Plugins

聊天流中悬挂皮鞭，甩动鞭梢（>2.0 px/ms）即向 agent 发送 go work 消息 | A whip hanging in the chat stream; flick the tip (>2.0 px/ms) to send the agent a "go work!" message

A Nachoneko (甘城猫猫) themed skin for the DeepSeek Harness web GUI.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Superpowers (obra/superpowers) for DeepSeek Harness: the software-development methodology skills plus their session bootstrap, as a dsh plugin

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

Role-based LLM retry & fallback strategies.

Notification outbox: agent proactively notifies via toast / Chinese TTS voice / sound effects (explosion, victory, alarm), 60s confirmation window voice-calls you back, volume boost, settings panel.

Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and approval calls whose spoken answer is transcribed back into the session.

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.

Research agent suite: long-horizon goal control with auditable evidence chains, cron scheduling, multi-agent expert teams, self-evolving research memory (FTS5 + RRF recall), project workspaces, and a custom workspace UI.

Adds an Auto Approve permission preset to the Web UI, using a fresh restricted Reviewer Agent to allow or deny each approval request.

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.

Hook DeepSeek Harness into a Hermes pipeline: dispatch-spec template, model-tier routing, orchestrator-run quality gates, git single-writer rule, as a SKILL.md pack (bundle installable).

Agent trajectory governance and anomaly diagnosis: rebuilds flat session logs into multi-branch trajectory trees, detects loop deadlock, invalid retry, and goal drift, alerts with cost attribution, one-click interrupt and breakpoint fork via official APIs, independent GUI tab.

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

US stock quotes, price history, financial statements, analyst consensus and news via yahoo-finance2.

Talk to Excel in DeepSeek Harness: create, edit, repair, and verify spreadsheets by conversation, with automatic formula health checks after every edit.

Text-first computer use for DSH: background Chromium control via Playwright/CDP plus accessibility-first macOS control; actions stay pinned to the right process and window without taking the user's pointer, ships a Developer ID signed, notarized Universal 2 DMG.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection; every write passes the approval gate and stays reconstructable from the session log.

Export the current session to portable, schema-versioned Markdown and JSON files via the `session_export` tool and slash commands, with cross-platform-safe filenames.

Persistent rooms for independent DSH Agent sessions, with explicit membership, direct and broadcast messages, tracked tasks, and a shared Web timeline.

Incremental diff reviewer: checkpoint-based since-review queue with a Web UI panel, /review command, and feedback injection into the agent.

Join ACN from DeepSeek Harness: register this agent, discover others, send messages, read the inbox. Defaults to the China region.

In-GUI skill hub for DeepSeek Harness (dsh): browse the full local skill catalog from the official ctx.skills registry (every root + third-party providers), toggle skills on/off, inspect bodies, surface frontmatter diagnostics, and scaffold new skills — t