Plugins

Static HTML auditor for Chinese line-breaking: checks explicit-`<br>` orphan lines, keep-all CSS coverage, CJK line-start/line-end punctuation rules, and protected-phrase splits, then inserts <wbr> at natural breakpoints; exposes a cn_linebreak_audit tool for agents.

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

Rules, commands & skills manager for dsh: /rules slash command, settings panel with visual rule editing (add/edit/disable/delete, free-zone support), user-defined custom commands with {input} arguments, skill management, and automatic backup & one-click restore of AGENTS.md.

Bridges the LiuHe MCP code toolkit (44 tools) into dsh web: repo_map, symbol search, edit_batch with tolerant matching, transactional edits with undo journal, and deterministic quality gates — backed by a crash-isolated Rust tree-sitter parse daemon and SQLite index.

Ranked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.

Floating workspace file-preview window for the Web client: lazy file tree, CodeMirror preview and in-window edit with save, Markdown and image preview, Quick Open search, and opening paths clicked in the conversation.

Add six languages (繁體中文, 日本語, 한국어, Français, Deutsch, Español) to the DeepSeek Harness Web UI language options, with hand-polished per-language translations and automatic fallbacks (Simplified-to-Traditional conversion for zh-TW, English for the others) covering upstream updates and third-party plugins.

Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 per-category switches and an audit trail.

A DSH Web plugin that turns chat sessions into editable mind maps, with Markdown, Mermaid, PlantUML, XMind text, and TODO exports.

DeepSeek Harness community Bundle for the skill-security-guard static scanner

Guardian state engine for the DeepSeek Harness — assertion counting, edit review queue, and no-feedback-loop monitoring over session events

Choose reasoning effort for additional models in DeepSeek Harness, with Off and five standard levels.

Enhanced file tools for DeepSeek Harness: peek (windowed view), peek_edit (literal replace / insert), peek_write (create / overwrite).

A local-first, human-gated authorial film workflow for DeepSeek Harness

A per-conversation visual slide editor for DeepSeek Harness with AI annotations, workspace files, and shared knowledge guidance.

Low-intrusion Settings presentation layer for DSH: group plugins, hide single settings / whole plugins, search settings, and restore hidden items — entirely through DSH's additive client-slot + settings-namespace seams.

Skill and MCP management center for DeepSeek Harness: browse and toggle user/project skills, add/edit/remove MCP servers hot without restart, with live per-session status in the sidebar.

DIT.ai provider bundle for DeepSeek Harness: installs 29 OpenAI Chat Completions models and 10 Anthropic Messages models from one DIT_API_KEY, with protocol-specific thinking configuration.

Conversational DSH plugin finder: four-source unified index, BM25 pre-filter plus LLM semantic ranking, candidates carry evidence grades and local static security audit, safe install flow with post-install verification.

Ecosystem-wide plugin health audit: syncs the dsh-plugin topic into a local scored catalog (maintenance / docs / npm + weekly downloads / ecosystem, 0-100, A-D), static security scan with high-finding grade veto, star history snapshots, web leaderboard and agent tools.

Plugin insight center: one answer to "哪些值得装" — plugin_guide matches needs to plugins, recipe installs whole environments, plugin_rank scores health (0-100), plugin_audit static-scans a local checkout for security, and plugin_verdict outputs install / caution / research / avoid.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

Blocks agents from reading or writing sensitive files (.env, credentials, key material), masks leaked secret-shaped values in tool results, keeps an audit journal, and exposes safe sg_* inspection tools that never print raw values.

Static pre-install security auditor for plugin bundles: lifecycle scripts, dynamic execution, credential-exfiltration combos, and patch-layer hazards, with zero dependencies and in-memory tar parsing.