플러그인

Tiered task queue as the single source of truth for DSH↔Hermes work (reset > approve > review): enqueue tools for all submission paths, lease/claim model with concurrency 1, priority aging against starvation, atomic busy mutex, and a Hermes-side consumer (cron */1 + monitor gating) that drains tasks, writes review-handoff requests with single-slot checks, and invokes the reset agent.

Mandatory cross-review for design proposals and lessons-learned: auto-detects design doc writes and enqueues them (tier=review) into the task queue, delivers the external reviewer verdict back to the initiating session, and appends approved preventive measures to OPS-GUARDRAILS.md (append-only, conflict-checked).

Turns a product or UI request into an implementation-ready design spec with /ui-workflow and /ui-rerun. Analysts run through a read-only ui_analyst tool, and the lead agent writes docs/ui-workflow reports.

Claude Code style /init command and tool that writes a minimal CLAUDE.md and symlinks AGENTS.md to it.

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

Sidebar disk browser for DeepSeek Harness - browse any folder on the server (including hidden ones) with text preview, streaming download and upload (multi-select / drag-and-drop, overwrite confirm), responsive on desktop and mobile.

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.

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.

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.

Adds a handoff button to every assistant message that writes an LLM-summarized handoff document of the current conversation into the workspace handoff/ directory.

Dreaming for agents: replay recent conversations between sessions (dream_digest), reflect and write a dream journal (dream_save/journal/recall), and idempotently bridge recurring lessons into AGENTS.md (dream_bridge). Reads multi-frame zstd session archives with privacy masking on by default; six tools including a health self-check; zero runtime dependencies.

Session change-review for DeepSeek Harness: tracks write/edit tool calls and renders VS Code-style side-by-side diffs via diff2html, auto-following the theme, with subagent aggregation and one-click revert.

In-session "Files" tab (conversation.view, order 20) for dsh Web that browses the active session's workspace directory with breadcrumbs and previews files inline — sanitized Markdown (marked + DOMPurify), images, line-numbered text and PDF — served by read-only /dsh-files host routes registered on ctx.webServer; no write endpoints. Bilingual zh/en.

Knowledge base (Vault memory + knowledge graph) for dsh: kb__* tools for deterministic memory search/write, knowledge-graph nodes/edges/subgraph/traversal, document-to-graph ingestion and unified cross-store query (KAL) - no web-search tools.

Analyze the current branch diff and generate a Conventional Commits PR title, motivation/scheme/testing/risk description and a self-review checklist, write PR_DESCRIPTION.md, optionally open the PR via gh.

Prompt optimizer for DeepSeek Harness: a composer tool-row button that rewrites the draft into a structured prompt via the session's selected model, with one-click restore

FS-shaped internal URL schemes (conflict://, pr://, issue://, …) resolved through one registry behind the read/grep/write tools — a standalone service plugin for DeepSeek Harness with no upstream harness changes required.

Role-based plugin recommender for DSH: asks the user's role (developer, designer, writer, researcher, ops, student...), recommends suitable plugins, and audits each with a local static security scan (dangerous code patterns + 0-100 risk score) and a reputation check (npm downloads / GitHub stars).

WikiPali Pali corpus research & write skills for DeepSeek Harness (dsh): pali-research + pali-write skill providers backed by the upstream wikipali CLI.

Lets the AI insert streaming-generated UI into the conversation or a side panel, written in TSX — already one of the model's native languages, so there is no JSON schema to teach it. Rendered without flicker, state kept across frames with no hard remount, and a click in the card driving the next chat turn. Inline is where streaming matters most; the side Canvas is the more agentic shape. Cards get agentic capabilities of their own — run bash, curl, call the model, read and write files.

Task dispatcher for DeepSeek Harness: use TickTick (滴答清单) 5️⃣AI as the daily task dispatcher — a cordis timer pulls today's due tasks each morning, writes them to the workspace task file, and notifies (flomo + macOS) so the agent works through them and wr

Display-layer text replacement for DSH chat messages: rewrite how any configured text appears on screen without touching the real conversation, with per-rule whole-word matching and code-block protection.

Percent-progress scoreboard docked below the todo pill: tracking_write rows with evidence-bound percents, host-captured git checkpoints with before/after deltas, and pursue/align/dismiss actions that reach the agent as instructions.

DeepSeek Harness 基础工具增强：持久 bash、结构化 read、多模式 edit、原子 write、双引擎 grep/glob、图像直读，一个插件全覆盖