Plugins

Adds per-Workspace category trees to the Web sidebar, with nested categories, drag-and-drop session assignment, category-scoped session creation, and category deletion that archives contained sessions.

Multi-tenant primitives for DeepSeek Harness (DSH): tenant identity, immutable session ownership, fail-closed authorization, and a replaceable ownership-store contract.

DeepSeek Harness bundle wiring the @forgeax/game MCP server, its bundled ForgeaX Skills, and a workspace guard into a DSH profile.

Adds file and folder drag-and-drop attachments to the Web UI, with composer cards, persistent history, and workspace-backed paths.

Scroll-painting message rail for DeepSeek Harness: a slim right-edge rail with one indicator per user message, scroll-spy follows the reading position, hover unfolds a canvas with full message previews, and clicking jumps to any history message; animates in sync with better-sidebar panels.

Caddy forward_auth administrator login for DeepSeek Harness Web, with Argon2id passwords, revocable sessions, bilingual UI, and a native sidebar sign-out action.

100+ multi platform social-media data skills, plus 40 native MCP tools covering data APIs, AI search and AI generation — all installable with one command.

Exact-profile control of your real logged-in Chrome browser: an MCP server plus MV3 extension and authenticated localhost bridge for tabs, locators, file injection, media export, and durable scroll capture, with no debug profile or remote-debugging port.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Per-workspace Skill and MCP enablement for DeepSeek Harness: control which skills and MCP servers new sessions load, per project.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Codex-style diff review in a floating panel: per-round session changes plus a git workspace view with stage/revert/commit/push and a history timeline.

Codex-style left-gutter tick rail for each user turn, with hover preview and click-to-scroll.

Execution-discipline suite for DSH with identical-retry interception, forced reflection, todo enforcement, memory deduplication, and experience-to-skill promotion (11 plugins + 6 skills).

Session-aware sandbox escalation compatibility plugin for DeepSeek Harness/DSH第三方模型会话沙箱升级兼容插件

Agent Client Protocol (ACP) server plugin for the DeepSeek Harness (dsh) — drive dsh agents from Zed and any ACP client

Structural code intelligence for DeepSeek Harness — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, what a change reaches, and how one symbol reaches another, from a tree-sitter index it builds itself

ICVO coding-standards kit for DeepSeek Harness: a bundle plugin that registers tools on load and injects the standards only when apply_coding_standards is called, plus a P0 gate CLI (npx dsh-coding-kit) with G1-G7 process commands, skills install and IDE-block refresh.

Performance profiling and LLM cache diagnostics for DeepSeek Harness — context engineering, latency profiling, and cache behavior reports.

dsh client bundle: a sidebar usage & cost dashboard — token stats, peak/off-peak aware per-model pricing, membership ladder, achievements and a daily heatmap.

Runs work as a crew of role agents: a product manager writes the PRD or DoD, waits for your confirmation, then starts architect, engineer, QA and reviewers whose tool sets are locked per role, and shares work through files on disk.

Tavily search with multiple API keys, key rotation and failover, a usage gauge, and a settings card.