Plugins

Tool-call discipline for DeepSeek Harness with behavior prompts, failure-driven concurrency reduction and retry guidance, post-write checks with backup rollback, high-risk command gates, change summaries and verification reminders, advisory project-memory checks, configurable project-discipline reminders after compaction or at intervals, and compliance statistics.

Host-neutral durable DAG workflows for Agents with CLI, MCP, on-demand Skills, triggers, replay, and a visual Canvas.

Modular AI research/engineering skill pack, installable via dsh plugin add — registers 27 skills (security audit, paper reading/writing, figure drawing, dev workflow, storage analysis) on ctx.skills.

Map and routing tools: driving/transit/walking/bicycling route planning, geocoding and POI search via free OSM/OSRM data by default, with an optional Amap (高德) key for better China coverage.

Browse and install DSH plugins without leaving the harness: a /store command, a Settings → Plugins tab, two agent-callable tools and a bundled skill, with an approval gate that lists the detected risk flags before anything installs.

Literary DSH plugin: one session is one book. Cover-card /new opens one of 19 realms, a prose-only 诸天万界DSH preset keeps the model writing fiction, keyword worldbook entries ground each turn, and /export-story typesets the session into a Markdown novel.

Database tools for agents: list/query/exec/schema/stats/health across SQLite/MySQL/PostgreSQL, with lexer-grade read-only protection, row caps, CSV/JSON query output and an approval-gated write path.

Codex-style drag-drop: drag any file into the DSH web GUI, it lands in ~/.dsh-dropbox, and the path is inserted into the composer as a whole blue chip.

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

Desktop side of a native Android DSH phone app: scan a QR code to pair, then chat, approve tool calls, answer questions, drive subagents and follow background jobs from the phone over an end-to-end-encrypted channel; one device at a time.

Turns your AI agent application into an interactive workspace for ideation and design, with editable panels, structured knowledge and guided iteration.

Antu diagrams inside DeepSeek Harness: Host tools (antu_validate / antu_layout / antu_render) and an interactive chat card.

Counts agent steps and, every N of them, adds a progress-report instruction to the batch that is about to be sent, so the agent states what it is doing, what it finished and what comes next, then carries on without stopping for you. Interval, prompt text and a main-agent-only default are editable in its settings page.

AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus and apps, set-of-mark screenshots, on-device OCR and verified actions — 11 tools bridged to the macos-cu CLI.

Adds a subagent_codex tool that delegates tasks to the local OpenAI Codex CLI, running the work in an isolated external process.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Embedded MCP server letting external agents (Hermes, Claude Code, etc.) drive DeepSeek Harness over StreamableHTTP: sync/async task execution, a three-tier file sandbox, a Web-backed approval bridge, session management and search, and path-jailed file tools.

Task panel for the DSH Web sidebar: publish tasks, auto-distill related sessions, and drive plan/develop/review stages with subagents plus in-panel acceptance.

Git-style conversation branching that mirrors how real programmers collaborate: a secretary root branch dispatches tasks to child branches with their own contexts, merging back only compressed summaries via squash or rebase; ships /branch commands, a branch tab, branch-to-branch messaging, and a governance baseline pairing each session branch with a git worktree.

Decentralized multi-device fleet: mDNS LAN discovery, key pairing, and SSH direct execution across networks.

Six-player no-limit Texas Hold'em for the dsh Web GUI. One human plays against five LLM agents that each see only their own hole cards. Adds a dedicated tab plus a draggable mini-window over the conversation area, per-browser sessions with CSRF protection, pot-relative raise sizing, three rebuys before elimination, and showdown reveals with board-card deal animations.

Edit the host-wide global instructions (~/.dsh/AGENTS.md) from a dedicated Customize page in Settings - every session on this machine applies them.

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

Playwright MCP browser control for AI agents: drive a real, visible Chrome (navigate/click/type/snapshot + ~80 browser_* tools), with a live screenshot panel embedded in the GUI that refreshes after every action.