플러그인

Captures every plan the agent presents through exit_plan_mode as markdown under <workspace>/.dsh/plans, opens a review window, and keeps a Plans history tab recording the outcome of each plan.

Terse prose for DeepSeek Harness — compress the agent's own output so every reply costs fewer tokens (layer 4). Style, never substance.

Folds the DSH skill catalog prompt surface with KV-cache-stable rendering, BM25/bge-m3 hybrid skill search, and optional auto route hints.

Product-thinking companion for DeepSeek Harness: clarifies negative boundaries first, separates facts from assumptions, routes through seven product lenses, and persists confirmed decisions to project memory.

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Serves the obra/superpowers skill catalog to the harness and injects its using-superpowers bootstrap as a persistent, compaction-safe system-prompt section.

Tree-shaped Markdown knowledge base for DSH agents: kb_list/kb_read/kb_write tools, tree/node HTTP routes, and a browser panel companion.

Converts half-width punctuation in AI replies to full-width Chinese punctuation, so copied answers stay publication-ready.

Voice control for the DSH web composer: push-to-talk speech-to-text into the input box (with optional auto-send), spoken playback of assistant replies via the Web Speech API, right-click settings popover, and a global Ctrl+M hotkey.

Injects native-Windows (non-WSL) PowerShell, encoding, filesystem, and cross-platform-build gotchas into the system prompt.

Realtime Avatar (realtimeavatar.ai) for agents: the developer API key held by the harness credentials store, the public docs as five on-demand skills, rta_* tools over the public REST API (balance, avatars, clips, sessions, usage) with approval-gated credit spending, and a /rta command that walks a developer from no key to a live avatar call.

A @-file reference tool for DSH: registers an at_file_read tool that injects workspace-file contents into the session, with traversal protection and a 50KB truncation cap (MIT).

Sidebar button that checks for DSH updates on startup, shows red dot for new versions, supports ignoring specific versions, and displays changelog preview with live download progress and GitHub mirror support for China.

Bridge local projects into Obsidian: bounded manifest scanning, deterministic dependency/tech/topic edges, and wiki-linked notes written into a managed graph/ vault namespace via the Local REST API or the vault filesystem.

Drag-and-drop enhancer for the composer: drop .md/.txt/.markdown to inline small files into the draft or save large ones to .dsh-drop with @-references (Shift forces inline), and drop SKILL.md packages to validate frontmatter and install them to project/user skill roots with one click - effective immediately via the skill watcher.

Cloudflare D1 tools for agents: d1_list/query/exec/schema/stats/health over the D1 HTTP API, read-only by default with a SQLite-accurate lexical guard, LIMIT row cap, CSV/JSON query output and an approval-gated write path.

Runs commands as background jobs that keep executing when DSH exits, with an optional sandbox to constrain file effects, plus a live web panel and offline CLI/GUI management. Windows only for now.

Codex-shaped coding tools and agent presets for GPT models on DeepSeek Harness: exec_command, write_stdin, apply_patch and view_image, plus OpenAI Chat Completions and Responses API routes, bridged to DSH-native plan, ask, approval and compaction. Long-running commands become DSH background jobs with bounded head/tail output readable through job_output, and each subagent type can be pinned to its own preset, provider, model and reasoning effort.

Mine local DSH session logs (JSONL) into personal usage & impact receipts: Markdown day/week/month reports plus a self-contained HTML receipt, cross-referenced with local git log — zero-network, privacy-first.

Native WCAG accessibility scanner: runs axe-core over local HTML files / build output / URLs and reports violations (rule id, impact, WCAG 2.1 mapping, element targeting, fix suggestions) as Markdown/HTML/JSON. Read-only, CI-able.

Single-file persistent companion memory: interests, preferences, tasks, and past works summarized into the system prompt, with read/update tools.

Bridges the agent to a persistent OKF memory vault over MCP stdio: a Python server (SQLite FTS5 + Markdown) with 10 tools for searching and storing decisions, facts, learnings, conventions, profiles and sources.

Session-memory autopilot: watches DSH sessions and extracts OKF entries in-process through the harness LLM (ctx.llm, deepseek-official by default) at idle, commit, compaction and end checkpoints, storing them via the vault MCP server.

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.