プラグイン

ファイル表示・編集、ターミナル、Git、サブエージェントを備えたフル機能サイドバーワークベンチ。サードパーティプラグインが新しいタブを登録可能。

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Skill 駆動の harness/ループエンジニアリングワークフローエージェントプラグイン。

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

会話の自動蒸留: バックグラウンドのサブエージェントによる振り返りと Skill の作成/更新。

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.

Live subagent run monitor for the Web UI: a sidebar footer trigger plus a fixed top-right card panel showing each subagent of the current session in real time (running/elapsed, terminal outcomes, tree indent), with one-click jump into the child conversation and a return button, refresh-surviving and mobile-hidden by default.

継続的な自己進化: セッションのトラジェクトリから harness の状態（プロンプト、メモリ、Skill、サブエージェント仕様）をバージョン管理・監査可能・ロールバック安全な形で洗練。レビューゲートとホットリロード対応の Skill を備える。

ロールベースの LLM リトライ&フォールバック戦略。

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Migrate and import a whole Claude Code or Codex setup into DSH. Skills, slash commands, MCP servers, hooks, subagents and permission rules, with a dry-run moving estimate, a migration diff report and a post-move doctor; installs as a plugin exposing a movein_from_claude_code tool so the agent can do the move for you.

Session change-review plugin for DeepSeek Harness: tracks write/edit tool calls per session and renders line-level diffs with customizable colors, with session isolation, subagent aggregation, and SSE live updates.

Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.

設定可能なサブエージェント profile システム: 単一の subagent ツール + profile パラメータ。Web UI 設定/リアルタイム進捗/サブエージェントツリーを含む。

Expert-mode agent preset for DeepSeek Harness (v0.3.0, bilingual EN/ZH): a chief coordinator plus 11 domain-expert subagents with automatic task delegation. Features: Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), expert persistence, cross-expert communication protocol, cross review, and experience pool. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance.

DeepSeek Harness 向けのインタラクティブな長時間バックグラウンドエージェント。任意のセッションから永続的で再開可能な子エージェントを起動し、Web UI のサイドバーで進捗を確認、いつでもメッセージ送信や中断ができます——すべて公式のサブエージェント機構経由です。

セッションのサブエージェントと永続ワークフローの実行状況を、ステータス・ナビゲーション・再起動に強い履歴付きのライブ DAG として表示します。

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Per-subagent LLM provider/model selection with role templates.