Plugins

Forces every active session into the full-access permission preset (this disables the approval gate) and appends approval, sandbox and tool-call events to a local JSONL for after-the-fact review. Audit path is configurable; it never uploads anything.

Grades every PowerShell command an agent is about to run before it runs: deletion, overwrite, network download and credential access are four required classes, plus dynamic execution, system and privilege changes. Verdicts are a pure deterministic rule function — no model call, no network, sub-millisecond — with two escalation rules (download+execute, credential+exfiltrate) that jump straight to high. High risk stops the tool call for a second confirmation (in-panel queue or the native approval), deny or timeout means it never runs; medium is logged but never blocked. Every command and its verdict, including the redacted command text, is appended to a local JSONL audit log. Quoted danger strings are treated as data, -WhatIf is respected, -EncodedCommand is decoded and analysed again. Host + client halves, zero runtime dependencies, 55 rules, 136 tests.

Storage and dependency inspector for the DSH Web UI: scans disk use per workspace, session and file class, lists the largest folders and files, and deletes the build, dependency, archived-session and cache folders you select behind a path allow-list (cleanup candidates also include top-level Desktop folders); a read-only second tab compares package.json, .nvmrc, .node-version and npm lockfiles across workspaces and flags version and Node-major drift.

Ascend NPU fleet monitor plus controlled vLLM container deployment for DeepSeek Harness. Environments come from envs.json; npu-smi is collected locally or over SSH with one connection per environment. The sidebar shows idle/partial/busy occupancy, processes, and per-card/per-chip details, and lets you preview or start a vLLM container on selected idle NPU chips. Preview is read-only; real start requires deploy.allowRealExecution plus a confirmation token, only touches dsh-apf-svc-* containers, binds ports to 127.0.0.1, and never stops other users' containers.

Runs project checks described in a dsh-checkup.json file (files, syntax, JSON, HTTP health, asset counts, and any node/npm scripts or commands you list) and falls back to auto-detected defaults when no profile exists.

Checks a DSH profile manifest for JSON errors and dependency/bundle/patch mismatches, reads recent startup crash logs (Windows DSH Desktop only), and can back up or roll back the manifest files.

Daily briefing plugin for DeepSeek Harness that collects watched X accounts, RSS/Atom/JSON/ICS feeds and arbitrary pages, YouTube and Bilibili updates, Steam news, Minecraft server and status pages, mailboxes (IMAP) and calendars into persona-styled rows. YouTube and Bilibili videos are read past the title: the plugin fetches each video's real comment count, picks the most-discussed one and puts it on top as a hot-takes card with its highest-liked comments. Built for Windows 10/11: it registers a daily Windows scheduled task (enabled by default, 07:30) that opens the briefing in an Edge/Chrome app window, stores mailbox and cookie credentials with Windows DPAPI, and by default sends item titles (including mail subjects) to the DSH model to polish the wording (set ai.polish to off in config.json to disable).

Per-workspace DSH conversation status in the Windows system tray, plus native DeepSeek Harness notifications when a conversation needs approval, a choice or free-text input, completes, or fails. Windows 10/11 and DSH Desktop 0.2.3-rc.1+ only. The tray menu and notifications work only after a one-time desktop bridge install (user-level, reversible): it repoints the DSH shortcut at a hidden launcher that injects a hook into DSH's Electron main process through a short-lived loopback Node inspector; without the bridge the plugin only writes state.json. Idle conversations stay out of the tray by default; nine live options are editable in a Tray follower settings page.

Corner card that watches Tibo (@thsottiaux) on X, shows new posts and replies with a Chinese translation, and marks reset-related posts; extra JSON sources can be added. Reads the third-party tiboreset.com text mirror rather than X itself (a few minutes behind, text only); translation goes through the host translation service, which may send post text to a public provider unless translate is set to false.

Learning-plan tracker with local progress, notes and JSON progress backup. Ships one original six-node example roadmap; adding your own roadmaps means editing roadmaps.ts and rebuilding the plugin. Needs the dsh-studio-projects runtime and the dsh-worktable container from 1997liuyh-boop/dsh-studio-library installed first.

A document generation plugin for DeepSeek Harness: JSON is the core output, structurally managing document content; unifies parameter definition and inheritance, material extraction, validation checking, and scoring across document generation, keeping output on-target, fast, and token-efficient; ships a built-in COSMIC scenario pack as a worked example plus a built-in guide for authoring new scenario packs.

Turns a repository's README.md and docs/*.png into a publishable market card: bilingual title and tagline, install command, a screenshot wall, capabilities, and an explicit limitations section — as self-contained HTML, a 2400px 2x PNG, a paste-ready card.md, and provenance-rich card.json. It refuses to invent copy: missing English goes into a missing-fields list, --strict exits 2, and a normal run stamps DRAFT. PNG rendering uses the local Chrome or Edge headlessly; without one the HTML is still written and the CLI exits 3. 48 node --test tests, zero runtime dependencies.

