Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1180 plugins found
dsh-latex
sbvan/dsh-latex
Renders `latex` / `tex` code blocks in the chat as KaTeX formulae, and injects a system-prompt section that tells the model to write `$...$` and `$$...$$` instead of fenced code blocks.
dsh-ghost-prompt
mochinek0/dsh-ghost-prompt
Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.
dsh-session-live
lilcandi/dsh-session-live
Live preview inside the sidebar session hover card: what the session is doing right now (running tool with elapsed time, thinking, last tool duration), an attachment thumbnail with click-to-enlarge, the latest user prompt and assistant reply with injected system scaffolding stripped out, a recent-tool icon strip, turn count plus token totals plus model name on one line, and a 12-item settings page (11 switches plus a slider) persisted to the profile.
dsh-composer-enhance
heshen-1/dsh-composer-enhance
Composer prompt enhancement for DSH Web: a ✨ button rewrites the current draft in place after asking only about genuine ambiguity, and an empty composer shows a grey next-message ghost that Tab or a click fills into the draft without sending.
dsh-prompt-enhancer
gu040303-ai/dsh-prompt-enhancer
One-click plain-text prompt enhancement with optional local checks and sentence review in DeepSeek Harness.
dsh-prompt-enhancer
cosmoliu2002/dsh-prompt-enhancer
Adds a ✨ button and an /enhance command to the composer that rewrite the draft into a structured prompt, flag open questions below the input, follow the current session model, and offer an undo.
dsh-prompt-reforge
cloud017/dsh-prompt-reforge
Adds a reforge control to the DSH composer that rewrites the current draft into a sharper prompt in place, as one undoable edit, with one-click revert and cancellation.
dsh-prompt-shortcuts
cdredfox/dsh-prompt-shortcuts
Pinned prompt shortcuts in a single row above the composer — one click replaces the draft with the saved text — plus a searchable panel for pinning, editing and deleting prompts, overflow collapsed into a "More" menu, storage in a Host-side JSON file, and a prompt_shortcuts agent tool that reads and writes the same file.
dsh-enhance-prompt
adcx222/dsh-enhance-prompt
Adds a sparkle button to the DSH composer that rewrites the current draft into a clearer, more specific prompt with a single tool-free LLM call, then writes the result back into the input.
dsh-zh-ui
1186258278/dsh-zh-ui
Chinese frontend UI design spec for dsh: injects the zh-ui-design skill and prompt rules (section-name headings, no filler copy, one signature element), plus a 10-rule UI copy/style linter.
dsh-prompt-freeze
lemonel/dsh-prompt-freeze
A DeepSeek Harness plugin that freezes tool declarations to improve prompt cache stability.
dsh-turing-table
dingchenhui0618-arch/dsh-turing-table
A social deduction game played against your own model configurations. A table has N seats (six by default, one of them yours) and some of the rest are played by agents bound to different provider, model, temperature, system prompt and disguise settings; you interrogate them and cross-check the answers to work out which seats are not human. Seat identity and each agent model configuration stay hidden in the host state until a seat is judged, then the disguise parameters are revealed. Every round exports a per-seat conversation JSONL plus the judgment record, and the same seed with the same move script replays byte-identical, so runs with different models or disguise strengths can be diffed.
dsh-read-guard
zhengqiuyang/dsh-read-guard
Deterministic prompt-injection interception: tool results from file reads, repo searches and web fetches are scanned before they enter model context; high-severity findings quarantine-wrap or block, and credential-material files quarantine on the path alone.
dsh-prompt-drift
zhengqiuyang/dsh-prompt-drift
System-prompt surface drift gate: every section any plugin or preset contributes to the assembled system prompt is hashed and baselined; a silent rewrite of what the model is told fails loud.
dsh-approval-explainer
arisuyuuko/dsh-approval-explainer
Writes a model-generated annotation into every DSH escalation approval prompt — what the command does, what the model intends, how risky it is and why, and what each choice means — and keeps a searchable history of past approvals at /dsh-approval/history, with a diagnostics page at /dsh-approval/diag.
dsh-mega-plugins (dsh-github-issue)
zhangj1164/dsh-mega-plugins
GitHub issue service for DSH: turns a telemetry failure analysis into a uniform issue report, builds a pre-filled new-issue URL that is shortened when it would exceed a configured length budget, rewrites a plain description into a structured issue with the deployment's model, and closes the intake loop by listing the open issues that carry a claim label and handing each one to a fresh session as a one-shot automation task on the host's Schedule service, which delivers the rendered prompt into that session when the task comes due and shows up on the Web Automation tasks page (a host with no Schedule service admits the prompt directly instead), skipping issues an earlier pass already dispatched, leaving the local day uncommitted when every dispatch is refused so the next startup tries again, and repeating the pass on the first start of each local day when autopilot is enabled.
dsh-harness-trace
oihai/dsh-harness-trace
Records every session as one readable Markdown timeline inside the session workspace - the full request sent to the model (system prompt and plugin injections included), user input, replies, reasoning, tool calls and results, file reads and writes, web searches, skill loads, command runs and token usage - with a review page, a per-session tab and configurable capture scope.
dsh-workbench-agent-studio
lucky01222/dsh-workbench-agent-studio
Agent Studio for DSH Web: configure models, prompts, per-plugin tool bindings and Skills; trial-run with editable tool results and run history; preserve session capability snapshots; export standalone presets; draft Agents with a guided creator preset.
zagent
z-asset/zagent
Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.
dsh-plugin-agent-collaboration (agent-collaboration)
leo-sail/dsh-plugin-agent-collaboration
Persistent Bots and group rooms inside DSH. Each Bot keeps its own model, permission preset, workspace and session across restarts; a Bot can also be backed by an installed local agent CLI (Codex CLI, Claude Code, ACP agents) using that CLI's own login and models. Unaddressed messages can be triaged by the room leader, the room accumulates a shared experience card, and every answer is a run in a durable ledger the sidebar panel replays. New Bots default to the full-access permission (any command, any file; the form asks you to confirm the risk), so choose read-only or workspace-write to confine one; Codex CLI and Claude Code Bots at full access run without their own sandbox or permission prompts.
dsh-vision-unlock
wmk66ds/dsh-vision-unlock
Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send and read images. No app.asar or config-tree edits.
dsh-quick-translate
wanyi424/dsh-quick-translate
Translate between Chinese and English without leaving DSH, using your configured models with no extra API key: streaming output, a customizable prompt, and local history to revisit and re-translate.
dsh-memory-snapshot
yzx4036/dsh-memory-snapshot
Injects your existing markdown documents (notes, rules, knowledge-base files) into every dsh session's system prompt as read-only memory — list file or directory paths in `files`; no database, no service, no write path; UTF-8 byte-budgeted truncation with line-boundary fallback, total budget, YAML front-matter stripping, and freshness timestamps.
dsh-long-memory
tangcuyu4/dsh-long-memory
Cross-session long-term memory: a hybrid-retrieval memory store (BM25 plus CJK bigrams), chunked long-document search, chat-log extraction and distillation, and context-summary archiving and browsing, with important memories and the latest summaries auto-injected into the prompt.