Plugins

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.

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.

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-model proxy routing for LLM requests: selected models go through a proxy (Clash etc.) while the rest stay direct, with automatic retry on transport errors, 429 and 5xx, configured live from the settings page.

Real-time DeepSeek account balance badge in the sidebar footer with odometer roll animation, multi-currency support, balance trend chart, per-key usage statistics with historical backfill, and GitHub version auto-check.

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

Replaces the Web GUI trajectory tab with a new-user-friendly round-by-round storyline, plain-language tool labels, category filters and fuzzy search.

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.

Compact Codex coding mode for DSH: light prompt guardrails against GPT over-explaining, with an editable prompt and native Codex-style tools.

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.

SSH remote-execution plugin for DeepSeek Harness — ProxyJump chain, SFTP filesystem, subprocess and PTY over ssh2

Browse and install DSH plugins without leaving the harness: a /store command, a Settings → Plugins tab, two agent-callable tools and a bundled skill, with an approval gate that lists the detected risk flags before anything installs.