Plugins

中文文本人味化 bundle 插件：强制深层改写工作流（十维叙事审计 + 功能路径 + 15 层分布）+ 内容忠实守卫。编辑辅助，非 AI 检测器。

Runtime-switchable model output styles with Claude Code outputStyles parity, plus the output.render.* presentation protocol: a /style command, per-session persistence, systemPrompt injection, six built-in styles, a web picker, and a renderer registry with per-session/per-tool rules and /export.

Shows DeepSeek balance and estimated daily spend, merges external vision-call JSONL records, and adds a per-session dashboard with model statistics, TTFT, cache rate, call logs, cost estimates, filters, and CSV export.

Common Word Box (常用词盒子) — DeepSeek Harness web client plugin: a persistent slide-up word/phrase panel next to the composer input, with global/current-project buckets and one-click insert. Works in every workspace.

DeepSeek Harness (DSH) plugin: live conversation cost and DeepSeek account balance in the composer stats row — RMB in Chinese UI, USD in English UI

Token cost tracker for DeepSeek Harness -- track usage, calculate costs, budget warnings

11 shareable workflow skills (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait-what, dsh-mode-routing, ask-matt, overnight-execution, full-throttle) as an installable skill pack.

Draggable floating card showing the balance/quota of your most recently used providers (DeepSeek/Moonshot/Kimi For Coding): auto-discovery, color-coded tiers, live refresh.

A minimal greet tool plugin for DeepSeek Harness.

A collapsible/expandable draggable floating music player with NetEase Cloud Music playlist import and song/artist search — chat and listen at the same time.

Meme search, the fun way: describe the vibe, and the agent finds and sends a real meme that actually fits.

Auto chess: human vs AI, or AI vs AI.

Per-model token cost tracking with configurable cache-hit/miss, output and peak-window pricing, a live session cost bar, and unconfigured-model flags.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Support for the nono sandbox backend.

Support for the microsandbox backend.

Redacts supported secret patterns from the `session-telemetry/record` export copy before configured telemetry backends receive it.

Automated unit-test generation: a /testgen command and generate_tests tool that scaffold, run, and fix tests until they pass (LLM + offline template generators; vitest/jest/mocha/node:test).

DSH meets Kimi WebBridge.

Loopback-first multi-agent message relay: HMAC-authenticated broker plus dsh plugin (relay_send/recv/peers/history), zero-dependency CLI and Python clients, wire protocol v1.0.

Two-level model circuit breaker with failover: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback.

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

SHOPLINE AI Toolkit: bridges the official SHOPLINE Developer MCP server and ships seven SHOPLINE agent skills (Admin REST, GraphQL, OAuth, webhooks, Sline) — the SHOPLINE counterpart of the Shopify AI Toolkit.

Dual knowledge-graph RAG for Markdown notes: prerequisite + similarity graphs (P/S-Agent traversal), paragraph chunking, n-gram/embedding hybrid search, and an explicit weight feedback loop — via MCP.