Plugins

Seaglass is a highly customizable glassmorphism theme.

macOS-style skin with a swimming whale aquarium background and a dot-matrix whale send button for the DeepSeek Harness Web GUI.

Local-first personal usage insights in Settings, with 1/7/30-day token heatmaps and a 30-day calendar, token composition, model mix, and skill-call status.

Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra review dimension.

DeepSeek Harness plugin: gzip /api responses for DSH versions before 0.1.2-rc.1 — fixes history loading failures over slow links; DSH 0.1.2-rc.1+ is unsupported

Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-depth panel with a 0-20 capability slider, isolated Velocity/Apex profiles, and offline reasoning toolboxes. Distributed as an obfuscated build; commercial use allowed, reverse engineering closed.

Request-level one-time prompt injection without further context pollution. SillyTavern-style UI and data compatibility, keyword/regex/constant triggers, and a lore_lookup tool for on-demand searching.

DIY你的小蓝鲸吧

为 DeepSeek Harness 提供桃濑日和的动态插件

给每次 AI 对话装一根 Token 保险丝：为每条用户消息设置独立总预算，统一约束输入、缓存、思考与回答。A per-conversation total-token safety fuse for DeepSeek Harness, with a whale slider and automatic reset on the next user message.

Card-style plugin manager in Settings: enable/disable each plugin through the profile patch layer, install-source details, npm update check with one-click update, uninstall, search, and load-error badges.

Installs a Web-profile helper that diagnoses and writes MCP config so Codex, Cursor, or Claude Code can spawn dsh --profile codex.

Pushes DSH approval and question cards to IM channels (WeChat first) and answers them from chat, with a session console, per-channel security, and an open push service.

Irreversible secret-scrubbing guard: rewrites access keys, bearer tokens, and private key blocks into `[REDACTED:<category>]` placeholders before they reach the session log and the model.

Multi-channel notifications for DeepSeek Harness: registers a send_notification tool and a settings page fanning out to NotifyX, WeCom app webhook, WeCom group robot, email (Resend), SMTP, DingTalk, Feishu robot; plus browser notifications and automatic notification on task completion and blocking events.

One-click update for the local DeepSeek Harness checkout — compare versions, pull and rebuild, then restart, and roll back to any past release, all from a sidebar panel with live progress.

Scheduled DeepSeek Harness Agent tasks with mandatory end-to-end tests, run history, and bidirectional delivery through nine messaging channels.

An RTS-style orchestration dashboard where commands replace chats: a resident commander agent decomposes each order into task briefs with acceptance criteria, typed subagent troops (recon/engineer/medic/scribe) execute them across isolated workspaces, and every session is indexed by the order that started it.

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.

Whole-report verification for scientific reports: per-claim checks against Crossref, PubMed (retraction scan), ClinicalTrials.gov, UniProtKB, GEO/SRA and PatentsView, URL accessibility and title agreement, claim-vs-source meaning at temperature 0, and a durable restartable audit ledger with an annotated report.

Council of High Intelligence: assemble an 18-member think tank of historical figures for multi-perspective structured debate, with a live DAG side panel, SQLite run history, and per-project defaults via .council.yaml.

Self-evolving project-level Agent for DeepSeek Harness: 16 SDD workflow skills (clarification, PRD, issue, coding, locating, acceptance, review) plus project memory and knowledge that compound over time.

Cut token cost in 4 layers without cutting model intelligence: handoff, rtk, headroom, caveman token-saving skills — each also available as a standalone installable plugin.

Watches agent execution traces and fires an LLM review at every successful turn end when signals trip, crystallizing reusable workflows into registered skills that improve progressively with later runs.