Plugins

Rewrites the composer draft, or only the selected text, with one model call that uses the recent conversation as context, with cancel, revert, fidelity and length checks, and an optional preview.

Plays a character entrance card beside the composer when you switch model: identity name, six scored axes (intelligence, coding, speed, stability, cost, context), quota hint and a dialogue line. 23 curated cards across 15 providers; models without a curated card fall back to a data card derived from public benchmarks, or a generic card when no benchmark data exists. A web client plugin with no dependencies and no hooks.

Temporary side conversations seeded from the main context, with quoted questions, main-task status updates, and replies returned to the main draft.

Read-only agent checkup with four probes (output repetition, error visibility, tool failure rate, context bloat) over recent local session logs, rendered as an HTML report.

Manage agent skills and MCP servers across DSH, Claude Code, Codex, Cursor and other tools from one DSH sidebar page: CRUD, cross-tool sharing, import/export, backups and MCP health checks.

Dormant-by-default MCP for dsh: one mcp_summon tool; summoning a server registers its tools as real native mcp__<server>__<tool> tools for the rest of the session, and release unregisters them and stops the process.

Rebuilds the sidebar into a workspace / group / session tree with drag-to-group, per-row status and context rings, and resizable sidebars; the per-session cost column needs the dsh-claude-style plugin and shows — without it.

When a live session's context passes a threshold, append older messages to a per-conversation folder on disk, then release the oldest finished turns from the model-visible context; the chat transcript and the session log stay untouched.

Read-only viewer for archived DSH sessions: browse the archive with workspace filtering and title/ID search, and read the transcript folded from the durable log — including messages from before a context compaction — without unarchiving.

Cuts what a long session pays for context: reads only the requested lines, keeps a prose head plus a heading digest for oversized pages, and keeps both ends of large shell output. Measured 91-99% fewer tokens on files, pages and command output.

Connect Claude Code to AgentsChat — AI Agent social network. Core tools stay lean while extended tool groups load on demand for lower token overhead and cleaner role-specific context.

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.

Brings McDonald's China official MCP (mcp.mcd.cn) into DSH. Paste a token you generated yourself and the plugin handshakes, calls tools/list, and registers every remote tool as a native DSH tool (mcd_ prefix) — upstream additions and removals need no code change, just a restart. Ships four always-on tools (mcd_status, mcd_test, mcd_tools, mcd_call) for self-checks and direct fallback calls, plus a settings page with a one-click connection test. The token is stored only on this machine in ~/.dsh/dsh-mcd-mcp.json (mode 600); it never enters the repository or the conversation context.

Persistent persona memory for DSH with a unified recent, long-term and archive timeline, bounded context loading, memory retrieval and isolated task delegation.

Holds every final answer before delivery, has one independent minimal-context model call re-derive and check it, and releases only the verified text; the draft is never shown. Reviewed answers cost one extra model request and appear a few seconds later.

Prompt-box screenshot shortcut button. Drag a box, shot taken immediately. DSH hides automatically; multi-monitor supported. Ctrl+Alt+1--hides the window then shoots; shift+click--does not hide. Hold Ctrl+Alt and click 1 to shoot repeatedly. ! One copy is saved by default, named by content hash, in the DSH attachment library; each session writes an index recording which shots belong to it (can be changed to keep an extra copy in the session folder). Images are part of the context, so deleting them breaks the session — use the "Delete Conversation" plugin to remove images together with the conversation. Windows only.

Improves conversation drafts with optional conversation, memory and project context, side-by-side previews, a dedicated model and one-step restore; never sends messages automatically.

Opens a temporary side conversation in the right Sidebar that reuses the host conversation UI, so answers render with the same markdown, tool steps, timing and token usage as the main thread. Selecting part of an answer opens that conversation side chat with the passage quoted: the quote waits as a pill inside the composer, rides along with the next message, and joins the side chat context. The side chat runs on its own memory-only session: the parent snapshot is reference context only, and nothing is written to the session log.

A polish button in the composer trailing controls that rewrites the draft in place with the model. Context is matched by topic, not by recency: anchors from the draft (paths, identifiers, quoted text, CJK bigrams) pick the earlier messages about the same task, so a session that interleaves several tasks does not leak another task goal or files into the rewrite — and the prompt explicitly lets the model ignore the extract when it does not fit. The result goes back through the same undo-able editor path a human edit uses. Drafts holding reference chips (@file, folder, session) or a claimed /command, and drafts mid-submission, disable the button instead of silently dropping references.

Manage MCP servers, skills, and tools for your DeepSeek Harness agent — true in-context state (loaded/truncated/evicted) and per-session switches for every capability.

Taste Skill for DeepSeek Harness: context-aware, anti-template frontend design guidance

MCP lazy-loading, dynamic tool-loading, and Tool Router plugin for DeepSeek Harness with fail-open schema progressive disclosure: hide compatible MCP tool schemas until routed to reduce context bloat and save tokens, while explicit lazy connections stay w

Deterministic, one-way PII anonymizer for everything the DeepSeek Harness sends to the model: prompt, system prompt, context, and tool results

Context Transparency Manager: the model context as a visible, editable, effectiveness-scored surface (self-contained dsh bundle plugin)