Plugins

“What should we build next?” There’s a skill for that.

Git-native, auditable long-term memory for AI agents

Visual channel configuration UI for DeepSeek Harness (feishu / imessage / telegram / ...)

Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容，同一字符串重复十次以上立即停止生成。

Expert market for DeepSeek Harness: WorkBuddy expert/expert-team system ported onto native agent presets, 425-expert catalog installed on demand, capability subtraction, and team delegation tools.

A visual plugin marketplace for DSH: browse multiple Git sources, install plugins with one click, and wire skills, subagents, MCP connectors, LSP servers and hooks into the harness automatically.

Global prompt-injection / context-virus defense for DeepSeek Harness: scans tool arguments, tool results, pre-model messages and the outbound stream; quarantine/block/monitor modes, canary trap, and an evolvable on-disk signature library with learn/import/export.

Mandatory cross-review for design proposals and lessons-learned: auto-detects design doc writes and enqueues them (tier=review) into the task queue, delivers the external reviewer verdict back to the initiating session, and appends approved preventive measures to OPS-GUARDRAILS.md (append-only, conflict-checked).

Browser notification plugin for DeepSeek Harness - system toasts when a task finishes, a run errors, or your input is needed (question / approval / plan review), click to open the session, per-type toggles, and no false 'done' while the main session waits on its subagents.

Background notification plugin: desktop notification, with a tab-title fallback, when an approval prompt or an ask-user-question card appears while the page is in a background tab. The host queues approval and question events behind a same-origin endpoint that the client polls every 3 seconds; clicking the notification focuses the page, and the tab title is restored once the page becomes visible.

Real Windows OS toasts for DeepSeek Harness: task-finished, needs-input and needs-approval alerts that persist in Notification Center under DeepSeek branding. Windows-only, zero runtime dependencies.

Evidence-first GitHub research subagent with bounded tools and in-memory request caching.

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to project .dsh/skills with human confirm and deterministic rollback.

External Agent control plane for Codex, Claude Code, Cursor Agent, and Antigravity adapters with settings and background job visibility.

Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.

Screenshot-review skill for DeepSeek Harness: the agent opens a frontend page, screenshots it, views the screenshot itself, revises the code, then re-screenshots — iterating until the page visually matches the user's requirements. Ships as a dsh.bundle, so it installs with `dsh plugin add`.

Lists WSL distros and validates a Linux workspace path for DSH.

Hints how to forward the Windows OpenSSH agent into WSL without dumping keys.

Browse WSL directories under / and /mnt for workspace picking (start/filter; im-workspace shortcuts).

Warns when the workspace path sits on slow /mnt/c.

Probes Windows-host Ollama, LM Studio, vLLM, and llama-server from WSL, compares ctx, and reports /v1/models apiReady versus TCP.

Reports PowerShell, cmd, and LANG encoding for UTF-8 versus code-page issues.

Lists or copies files from the Windows Downloads folder into the WSL workspace.

Reports Docker CLI, context, and daemon reachability in WSL, plus vLLM :8000 /v1/models health and GPU runtime hints.