Multi-lens structural analysis skill: adversarial-first analysis across 16 lenses in 4 categories with 10 structural tools, confidence calibration, and fact-bound layered output.
Plugin marketplace
Explore the full directory and find projects that fit your workflow.

Public repositoryKanban board for DSH: task state machine with git branch isolation, agent auto-execution, and review-driven merge.
Config-driven lifecycle hooks, including context injection: declare event, handler and outcome in YAML, where the handler is an in-harness tool (MCP included), a shell command or an HTTP endpoint, and the outcome is model-visible context, a denied tool call, or fire-and-forget.
Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.
Superself's self CLI as model-facing tools (project context, work units, reports, decisions) plus a /self command — cross-session, cross-project project state kept outside the code repo.
Public repositoryDurable multi-agent collaboration for DeepSeek Harness with channels, threads, tasks, and resumable agent sessions.
Runs Claude Code as a DSH conversation while preserving its native agent loop, tools, skills, hooks, and MCP integrations.
Creates and inspects RecoWork local-agent-project workspaces through two bounded DSH tools and a web workspace card.
Programming Mode agent preset bundle: the standard coding agent with its persona mandating the Superpowers discipline (skills first, brainstorming before building, plans before code, TDD, systematic debugging, verification before completion); ships all fourteen skills bundled.
Connects your GitHub account to DSH agents from the composer GitHub button (OAuth device flow or personal access token) and lets them call the GitHub API through the github_api tool.
Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.
Web Audio lifecycle cues for DeepSeek Harness: ten configurable events, three low-noise defaults, per-event custom sounds, and no shipped audio assets.
Adds an approval-mode toggle next to the permission selector: default approval keeps per-call confirmation, bypass approval auto-approves every tool call while staying in Workspace Write.
Identity-gated Tailscale access to the Web GUI with dsh still bound to loopback: a 127.0.0.1 proxy published by `tailscale serve` admits a request only when the Tailscale login it stamps is allowed, with an optional per-device allowlist, so the privileged /api methods behind the loopback check — Settings, Models, Plugins — answer without dsh being told to trust a remote host.
Public repositoryChat with local DeepSeek Harness agents from iPhone iMessage: switch workspaces/sessions, start new sessions, and get replies in the Messages app — no extra apps, no servers, no cloud.
Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.
Public repositoryA polished floating whale desktop pet for the DeepSeek Harness Web UI with 95 categorized transparent animations, state-aware event reactions, customizable actions and triggers, click interactions, dragging and screen wandering.
Real-time gold board & strategy diagnostics: a draggable floating panel (collapsible to a ball) that pulls CMB gold-accumulation bid/ask prices first, falling back to international gold + FX estimates; includes an independent trading calendar, CMB bilateral history, position/limit & fee references, threshold-crossing alerts (system notification + webhook) and exploratory replay.
机构多因子选股量化研究员 preset(A 股向):把券商/对冲基金的多因子流水线变成纪律感的研究员——覆盖取数因子检验合成组合全流程的方法论知识库,配可复现因子统计的 Rust 确定性核心。社区项目,非 DeepSeek 官方 preset。
Brain-inspired cognitive plugin: episodic / semantic / procedural / emotional memory stores with a reward-ledger and UCB1 bandit loop, a goal stack with time triggers, curiosity-driven autonomous web research, and proactive initiatives. Recalled memories ride along in the prompt to your configured provider; license is source-available, non-commercial.
Connects DSH agents to Busabase knowledge and structured data through MCP, renders records and ChangeRequests in a live inspector, and keeps agent writes behind human review; compatible with DSH 0.1.1-rc.2.