プラグイン

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

loci second-brain sidebar tab: hybrid search, cited Q&A, day-grouped memory browsing and quick capture over a local loci knowledge base; proxies `loci serve-http` same-origin from dsh-better-sidebar, no core fork.

Windows-native computer use for DeepSeek Harness: two tools drive and read any desktop app. One batch call runs find, click, type, key, read, wait and screenshot steps in a single engine pass, so a task whose steps are known up front costs one model round trip; reading returns window text rather than an image, and input and capture prefer UI Automation patterns, Win32 messages and offscreen PrintWindow so the user's focus and pointer stay untouched.

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.

Agent screen capture on macOS and Windows: one tool captures the screen and returns the image itself, so the model sees it without a second call. On Windows a whole burst runs in one engine call; on macOS a resident helper drops a region capture to 13ms and a change check to 23ms. A second tool, macOS only, reports whether Screen Recording is granted and opens the settings pane that fixes it.

System-audio visualizer for the turn navigator rail: the rail reacts in real time to whatever the default playback device is rendering, with four motion modes (spectrum, pulse, sway, travelling wave), a 16-band logarithmic spectrum from a 2048-point FFT on the host, and live sensitivity, strength, bass-punch and wave-speed controls. Audio is captured host-side through WASAPI loopback, so there is no permission prompt, no microphone and no screen capture. The browser half adds one attribute, one stylesheet, some CSS variables and a sidebar control row, and never patches the official component; switching it off removes the attribute, the stylesheet and the variables, returning the rail to its default styling. Windows only.

Durable plans for DeepSeek Harness (dsh) — captures every exit_plan_mode plan to <workspace>/.dsh/plans as markdown, opens a review window when one is presented, and keeps the history

Embeds external AI chat sites in a DSH side panel through the same-origin reverse proxy with per-site DOM adapters, and adds a composer button that either rewrites the draft with the host model or runs a two-round loop: compress the conversation, optimize, send to the embedded site, capture the reply, then finalize it into the composer.

Web UI for capturing and reviewing raw LLM requests, streamed responses, token usage and tool calls.

WeChat-style in-app screenshot button: drag a region, fine-tune with 8 resize handles, Enter to capture and Esc to cancel; auto-numbered PNGs plus a \[Shot N HH:mm] marker written into the composer. Windows-only, tested on DeepSeek Harness Desktop.

Makes ctx.logger output visible: a /logs chat command over a full-capture ring (level, name, grep, since filters) plus a default-on stderr exporter for warnings and errors, configurable per plugin; works headless. Also documents that dsh's default log buffer silently drops warn and debug records.

Per-workspace custom system prompts for DeepSeek Harness (DSH): set one active prompt per workspace, captured into a session at creation time, editable from a session-header dialog. 给 DeepSeek Harness 的「工作区自定义提示词」插件：每个工作区一条生效提示词，新建会话时固化注入，会话头部弹窗增删改查。

Captures every plan the agent presents through exit_plan_mode as markdown under <workspace>/.dsh/plans, opens a review window, and keeps a Plans history tab recording the outcome of each plan.

Percent-progress scoreboard docked below the todo pill: tracking_write rows with evidence-bound percents, host-captured git checkpoints with before/after deltas, and pursue/align/dismiss actions that reach the agent as instructions.

One-shot DSH skill (SKILL.md) generator: capture intent, draft, validate, package and distribute skills from inside a DeepSeek Harness session (skill_new / skill_validate / skill_package / skill_improve_description).

Per-workspace memo/todo panel that auto-captures queued and running user instructions, marks preempted tasks as interrupted, and restores them to their previous state with one click.

Agentic git plumbing for DeepSeek Harness: the host ctx.git service (diff capture/parsing, hunk staging, commit/push/log over the subprocess seam) backing the commit and review tools in @hy-sde-org/dsh-tool-git — a standalone plugin with no upstream harne

Percent-progress scoreboard docked below the todo pill: tracking_write rows with evidence-bound percents, host-captured git checkpoints with before/after deltas, and pursue/align/dismiss actions that reach the agent as instructions.

Desktop-grade DeepSeek Harness plugin: native notifications for user questions/approvals, a floating attention HUD, a screen-capture tool, and a multi-agent tiling canvas.

Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.

Git development workbench for DeepSeek Harness: captures branch, status, worktrees, stashes and recent commits, with commands, tools and a settings UI.

Desktop (native) control for dsh as a stdio JSON-RPC bridge over a Python core: capture the screen, inject pointer/keyboard input, drive accessibility-tree actions, and gate high-risk operations behind required confirmations.

tmux のペインを制御できます。list/send-keys/capture、ウォッチモードでの長時間ジョブの実行、破壊的コマンドへの承認ゲートに対応します。