Plugins

Claude Code rules.md-style rule prompts: activate rule markdown files by glob-matching the files an agent reads or edits, with prompt injection and ordering support.

Yellow one-line notice for a prompt cache miss after the cache was rebuilt; shows re-billed uncached input tokens, cached hit tokens, and TTFT.

Fridge-magnet quick-task stickers docked above the composer: one-click sends a preloaded prompt into the current session, grouped long-term/short-term.

A green interrupt button beside the send box: silently stops a running agent, which then summarizes its progress and asks for your new requirements, with a customizable interrupt prompt.

DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.

User preference memory for DeepSeek Harness: persisted user profile with memory_get/memory_update tools and system-prompt injection

A model-native meta-agent plugin for DeepSeek Harness: the model synthesizes task-specific workflows at runtime from five agentic workflow patterns (prompt chaining, parallel workers, router, supervisor, evaluation loop) and coordinates tools and subagent

Local, per-session LIFO prompt stash for temporarily setting aside unfinished composer text and safely restoring it later.

Edit user and built-in system-prompt sections with live preview.

Side-by-side model comparison for the DeepSeek Harness Web UI: send one prompt to 2–4 models in sibling sessions forked from the current one, watch the answers stream in columns (tabs on phones) with latency, time to first token, tokens, and cost, then co

Drive DSH from anything that speaks HTTP: 47 routes (REST + SSE) for workspaces, sessions (create/prompt, live SSE generation, history, stats, todos, cancel, ask-user Q&A), models and the global default model, providers, agent presets, settings namespaces, skills, and workspace files including resumable chunked upload — plus an OpenAI-compatible /chat/completions, a built-in OpenAPI 3.0 spec and an interactive request page. It only injects the host webServer and tools, so it rides on the DSH webserver (default prefix /api/v1) or its own port with optional API-key auth, and it ships a skill that teaches the DSH agent to call the API.

Session-aware local notes for DeepSeek Harness: capture notes and page selections in a floating Apple Notes style panel, let the LLM classify topics, auto-inject convention notes into the system prompt, and dispatch todos with recall context to active sessions.

Task-to-skill pairing meta-skill with a laziness ladder for minimal loading, a user-editable routing table, and a quarantine, SkillSpector scan, human-approval install flow.

Adds prompt optimization, cancellation, and undo controls to the DeepSeek Harness composer.

Multi-agent task decomposition, DAG workflow orchestration, and prompt caching optimizer for DeepSeek Harness.

Adds a sparkle button left of the model selector in the composer: it rewrites the draft into a clearer, more complete task brief, replaces it in place with one-click undo, offers five rewrite styles, and greys out while the draft carries file/command chips.

Prompt-polish template injector for DSH: click ✨ in the composer to inject a "polish my prompt" template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context. Replaces narrative-prompt-polish (2026-09-14 migration).

Custom modes and custom prompts for DeepSeek Harness (dsh): edit a mode's system prompt on the settings page (it takes effect on the next model step), choose its base mode, switch plugins row by row, and keep several assistants side by side.

Forwards an unattended DeepSeek Harness run's tool-call approvals and ask_user_question prompts to Feishu cards on your phone. The desktop GUI answers first — a card is only sent after `delaySeconds` (120 by default) with no answer there — and a phone approval grants `allowed-once`, so no authority accumulates on the phone. One outbound WebSocket long connection to Feishu: no public IP, domain, tunnel or relay.

Session-affinity routing for LLM gateways: injects the session ID into every request sent to NewApi-style gateways so the gateway can pin requests per session and raise prompt-cache hits; takes over the official pi-ai routing on install and restores it on uninstall.

Adds a composer button that optimizes the current prompt or designs the next one from the current session and project context.

Conversation enhancements: a history-input overlay (Alt+Up with workspace/session/global/prompt scopes), recall of unapplied interjected messages, conversation forking with fork-family version switching, and optional auto-resend after forking (off by default).

Tool-health sentinel for DSH: cross-session tool success/latency/error history, chronic-failure warning injected into the system prompt, report tool + /tool-health command + GET /dsh-tool-health/summary.

DeepSeek Harness 输入栏「提示词精炼」插件：✨ 一键把模糊草稿改写为目标/背景/步骤/要求/[假设] 结构化提示词；成本可路由（默认模型可换成便宜的优化模型）、结果缓存、token 用量统计落盘。静态版为功能主体，动态版免安装尝鲜。