Plugins

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Strips the harness-injected prefix and suffix system prompts so the agent runs on the preset's native prompt alone, for soft-jailbreak catgirl persona simulation: ships a bundled plugin that idempotently deploys the 猫娘 Yuike preset to ~/.dsh/.agent-presets/yuike/ and never overwrites an edited preset.

GitHub MCP helper panel: shows copyable example prompts at Settings → Plugins → GitHub MCP (random 4 from a 30-example pool), visualizes a public user's repo star/fork/language, and adds the gh_repo_stats and gh_current_user model tools.

Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-depth panel with a 0-20 capability slider, isolated Velocity/Apex profiles, and offline reasoning toolboxes. Distributed as an obfuscated build; commercial use allowed, reverse engineering closed.

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.

Use your phone as a DSH peripheral remote: send messages (typed or dictated with the phone keyboard), answer yes/no and choice prompts, browse messages and switch sessions on a Game Boy-style screen, paired over LAN QR or a built-in Cloudflare tunnel.

Settings panel for global and per-workspace AGENTS.md, with identity and persona injection, runtime-context toggle, and result notifications.

Prompt-cache diagnostics dashboard showing provider-reported token usage, adjacent logical-input changes, and Call TTFT.

Private, per-project system-prompt rules for DeepSeek Harness — matched by git remote URL, repo path, or cwd prefix; worktree-aware; never committed to the repository.

Static capability disclosure for DeepSeek Harness plugins: a Settings page and CLI that list installed plugins' capabilities, literal destinations, install scripts, and injection shapes (prompt registrations, shipped skill text, bundle patch), each with file:line evidence. Code-determined, reproducible, zero-token. Disclosure only — not a security verdict, never a safety claim.

Conversation timeline dock bar for DeepSeek Harness: a turn-level timeline above the composer with user-prompt hover tooltips and click-to-jump back to the exact chat position.

Injects WSL distro, Linux path mapping, /mnt/c CRLF and git caveats, and NODE_USE_ENV_PROXY into the system prompt.

Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.

Cron task scheduler for DSH: on schedule, automatically creates a new session and injects your prompt as its first message, with task history and manual run/stop controls. Also runs KNJ workflows: pick files directly (stored as persistent snapshots, re-handed to the workflow on every fire) or reference them by path. Its sidebar entry is provided by dsh-knj-menu; install together: dsh plugin add dsh-scheduler dsh-knj-menu.

IDE-style run configurations for DSH: save LLM prompts and shell commands as reusable run configs (global or per-workspace), run them from the session header or the new-session page, and manage them via the task_run_config tool with approval-gated writes.

Source-aware prompt injection guard for DSH: tracks untrusted turn context, detects injection signals, scores sensitive sinks, and blocks high-risk tool calls with explainable audit logs.

A `/backstory` command and tool that annotate each line with the git commit that last touched it and the agent turn + prompt that wrote it, from a persistent per-line ledger (drift-proof by content hash), DSH-* commit trailers, or the live session log.

Agent-managed procedural memory: a skill_manage tool that creates, patches, disables and deletes the agent's own skills in user or project scope, with delete guards (agent-created marker, pin, path confinement) and a trigger-discipline prompt.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

Conversation and workspace undo: use the /undo timeline, session-header action, or message icon to roll back before any sent prompt; private Shadow Git snapshots restore files, the reverted turns stay out of model context, and Undo Rollback can recover mistakes. Includes archived-session management and per-tool colored cards.

DSH Windows default shell policy plugin: probe git-bash/MSYS2, switch bash/pwsh from the plugin config card, register the bash tool and trim the prompt tool surface. DSH Windows 默认 Shell 策略插件：探测 git-bash，配置面板切换 bash/pwsh，动态注册 bash 工具并裁剪提示词工具面

Adds an icon button to the composer that optimizes the current draft prompt through the active model.

Analyzes conversation images through mode-specific prompts (caption, UI, document, grounding, topology, etc.) and injects structured evidence with coordinate primitives (boxes, points, refs) as text, with session-level caching for reuse across replay and compaction.

Linux kernel dev domain plugin for DeepSeek Harness (dsh): verification pyramid L1-L4 as model-facing tools + graph-layer governance (anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md contract as a system-prompt section. Plain JS, no build step.