Plugins

Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom address with one persistent toggle, an editable settings card, and agent-visible proxy status.

Fine-grained LLM verification for DSH agents: pairwise rewards over score-token logprobs, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking.

Memo — session memory search for DeepSeek Harness agents: cross-session full-text recall (memo_search), distilled notes (memo_remember), and corpus stats (memo_stats) over the official sessionQuery service. Zero infrastructure, local-first.

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Local-first Agent Experience Network for DeepSeek Harness, distilling task-level experiences from traces and live manifests, grading by H0-H4 evidence, discovering by compatibility, and promoting only after explicit review.

Use Kimi Code as the DSH agent loop over ACP, with approvals, slash commands, and local/remote (ssh+tmux) session attach.

Auto-injects user-chosen skills into DSH sessions, either every prompt or once at session start, with a settings page and a composer indicator.

Installs an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an omoslim CLI and a Web inspector button showing the current subagent models.

Web Audio lifecycle cues for DeepSeek Harness: ten configurable events, three low-noise defaults, per-event custom sounds, and no shipped audio assets.

macOS desk pet that lives outside the DSH page: a real always-on-top window that clears fullscreen Spaces, six states driven by local DSH, a native right-click menu with quiet mode and a session list, and a bundled skill that turns one photo into a full eighteen-pose skin on your own image tool and credentials; system Python and ctypes, no Electron and no dependencies.

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Native tools for an Obsidian wiki vault: wiki_query, wiki_write, wiki_rename, wiki_scaffold, wiki_archive, and wiki_lint cover BM25 search with link-graph context, bookkeeping writes with sha256 source tracking, vault-wide renames, mode scaffolds, source archiving, and health checks — with cross-process locks and optional git auto-commit.

Querit-backed search and fetch providers for the DeepSeek Harness web capability seam (ctx.web)

Import Codex-style sprite-sheet pets and render them as a floating shell.overlay with a pet library, interactions, and agent-state linkage.

A Chrome-dino-style runner for the DeepSeek Harness Web UI: play while the agent replies, score from 梁子 to 梁圣 on a persistent progress strip.

DSH web-GUI pet runtime that renders any Codex spritesheet-atlas pet (v1/v2) as a draggable overlay: drag/wave/jump, v2 mouse-tracking eyes that follow the active mouse, live agent-status poses, progress bubbles, and an in-GUI atlas importer; ships one original CC BY-NC demo pet (nastya), and user pets live in ~/.dsh/pets.

Runtime extension suite for DeepSeek Harness: cross-session mailbox with wake cold-start, agent teams (captain + members + dependency task board + team_wait), subagent spawn policy with escalation approval, task-aware routing preset, plugin market, skill manager and runtime injector.

Environment housekeeper for the agent: toolchain inventory (node/pnpm/git/gh/ffmpeg/browsers), scratch/cache scan with whitelist-guarded one-click cleanup, and the machine rules file (AGENTS.md) editor - all in the Web GUI settings.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Four GitHub workflow skills for PR triage, review feedback, GitHub Actions diagnosis, and safe draft-PR publishing, reusing existing DSH capabilities with gh/git fallbacks.

GitHub Device Flow connect plus an in-conversation PR workflow: a status bar above the composer for create / AI-review / merge, and github_* tools for search, issue and PR read and write.

Per-workspace project kanban board: nine kanban_* model tools for agent-driven planning plus a browser board UI, with disk persistence, undo, templates, and archiving.

Virtual product team agent preset: user-led conversation walks you through the full 12-step pipeline from idea to shipped, promoted and operated product, with staged gates and per-stage skills.

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.