Plugins

Registers system-prompt sections that make the model reason in Simplified or Traditional Chinese, with strict/prefer modes and an optional reply-language policy. Adds a /thinking-zh command for per-session switching. Zero runtime dependencies.

Inventory every listening TCP endpoint and grade each holder as agent-spawned, workspace, dev-server, unattributed, system or protected; only the first two can be auto-selected, and a reap previews its descendant-closure plan unless confirmed.

Milestone progress soft-enforcement guard: injects persistent system-prompt rules and post-execute notices when tool calls omit visible progress text, with a Web settings form.

Pins a Chinese (zh-CN) thinking and answering constraint into the system prompt, and registers a per-step runtime reminder so the agent does not drift back to English after tool output. Zero runtime dependencies, single file; falls back to a second registration path and only logs a warning when the host API changes.

Composes tools, skills and MCP servers into switchable per-session sets, shrinking the resident tool surface and the system prompt on demand.

Config-only DeepSeek Harness bundle that mounts the in-box MCP client bridge against CursorTouch/Windows-MCP, excluding PowerShell, FileSystem, Registry, Process and Scrape by default (16 of the 21 tools upstream 0.8.8 publishes). Requires uv on PATH.

System One decision runtime for dsh. Ships fast non-generative tools (choice, score, screen, gate) on a local or hosted System One gateway, and — without the model calling anything — prunes oversized tool output segment by segment, refuses repeated identical calls once System One confirms stagnation, verifies completion claims against real tool evidence, and corrects failing retries. Published on npm as dsh-harness-reflex (plugin) and harness-reflex (core, also a stdio MCP server).

Per-workspace gate that hides the tool schemas and system prompt sections of selected plugins from the model in directories that do not need them.

Write guard for the Akasha Book store: blocks tool calls that write into the memory data directory, and injects the store usage contract and self-layer sections into the system prompt. Companions: Hindsight (repo memory), OpenViking (user memory), and the built-in session search (see repo README). Setup: clone the repo, copy core/ aside, then replace <AKASHA_DIR> in cordis.patch.yml with its absolute path (or set the AKASHA_DIR env var); plugins fail loudly while the placeholder remains.

Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.

Mounts a persona kept in Markdown as a system-prompt section, so editing ~/.dsh/persona/*.md changes how the agent speaks; it reloads 150ms after a save instead of requiring a restart, and project-level .dsh/persona/ files override the global ones.

Gives the model a private glossary: reads 「滚木」 as "none" and 「棍母」 as "doesn't exist", and decides on its own whether to phrase a sentence with those words when expressing that meaning. Registers one system-prompt section and rewrites nothing; word lists ship as per-category YAML (moba/fps/comments/ai/dev/private) with a settings page to toggle files, change reminder strength and open the glossary folder.

Imports SillyTavern AI presets as switchable, editable prompt layers: preserves the raw JSON, edits prompt order and sampler parameters, previews the injected System Prompt, exports back to SillyTavern-compatible JSON, and archives or permanently deletes presets with confirmation. Applies temperature and maximum output tokens to Harness requests; other sampler fields are preserved and exported but not applied.

Sparkle button immediately left of the model selector that rewrites the composer draft into an executable prompt in place, modelled on WorkBuddy: the host calls the conversation LLM with a prompt-engineering system prompt, multi-level undo keeps up to 8 previous drafts, and a token-level diff card shows added and removed spans, the number of changed spots and the net character delta. Runs on the session model, is disabled while the draft is empty, and keeps the browser-session cookie fence in front of the LLM call.

Renders `latex` / `tex` code blocks in the chat as KaTeX formulae, and injects a system-prompt section that tells the model to write `$...$` and `$$...$$` instead of fenced code blocks.

Adds Restart App and Host, Reload Page and Force Quit items to the Windows system tray of the official DSH desktop app by patching app.asar in place, and re-applies that patch after each desktop update.

Live preview inside the sidebar session hover card: what the session is doing right now (running tool with elapsed time, thinking, last tool duration), an attachment thumbnail with click-to-enlarge, the latest user prompt and assistant reply with injected system scaffolding stripped out, a recent-tool icon strip, turn count plus token totals plus model name on one line, and a 12-item settings page (11 switches plus a slider) persisted to the profile.

A file editor in the DSH web GUI right sidebar: open any text file, edit it, and save in place, with a version gate on every save — if the file changed on disk during the edit it stops and asks instead of overwriting. The document preview gains an edit button and a two-step delete button, and a separate File editor sidebar tool brings its own file tree for create, rename or move, copy, cut and paste (including a file taken from the system clipboard), delete and drag to reorganize. Two renderer bands cover 107 plain-text, config and source extensions; the second is offered only as an open-with choice, leaving the shipped Markdown and highlighted-code views as the default. All mutations run through the plugin's own trusted host routes, behind the connection trust fence, the workspace containment check and the sandbox policy.

Adds a restart control at the DSH Web sidebar foot: the host exits through its own graceful path and the detected supervisor (systemd, Kubernetes or Docker) boots the replacement, or the plugin starts one directly when it finds no supervisor; a frame-wide notice polls the host pid until a new process answers.

A DeepSeek Harness plugin that freezes tool declarations to improve prompt cache stability.

A social deduction game played against your own model configurations. A table has N seats (six by default, one of them yours) and some of the rest are played by agents bound to different provider, model, temperature, system prompt and disguise settings; you interrogate them and cross-check the answers to work out which seats are not human. Seat identity and each agent model configuration stay hidden in the host state until a seat is judged, then the disguise parameters are revealed. Every round exports a per-seat conversation JSONL plus the judgment record, and the same seed with the same move script replays byte-identical, so runs with different models or disguise strengths can be diffed.

System-prompt surface drift gate: every section any plugin or preset contributes to the assembled system prompt is hashed and baselined; a silent rewrite of what the model is told fails loud.

Rewrites agent-issued delete commands (PowerShell `Remove-Item` and its aliases, Bash `rm`/`unlink`/`rmdir`, CMD `del`/`erase`/`rd`/`rmdir`) into system recycle-bin operations on Windows, Linux and macOS, best-effort checks scripts for the same operations before they run, and keeps no permanent-delete fallback.

Records every session as one readable Markdown timeline inside the session workspace - the full request sent to the model (system prompt and plugin injections included), user input, replies, reasoning, tool calls and results, file reads and writes, web searches, skill loads, command runs and token usage - with a review page, a per-session tab and configurable capture scope.