Plugins

Per-message delete for DeepSeek Harness — a trash icon beside the copy button on every chat message that removes that message from the derived model context (and the visible transcript) via the official surface-replace contract

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.

Branch-role guard for AI coding agents: configurable integration/preview/production/archive roles, blocking direct push, force-push and delete on protected branches and agent merges into production/archive.

Generates editable PPTX decks in DSH with a bundled authoring Skill, deterministic PPTD scene checks, native PowerPoint objects, and local PPTD source-project delivery.

Local semantic code search for DeepSeek Harness: fragment-level symbol-aware indexing, offline lexical embeddings or an OpenAI-compatible endpoint, and hybrid vector + BM25 retrieval fused with RRF - three dsh tools plus a sema CLI.

Official DeepSeek platform monitoring inside the provider card: a live balance chip left of the composer model name plus an expandable account-details panel with per-model monthly usage and a daily stacked chart.

iPhone-style agent phone: dual-panel calls & SMS, RCS group chat with trust gates, cross-device agent messaging via the registry inbox bridge, L0–L4 trust badges and evidence audit. Experimental: trust summaries are not a security guarantee, and SMS/signalling is relayed through the operator's inbox (visible to them); E2E encryption is planned.

Re-sorts sidebar workspaces by last activity once per day; stable order within the day.

A floating right-side table of contents (TOC) for the DeepSeek Harness Web UI: one entry per user question, click to scroll to that message.

Turns stock names and codes in DSH output text into clickable buttons for quotes and company news.

AI-driven source-code security scanning workbench: 5 model tools (start/finding/status/report/list) plus a /hawkeye web UI and JSON/Markdown/HTML vulnerability reports; zero-dependency Cordis plugin, installable as agent preset or npm package.

Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.

Reusable skill to browse, search and download Wallpaper Engine (Steam 431960) workshop wallpapers and wire them into the DSH skin center, including bypassing the Steam HTTP block and the region-mismatch sign-in block via a matching SOCKS proxy.

Invoke user-accessible Skills with @name tokens and show matching Skill suggestions in the conversation composer.

Writing bridge to the open-source QingAgent client: the agent drafts and revises documents through qing_ prefixed host tools, typeset on a rice-paper panel with mermaid, drawio, tables and KaTeX; edits stage as reviewable diffs and land only on commit, and it requires the QingAgent desktop app on the same machine.

Subtitle-first video transcription with SRT export, cancellable job controls, and a faster-whisper large-v3 fallback when subtitles are unavailable.

Read-only Odoo tools over JSON-RPC: server info, model field introspection, and a restricted search_read limited to an allow list of models whose domain field names may not contain dots, so related-record traversal is not possible. A draft-create tool is registered only when allowWrite is enabled, and is limited to sale.order and project.task with the draft state enforced by the plugin.

Per-session status labels (built-in active/done/paused plus custom) shown in the sidebar, conversation header, and hover card, with editable colors.

Grok Build provider using the official CLI browser login, with dynamic account-visible models, streaming reasoning and tools, plus quota and model-capability settings.

Hard-stop consecutive identical tool calls after a configurable streak so the agent cannot spin in place.

Turn your phone into a full-featured camera for dsh sessions (requires the open-source Android companion app — install the plugin and scan the QR code it shows to download the APK): 1. Live viewfinder over LAN or USB, injectable into the chat or savable to a folder. 2. Callable tools let the dsh model take photos, zoom, and switch lenses on demand mid-conversation, so in fully automated workflows the model can actively "see" the physical world. 3. Full zoom/flash, crop, and annotation. 4. Rich settings.

Economics-first journal/working-paper monitor for DeepSeek Harness: NBER RSS + arXiv econ (4 categories) + Chinese econ journals (Shi Jie Jing Ji via Magtech, Zhong Guo Nong Cun Guan Cha, Cai Mao Jing Ji, Zhong Guo Ren Kou Ke Xue, Jing Ji Guan Li via ajcass) fetch, keyword filter, dry-run/Webhook push, dedup persistence, and schedule_create-compatible briefing.

DeepSeek API pricing reminder with a game HUD: Beijing-time countdowns to peak/off-peak windows, a draggable HP capsule with day/moonlight themes, and a nine-realm cultivation system with breakthrough animations.

Trading-terminal style cost tracker for DeepSeek Harness: sidebar balance and today spend, per-step RMB cost table, auto-synced official pricing with peak/off-peak, cross-session and per-day summaries, tool-level attribution, and cost forecast.