Plugins

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).

Request-side injection and jailbreak plugin for DeepSeek Harness: rewrites only the request copy sent to the model — system-prompt sections, fabricated turns, and keyword or regex replacement — leaving the conversation log and host files untouched; ships unrestricted / nsfw / authority presets, imports the dsh-purge 破甲 prompt as an ordinary preset, enables per agent preset, always-on, or by model and agent preset, and records each injection as a collapsible row in the session.

Per-model working languages: ordered regex rules map model ids to BCP 47 language codes, your prompts are translated into the model's language with DeepSeek Flash before sending and replies are translated back after each turn, with in-place toggles for the original reply and the text actually sent, a system-prompt rule that keeps bridged models in their working language, a warning under the message when translation fails, and no translation or cost when the languages already match.

Academic writing guard (EN/ZH bilingual): removes AI-style defensive writing, protects scientific evidence (numbers, citations, claim strength, null findings, scope) during polishing, and calibrates writing toward a target journal (Journal Profile + Journal Fit). Deterministic local regex/statistics, zero network/LLM; writing_rules / writing_audit / writing_style_profile / writing_journal_profile with auto-audit on paper writes.

Zero-dependency toolkit: time / encoding / json / calculator / csv / regex / markdown / diff / stat / schema — ten deterministic tools in one install.

Zero-dependency tool suite (calculator/csv/diff/encoding/json/markdown/regex/time).

Scopes system-prompt personas by workspace path or session id (exact, prefix, contains, regex), with an optional default persona for sessions nothing claimed, a 人设 tab on the conversation showing the prompt actually sent, import and export of the list, and a switch that refuses tool writes to the persona store.

Type /私 and complete 私家大厨 — Chinese skill names, zero renaming. Patches DSH skill discovery, the / gesture and the skill tool so any Unicode SKILL.md name (私家大厨, 卡路里, 作息管家…) works: slash completion, direct /私家大厨 invocation, model skill({name}) loading. Zero config; runtime changes revert on uninstall, but the regex patch written into three DSH packages on disk stays until the next DSH upgrade replaces those files.

Ctrl+F find-in-session for the conversation, powered by the session store rather than the DOM - labels every hit by source (you / assistant / reasoning / tool call / tool result / system), groups results by turn, merges identical snippets, offers prose-vs-everything scope, regex / case / whole-word options, highlights all matches, and copies or exports the result set as Markdown.

Request-level one-time prompt injection without further context pollution. SillyTavern-style UI and data compatibility, keyword/regex/constant triggers, and a lore_lookup tool for on-demand searching.

Blocks edit/write writes that contain characters matching configurable regex rules, executed before the tool runs, with configurable messages and same-turn pwsh propagation; default rule matches full-width parentheses.

Test/extract/safe-replace/statically explain regexes without executing code.

Parse Chinese e-invoice PDFs (XML attachment first, text-layer regex fallback) into structured JSON with amount cross-check, and generate expense reports (Markdown / xlsx).

Real-compute verification gates: math simplification, logic proofs, regex validation, E-prover FOL, state-machine checks, and code repair, backed by Go-compiled binaries with prebuilt Windows executables.

Right-sidebar file-preview enhancement built on `dsh-better-sidebar` (required — without it the plugin stays inert): a floating find bar for any text file (Ctrl+F, literal or regex, case-sensitive, match counter, next/previous) plus a collapsible Structure panel that lists classes, methods and file-level variables for Java, JavaScript, TypeScript and Python and an element outline for HTML (including .vue/.svelte), with click-to-line jumps. Read-only, no separate tab.

Detect and redact sensitive message text before sending it to models, with local regex, browser BERT, or ZeroClave API detection and manual review.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

MUV engine for DeepSeek Harness: runs the regex_scripts from a character card against model output, tracks variables, renders a status bar, expands macros and LaTeX, and styles tagged code blocks such as letter, terminal, newspaper and phone. Needs dsh-muv-table installed as well, which is its companion plugin.

LLM approval answerer for sandbox escalations beyond workspace-write: a deterministic regex filter first, then a clean-context reviewer model; humans are asked only when it is unsure. Requires the bundled core patches.

Adds four tools that query a local SAG Wiki index through the installed SAG CLI: semantic search, exact or regex match, and index status or update. Needs the SAG CLI on PATH, and semantic search also needs a JEV model configured in SAG; the model chooses which directory to index or drop (default: the session working directory).

Watches the turn endings of the models you select and asks a second model whether the turn was actually finished: if the assistant stopped after text with no tool call, a three-way verdict of continue, finished or uncertain is recorded and shown in a sidebar panel. In suggest mode it only reports; in auto-continue mode it calls agent.followup() once the turn is idle to send a continuation message, up to a per-turn limit. Single-step turns are always rechecked, watched models can be picked exactly or matched by case-insensitive regex, and the resume text is configurable.

Fetches AOSP source snapshots from codeload and searches them on the device with ripgrep through nine tools covering mirror listing, preset bundles, fetch, incremental update, cross-module regex search, a heuristic call-chain trace and line reads, with no git, no root and no build.

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.

DSH plugin: 29 deterministic, offline tools for JSON validation with exact line/column, JSONPath queries, YAML/CSV conversion, text diff, regex capture, encodings, hashes, Unicode, CIDR, JWT structure and timestamps. Every call returns a { result, meta }