up and down keys in an empty composer, and shows a position badge while browsing.
dsh-model-prompt-injector
moonlitdropofblood/dsh-model-prompt-injector
Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.
dsh-universal-worldbook
tritiumwang/dsh-universal-worldbook
Request-level one-time prompt injection without further context pollution. SillyTavern-style UI and data compatibility, keyword/regex/constant triggers, and a lore_lookup tool for on-demand searching.
dsh-discipline-guard
haozheou/dsh-discipline-guard
Agent discipline guard for DeepSeek Harness: four gates enforced at the harness boundary — loop circuit-breaker, token-cost fuse, route-switch warning, plan approval — where prompt-level reminders can't reach, so an agent can no longer burn a weekly quota in minutes; one-click 🛡 chip, hot-reloadable thresholds, and presets from invisible-but-armored to warn-only.
dsh-tacit
hackernotfound/dsh-tacit
Learns what you leave unsaid in your prompts from messy turns and your own corrections, and injects the learned directives into the system prompt of every new conversation; the directives are editable in Settings and a composer button rewrites the current draft with them.
dsh-i-have-adhd
yongshuai0314/dsh-i-have-adhd
Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.
dsh-capability-toggle-plugin
lifeopsgo/dsh-capability-toggle-plugin
Adds session, project, and global controls in the DSH WebUI for skills, MCP servers, tools, prompt injections, approval escalation, and safety guards; enforcement is scoped to the current agent.