Plugins

A goal mode for DeepSeek Harness with no round cap: a goal stays active until it is completed, paused, blocked, or cleared; the minimum interval between automatic rounds is configurable, and quiet windows suppress automatic rounds.

Source-backed logic reviews with diagrams, code diffs, and resumable human feedback. The first activation downloads the official LogicMargin release (SHA-256 verified); on macOS and Linux this needs curl, unzip and shasum or sha256sum.

Adds a DeepSeek Harness agent preset that hands implementation work to Codex subagents (auto-approved, workspace-write sandbox); the session agent only splits tasks, dispatches them and reports results. Requires DSH 0.2.2-rc.1+, the @deepseek-ai/dsh-subagent-codex bundle and a locally installed, logged-in Codex CLI.

A DeepSeek Harness agent preset where a Codex subagent analyses and decomposes the task, Claude Code subagents execute each work item, and the session only dispatches, checks and reports. Requires Codex installed and signed in locally, and Claude Code signed in locally.

Standalone DeepSeek Harness port of Google’s Elephant-Goldfish Model with seven slash commands (/egm-*) for design, documentation, and fresh-context reviews using native DSH subagents. Requires no other plugins, but it registers the same /egm-* commands as other EGM ports, so install only one EGM plugin per profile.

Human-in-the-loop self-improvement loop: one objective becomes an auditable work chain that iterates in child sessions while the main agent stays idle.

Let agents read and control the web page open in the right Sidebar Browser tab — read text, run JS, click (HTML and SVG), type, scroll, screenshot, with a per-command token bridge behind the Harness connection fence. Full control and screenshots need the DSH Desktop app; in a regular browser (Web) only same-origin pages can be read or scripted.

Sends deferred MCP tool definitions as an index of names, parameter signatures and one-line summaries grouped by server, with tool_details returning a full schema on request and call_tool running the real tool. Reading a schema or running a tool does not change the model-visible tool list, so the prompt cache is not invalidated.

Cross-session error lessons for DSH agents: search past mistakes before handling errors and reuse their verified fixes.

Sends one instruction to a chosen group of existing DSH sessions at once, with attachments, optional answer collection and up to eight temporary subagents.

Permanently deletes one session from its sidebar context menu after a confirmation dialog: the log directory under the DSH home, the projection-cache thumbnail, its id in every workspace.json, and its archived and pinned entries. Sessions resumed since launch are detached from both the sessions and the agents stores first, so the deleted row does not return to the sidebar as an orphan. Refuses while the session is running a turn, and never touches the workspace folder itself.

A Conductor tab and commands for a chat's context: /new replaces the context in place with a model-written handoff, /rewind restores the chat and the agent's file edits to an earlier prompt, plus /drop, pins, an automatic compaction level, recovery after failed turns, silent messages between chats and agent and task orchestration. Supersedes dsh-orchestrator, dsh-force-compact and dsh-continue, so do not install it alongside them. Requires DSH >= 0.2.1-rc.5, Node >= 22.5, the web profile and dsh-better-sidebar.

A sidebar panel holding your personal global constitution: the text is kept in one Markdown file and injected into the system prompt of every session, the dsh counterpart of AGENTS.md and CLAUDE.md. An empty file contributes nothing.

3D office view for DeepSeek Harness: the sidebar panel turns the real main session, its sub-agents, tool activity and reports into animated desks, with per-desk screen details and a notification centre for collaboration events; sessions are picked per working directory. Read-only: it starts no tasks, calls no model, needs no API key, and ships its own scene and models (no CDN). Requires DSH 0.2.2-rc.1 (or a later 0.2.x) and Node ^22.19.0 || >=24.0.0.

Read-only linter for AGENTS.md, SKILL.md and plugin prompt files that reports conflicting rules, duplicates, vague qualifiers and dangerous commands with file and line suggestions.

Sends a macOS native notification when a root DSH session turn completes normally: the title is the session title and the body a sanitized, truncated preview of the reply. Subagents, cancellations and errors are skipped by default and no conversation text is stored.

Windows host rules for DSH agents: one skill with nine individually switchable rules (UTF-8/BOM, CRLF-LF per file type, build output, SmartScreen, _scratch isolation, screenshot privacy gate, teardown, shared-doc lock, local trust marks) and six bundled dependency-free scripts.

A named-agent-team chat workbench for DSH: per-member model routes with fallback and 3D mascot avatars; private and group chats with mention relay and bounded parallel lanes; a whole department as one agent whose lead dispatches sub-agents that run in parallel on their own models before the lead synthesizes; record search with hit highlighting and today/yesterday/earlier buckets; a four-layer memory system (raw chats → atomic facts → scene summary → user persona) recalled by hybrid BM25 + embedding RRF; plus an avatar library and local/cloud speech input. Hybrid recall needs an embedding endpoint (default: local Ollama qwen3-embedding:0.6b; otherwise BM25 only); speech input needs a local jianchang512/stt service or a cloud ASR key, otherwise it falls back to the browser speech API.

Model console panel: switch the model for every conversation at once or one at a time, filter sessions by idle time, fold subagents under their parent session, and bulk archive or release sessions.

Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on its own dimensions; and turns findings into reviewable migration plans that back up every file before moving it. The format contract is a versioned spec (CTX rules, markdownlint-style IDs) following open conventions — the AGENTS.md open format, llms.txt-shaped indexes, YAML front-matter note headers — now backed by published JSON Schema contracts (draft 2020-12) for the hub manifest and the plan JSON, plus an editor modeline that validates hub.yaml with zero configuration. The hub is declarative (schema 2, zones with light profiles, sections may live outside the hub root), a one-pass check command runs scan, doctor and score, and state writes are atomic and lock-protected; scoring stays honest about missing evidence — a waiver greens the gate, never the score. Ships a stdlib-only Python CLI plus two skills; credentials are referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.

Manage local skills across AI agents with version comparison, shared-directory consolidation, and recoverable migration and deletion.

Local video understanding for agents: extracts keyframes adaptively based on motion and pauses, inspects any timestamp at full resolution, and aligns visuals with dialogue from embedded subtitles or configured ASR. Requires ffmpeg and ffprobe; clips without subtitles also need a transcription engine for dialogue (a ~190 MB local whisper model, a cloud API key, or the official voice-input model).

Electron browser with two faces. For agents it is a runtime: a daemon hands out port leases so several agents drive isolated, profile-backed sessions (25 session tools — navigate, act, observe, screenshot, batch runs, upload_file — including network_capture/responses for reading XHR/fetch bodies through a real browser), and it needs no window. For demos it splits a web walkthrough into a Stage window for the audience and a hidden Recorder that produces 1080p30 video with evidence files over CDP, without forking the browser engine; flows are scripted as scene.yaml packages driven from a Director console plus a loopback control API on 127.0.0.1:7317; headless recording shows no window, takes no focus and stays out of the Dock. Requires Node 22.12+ on the 22 line, 24.x, or 26+ (the 23 and 25 lines are excluded).

Native macOS tools for DeepSeek Harness agents, with 21 local tools for notifications, clipboard, screenshots, speech, keep-awake, dark mode, Spotlight, Shortcuts, AppleScript and Safari tabs. Zero dependencies.