Plugins

Codex-style `@file` mentions: search workspace files in the composer and attach their contents to prompts.

Codex-style `@file` mentions: search workspace files in the composer and attach their contents to prompts.

Evolve skills, agents, prompts, code and plugins from inside DeepSeek Harness, with AgentDescent.

Pi Host ABI compatibility engine: after one install, unmodified Pi extensions from npm mount as native DSH plugins with `dsh plugin add <pi-package>`. Verified end to end on stock DSH with pi-mcp-adapter (full MCP manager: OAuth, resources, prompts, MCP Apps, elicitation, sampling), @tintinweb/pi-subagents, pi-code, pi-hermes-memory and pi-background-tasks; `pi2dsh inspect` reports a package's compatibility before installing.

Red-team engagement mode: send one target organization name and a planner session runs a five-role execution team (recon, asset triage, vulnerability discovery, exploitation, internal pivot) under a user-configurable concurrency limit (three by default, changed from the console and taking effect immediately), preflight-checking skills and resources and asking once for any missing key or VPS first, guided by a built-in first-run onboarding skill; scoring follows the merged intrusion scoring rules (8 categories / 25 points) with server-side caps, highest-privilege-wins and per-service dedup, and self-registered accounts never score — a login that fits no more specific category is scored as controlling a web application system rather than dropped; findings land in a local SQLite fact base with discovery timestamps, shown in a persistent right-side console of 9 tabs (asset mapping with a discovery timeline and the live test view, the agent roster with its concurrency setting and editable role prompts, session/tunnel state, findings — vulnerabilities, credentials and access sessions plus the attack files archived against each vulnerability — five-stage attack chain, scoring targets, an evidence-screenshot capability (register a screenshot per score point, at most three representative shots per point so a bulk result such as dozens of endpoints does not flood the console or the report, viewed inline in the console and embedded in the report, with on-site screenshots kept strictly apart from record-generated evidence cards), and a report that spells out how each score was obtained (actions, exact commands, credential provenance, tunnel build commands, a reproduction entry that is either a paste-ready HTTP request or a runnable command, plus success criteria and an evidence index), a category-organised POC/EXP knowledge base, and a skill library that reports for every unusable skill why it is unusable and the concrete steps to repair it); ships 14 reconnaissance/assessment skills (the npm package deliberately carries no tool auto-installer and no attack-chain skills — those ship as a separate toolkit Release attachment that the operator fetches and runs themselves), 56 redteam_* tools and one-command self-update.

DeepSeek Harness 提示词市场插件：对话框内一键浏览、搜索、收藏提示词，选中即写入输入框。零后端、免构建、数据只存本机。 | A prompt marketplace for DSH: browse, search and insert prompts straight into the composer.

Notifications for four session states, with browser alerts and prompts.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

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.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

Idle session reminder: prompts to archive sessions untouched for N hours, with a snooze window after each refusal, using the official archiveSession API.

Bridge Claude Code's .claude/ directories into DSH with zero migration: project and user-level skills, commands, rules (one system-reminder envelope), agent files, hooks (PreToolUse/PostToolUse/UserPromptSubmit/ SessionStart/SessionEnd) and .mcp.json servers, plus Claude Code plugin marketplaces. Ships /cc-plugin for full plugin/marketplace management (claude CLI first, self-implemented fallback), /cc-resume to list and import Claude Code sessions into DSH as native event-sourced logs, and /cc-export to write DSH skills back as Claude Code skills. Two-way Claude Code <-> DSH bridge, versioned and released as dsh-claude-compat.

Generate complete AI songs and BGM from prompts or lyrics, with reference-audio creation and song extension.

Adds an Execution graph conversation-view tab that renders each turn's prompts, replies, and tool calls/results as a foldable timeline with a detail panel and PNG export.

Skill pool manager in the Settings sidebar: enable/disable, folder batch import with rename-conflict prompts, state-driven one-click DSH-spec check & auto-fix, system/project scope labels.

From chat to canvas to artwork — drive ComfyUI as a visual workflow IDE inside DSH. Embed ComfyUI (local or cloud) as a split-screen canvas in DeepSeek Harness Web: the agent sparks ideas, writes prompts and scripts right in the chat, applies them live to the canvas in front of you, and produces images, music, video, and 3D. From idea to finished output without ever leaving the conversation or switching front-ends: Canvas ops — compose and arrange pipelines, read/write workflows, edit nodes, wire links, run, tune parameters, and debug errors, all live and WYSIWYG on the exact canvas you are looking at; Production tasks — batch parameter sweeps (batch_run) and automatic output-image retrieval back into the chat (get_outputs), powering multi-modal creative and batch generation across images, music, video, and 3D; Environment upkeep — one-click launch of ComfyUI and one-click upgrade of the core plus every custom node (upgrade), keeping the stack healthy without interruption. This package is the DSH-side plugin, and it ships the ComfyUI-side bridge node too.

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

An opencode-inspired terminal UI for DeepSeek Harness that boots as a dsh profile app plugin, with a session sidebar, streaming chat, markdown tool cards, todo lists, slash-command suggestions, a telemetry footer with a context meter and inline approval prompts.

Composer input toolkit: arrow-key session history (first/last-line gated, IME and command-menu safe), an instructions viewer/editor for global and project AGENTS.md/CLAUDE.md, and a prompt library of 780 Chinese prompts (Cherry Studio agents-zh corpus, AGPL-3.0) inserted into the composer in one click. Ships on npm as `dsh-composer-tools`.

Web GUI convenience suite with appearance controls, timeline navigation, project folders, prompts, conversation export, Mermaid rendering, quote reply, and DeepSeek balance and daily token usage.

Per-project scheduled prompts run as fresh headless agent sessions, with one-time, interval, and cron schedules plus durable run history.

Browser-local prompt library with a composer picker for injecting multiple session-scoped system prompts, branch inheritance, bilingual UI, favorites, and JSON backups.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.