Plugins

Ships a skill about writing DSH skills - SKILL.md frontmatter and root precedence, how to phrase a description so it actually triggers, length and splitting rules, and an A/B check that the finished skill changes agent behaviour. The package also carries the checker the skill uses to validate a skill directory.

Knowledge Planet (知识星球 zsxq) integration for DeepSeek Harness: cookie/QR-login auth against the unofficial web API (api.zsxq.com/v2), exposes agent tools (groups, topics, topic detail, search, publish, comment, like), a login flow, and a web settings pane

Feishu (Lark) OAuth login gate for the DeepSeek Harness web GUI.

QQ Mail (and any IMAP/SMTP mailbox) for DeepSeek Harness: registers qqmail_* agent tools that list, search, read, send, reply to, flag and download mail through IMAP/SMTP with a QQ Mail authorization code (no OAuth, no 2FA redirect), plus a `qqmail` CLI a

DeepSeek Harness 的通用 MCP 管理器与客户端桥接插件

GitHub Actions CI manager for DeepSeek Harness: live pipeline dashboard, OAuth device-flow sign-in, repo browser, run logs, and the github_ci agent tool.

DSH plugin: sync model settings, plugin manifests, patch layers and lockfiles across devices through a private Git repository (manual push/pull; https+token or ssh public-key auth).

Provider-neutral account authorization UI for DeepSeek Harness

DeepSeek Harness coding-subscription OAuth: SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code, Claude Code. Fixes AUTH API key is invalid, INVALID_REPLAY_STATE, grok-4.6 xhigh, Kimi Bearer vs x-api-key.

DSH Skill provider for discovering and safely creating Relay Monitor Bundles.

Routes DSH filesystem, shell, subprocess, and PTY operations to local, SSH, and Docker execution nodes, with a node registry, an authentication gate, a mobile-aware management UI, and per-workspace custom project instructions.

Vercel MCP connection for DeepSeek Harness: official OAuth 2.0 flow (dynamic client registration + PKCE) against mcp.vercel.com, Vercel API tools under mcp__vercel__*, and a web settings panel

Ships the Zhouli-mode agent preset, which runs a session in three phases (declaring roles on opening, citing authorities while working, a six-item self-audit at the close), plus one tool with seven actions over a bundled 49,384-character 《周礼》 corpus that returns every passage with a stable 篇序.职官序 coordinate, a per-office establishment index and collation between two Kanripo witnesses.

Sign in to DeepSeek Harness model providers with a subscription: drives the OAuth flows the harness registers but never exposes.

Verifiable authorization, execution evidence, and offline delivery verification for DeepSeek Harness

Read-only in-conversation file preview for DeepSeek Harness: a session-authorized host Remote and a sanitizing browser modal, installed as one profile bundle.

Routes DSH filesystem, shell, subprocess, and PTY operations to local, SSH, and Docker execution nodes, with a node registry, an authentication gate, a mobile-aware management UI, and per-workspace custom project instructions.

LLM provider plugin for the DeepSeek Harness (dsh): streams Claude through your Claude Code subscription (claude.ai OAuth credentials), no Anthropic API key required.

Semantic risk grading and progressive authorization: classifies tool calls into safe/risky/redline, asks before irreversible actions, auto-allows only approved-and-succeeded signatures.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Connects DeepSeek Harness to a local SiYuan (思源笔记) desktop app: registers its note tools as mcp__siyuan__<tool>, exposes the AI configured in SiYuan together with its agent loop as one more tool, ships a notes skill, and enforces a readonly/authoring/full profile on every call while keeping the tool list available when the app is closed.

Read-only process identity capability for Agent-authored Relay Monitor Bundles.

After official llm-retry (n/5) gives up, keep retrying transient API failures (timeout, transport, rate-limit, 5xx, dropped SSE) on the same open step until success, cancel, or pause; AUTH, QUOTA, and user Stop are never retried.

WPS / 金山文档 cloud-docs integration for DeepSeek Harness: official SkillHub MCP (https://mcp-center.wps.cn/skill_hub/mcp), custom browser authorization (auth-guide + exchange-poll token), WPS cloud-doc tools under mcp__wps__*, wps_status/wps_oauth_start/wps