Plugins

Document-code consistency guard: audits version headers / changelog tables / directory trees / module & test counts / cross-doc references for drift, with severity-sorted, read-only fix suggestions.

Code smell radar: statically scans TODO/FIXME debt, stub implementations, long lines, oversized files and duplicated blocks, with severity-sorted read-only fix suggestions.

ProactiveAgent × DeepSeek Harness 插件组：主动记忆 + 主动建议接入 DSH（bundle 聚合包，dsh plugin add 一键安装）

A DSH plugin that generates high-EQ reply suggestions based on chat context, with reasoning and strategy.

Email assistant forked from dsh-email with host-side 163 IMAP monitoring that creates DSH conversations for summaries and reply suggestions, manual suggestions for selected messages, and persistent automatic/manual processing records with session links. Includes multi-provider mailbox browsing; automatic monitoring currently supports 163 IMAP only. Install it instead of dsh-email, not alongside (both mount the same tool-email row). It registers no send or draft tools; mail text goes to your configured model and is kept in the session logs; monitoring needs DSH running continuously and a 163 IMAP authorization code.

Ghost-text suggestions in the composer: the message you are most likely to send next after a reply, and a continuation of your draft when you press Tab, including images attached to the composer. Tab accepts, Alt+Down cycles candidates, and the Settings row shows which model route answered. Adapted from Stijnus/dsh-composer-predictions, so do not enable both at once (they share the composer overlay and the Tab key); each suggestion is an extra model call on the Session's model unless you pin another.

Right-click menu inside the message composer: for the word under the cursor it checks a bundled English frequency dictionary of about 30,000 words plus a curated list of 182 common misspellings, and offers corrections ranked by edit distance and then word frequency. The same menu keeps add-to-dictionary, cut, copy, paste, select all, undo and redo. The dictionary and the menu are local, so nothing is sent over the network.

Read-only linter for AGENTS.md, SKILL.md and plugin prompt files that reports conflicting rules, duplicates, vague qualifiers and dangerous commands with file and line suggestions.

Per-turn next-step suggestions under each reply: a 2x2 grid of up to four clickable actions, projected from that turn's own tool result instead of a shared per-session store.

Treemap disk usage map with linked cleanup suggestions, a reviewed trash plan, and an append-only audit log on macOS.

Composer suggestions for the DSH chat input: Up / Down step back and forth through every prompt sent in the current session — read from the session event log, so a message accepted from a prediction or sent by queueing counts too — Ctrl+Up opens a searchable history picker, and grey ghost text predicts the next message, accepted with the Right arrow. Every key only edits the draft; nothing is ever sent automatically.

Predicts the next user message as composer ghost text using the configured DSH model; Tab fills the draft without sending, with time-aware context and cached suggestions.

Implicit session plans with Tab-completable next-message suggestions for DeepSeek Harness

A DeepSeek Harness workbench with model metrics, cost estimates, prompt presets, optional auditing, and context-aware reply suggestions; automatic suggestions default on and may incur API fees.

Drives Proteus 8/9 interactive simulation from the agent through eleven proteus_* tools: connect, simulation start/stop/status, probe readings, a project save that checks the file hash and mtime actually changed, and layout suggestions computed locally; on machines that register the Labcenter.InteractiveSimulation COM server it also places devices from a whitelist and queries and connects pins, while without COM it falls back to a keyboard-driven UI transport covering the simulation lifecycle and saving. Requires Windows with a local Proteus 8/9 installation.

Context-based next-message suggestions and draft rewriting for DeepSeek Harness, with candidate paging, shortcut recording, and companion MCP tools.

Five production-grade DSH tools bundled into one plugin (8 tool slots total): git regression finder (find introducer, recent changes, bisect, blame age), stack-trace decoder with local code context, YAML/ENV/properties config validator with typo suggestions, cross-platform shell escape (POSIX/PowerShell/cmd), and MyBatis Plus SQL static auditor (N+1, missing @Transactional, LIKE leading %, SELECT *, missing WHERE). Zero npm dependencies, all offline; concurrency-safe except the bisect tool (dsh-when-broke). Each sub-plugin is also installable standalone (dsh-when-broke, dsh-stackdecoder, dsh-config-guard, dsh-cmd-shield, dsh-mp-auditor).

Names a session from its first prompt, and streams AI title suggestions into the rename dialog.

Estimates what is filling the context window — per instruction file, per skill and per tool result — with a bloat verdict and actionable suggestions.

Recognizes a model ID in the DeepSeek Harness model catalog and fills that row's context window, input modalities and reasoning levels as editable suggestions, from a bundled offline rule table covering 33 vendors.

Next-step suggestions for the DSH composer: after each completed turn, one auxiliary call on the session's current model returns 3 clickable follow-up suggestions above the input box, and clicking one fills the draft.

Shows token and CNY cost per turn and per session in the harness's own statistics form, a whole-account bill over 1/7/30-day windows with cost-per-unit-of-work trends, and an advisor that re-measures its own suggestions after you adopt them.

A ✨ button left of the send button: reads the draft and recent turns, asks the configured model for three suggestions each pairing an issue with a patch, lets you tick them individually with a live preview of the merged prompt, and writes the result back to the composer without sending.

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.