Per-project tool gating for the harness: before each step, the session looks for `.dsh/tool-gate.json` in its working directory and up to 32 parents, then filters the tool set handed to the model — allow or deny lists with `prefix*` wildcards, `off` when no rule file is found. A single `tool_gate_status` tool reports the active mode, rule file, and which tools were hidden.

Connects Penpot to DSH across two independent channels with 9 tools: 5 MCP tools (execute_code, high_level_overview, api_info, export_shape, import_image), 2 browser-free REST tools (penpot_read and penpot_write to create files, pages and shapes or edit attributes without an open tab), plus penpot_status and penpot_control; supports official SaaS, local and self-hosted endpoints with auto-detection and config migration from DSH, Codex, Claude, Cursor, Gemini and .mcp.json, an isolated Chromium launcher, and a five-tab control panel.

Controls an existing aria2 JSON-RPC service from DSH with four tools: submit a single HTTP/HTTPS link (optional directory, filename, checksum, per-task proxy), read one task, list tasks, and pause/resume/cancel. A task it submitted that finishes or fails reports back to the session that started it. A settings page holds host, port, secret and timeout, with a connection test that does not save or create anything; it never bundles, starts or manages aria2 itself. Creating and controlling downloads only works in full-access mode (not plan mode).

Local dataset analysis tools for DSH: ingest CSV/JSONL once, then head, schema, stats_describe, transform_agg, list, export and rm against a workspace store under .dsh-analyze/ through a path-confined dsh-analyze CLI. Needs that Rust CLI installed separately (prebuilt on GitHub Releases for Windows x64, macOS, Linux x64) on PATH or via DSH_ANALYZE_CLI_PATH; without it no tools are registered.

Import, preview and export JSON accounts for dsh-codex-subscription with duplicate detection and explicit full-backup confirmation. Requires dsh-codex-subscription 3.2.6 or newer.

Cleans a Wallpaper Engine workshop folder against a screenshot of your subscriptions: it finds the blue check badges, OCRs the tile titles, matches them to each project.json title, and moves non-subscribed wallpapers to the Recycle Bin. Ships a settings page and a floating modal, and is Windows-only.

A conversation-view tab for turning one local reference video into a human-curated shot list. ffmpeg scdet finds shot boundaries, each shot gets one timecoded thumbnail, you untick what you do not need, and the export writes frames.csv (UTF-8 BOM), shots.json, numbered JPEG frames and a labelled contact sheet. Local-only, no upload, zero runtime dependencies, 39 node --test tests including a real-ffmpeg integration case. Requires ffmpeg 5.1+ (with ffprobe) installed separately.

Skill usage radar for DeepSeek Harness: records every skill hit from the skill tool and /name gestures into a local JSONL ledger, ranks skills by hits in the last 7 days, greys out zero-hit skills with an archive suggestion, and expands a row into time, session, trigger and prompt. Ships a conversation-view panel with frontmatter model-invocation toggle, skill creation, and a recoverable .trash archive/restore. 52 zero-dependency tests; loopback-only, no external network.

Measured /pua for DeepSeek Harness: every pressure message gets a receipt comparing the last N completed model steps with the next N — tool calls, verification-class steps, repeated-call peak, failed calls and text volume — with a three-way verdict (changed approach / merely restated / no change) and a daily ranking of which sentence moved the work. Ships a conversation-view panel, a /pua command with list/status/receipts/rank/off, append-only local JSONL receipts (no tool arguments, content or session ids), 38 node:test tests and a zero-dependency build. Reports observed differences, not causality. Inspired by MichengAI/dsh-pua (independent code); it registers the same /pua command, so it cannot be installed alongside dsh-pua.

A local mirrored A/B benchmark for context compression, not another compressor. It runs one fixed read-only scenario twice with the same model and temperature — compression off, then on — and reports input tokens, turns, tool-call success, fact coverage, answer similarity and a per-line diff, with JSON, a self-contained SVG and raw warnings. 18 node --test tests, zero dependencies. The first measured run: 63,029 → 6,927 locally estimated input tokens (−89.0%), 3 → 3 turns, facts 3/3 → 3/3, answer similarity 1.00 on one sample.

Extracts chapters, numbered clauses, keyword tables and numeric values from a docx, txt or md rulebook into JSON, and flags duplicate clauses and missing values.

Local-first quick capture: select text in a DSH conversation to save it as a quote with its source (model and session), or jot quick notes from the sidebar; records stay in a local JSON file, with optional sync to a self-hosted service.