Plugins

33 github_* tools covering REST reads, issue writes, Git data writes, private repo creation, and clone; in-process permission gate and cost-discipline companion skill; no gh CLI required.

Training attestation — reproducible, attributable, auditable off-site standardized training for asset pricing. Hard-gates four failure modes (half-refresh, hash mismatch, unknown-read-as-pass, master pollution). Ships one skill.

Controlled browser automation for DeepSeek Harness: the agent_browser tool and BrowserAutomationService drive a real Chromium or Chrome page (or an explicit CDP endpoint) through the agent-browser CLI, with allowedDomains containment and per-call output limits.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.

Read-only enhancer for a file-based long-term memory library (markdown cards in git): a memory_find search tool, a small budgeted memory digest injected into the system prompt, and a settings page with library overview, health-check status and toggles.

RP memory built on pmp tavern: RP history summaries ride the native compaction pipeline, with plain tool sessions kept out of the way. Full recall requires the downstream anima plugin. Requires the plugin-provided roleplay preset to be enabled.

Shared engineering skills, a read-only memory-bank dashboard with stages and SQLite audit browsing, and workflow request previews for DSH.

Layered cross-session memory for DSH that pushes only what changed - the first round injects every active entry, later rounds push only added / updated / removed ones, and nothing at all is injected when nothing changed, with keys that merely repeat an entry id left out of the text so the baseline is about 26% smaller. Facts and decisions carry semantic keys (one active truth per key), the model may only write to an inbox that a human promotes, an entry can carry a review date that raises a one-time reminder when due, and search is relevance-ranked with journal lines down-weighted and Chinese matched by bigram. A sidebar tab tells the lifecycle story instead of listing files - entries are grouped by stage (awaiting confirmation / in use / archived) along four axes (topic - one level, human-assigned, type, tag, date), each group can be ticked for batch promote / withdraw / archive / restore / delete / assign topic, and topics can be renamed store-wide or searched on their own. The archived stage reads in three levels - the category says why an entry left (distilled into the docs / useless for good / not needed right now, the first two being defaults you can add to), below it the entry topic stays collapsed until you click it, and entries with no topic sit right under the category. The tab also shows the global and workspace instruction files plus the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

Requires DSH >= 0.2.0-rc.2 < 0.3.0. Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.

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.

Hide chosen workspaces from the DSH sidebar and archive their sessions along with them, so those sessions never spill into the ungrouped list. Fully local and reversible; with dsh-archive-manager installed the archiving is real and undoable, otherwise it stays a display-only layer. Restore any hidden workspace from Settings.

Floating audio control panel in the Web GUI: play/pause/next/previous for Windows media sessions (SMTC) and the system master volume/mute, served by a Node route half that runs a PowerShell helper.

A draw.io editor as a .drawio file viewer in the DSH sidebar: diagrams are ordinary workspace files (new ones default to docs/diagrams/), edits autosave, and a file changed outside the editor is refused with a conflict bar instead of being overwritten; the editor is downloaded once from a pinned upstream release with a SHA-256 check and then runs fully offline.

Chat agent for a DeepSeek Harness session: create characters and write their personas, keep several archive threads per character, undo or rewind the locally stored transcript, and record story beats in an event book.

Database connections and SQL for DeepSeek Harness: register data sources, browse and comment schemas, run AST-checked SQL with a per-source read-only toggle, and render bar, line and pie charts, from chat or the Settings page.

Per-turn token usage, request composition and cost breakdown panel for the DeepSeek Harness Web GUI.

Codex-style DeepSeek Harness model and reasoning selector with model-advertised effort levels, DSH-native themes, left-clipped radiation effects, and copy-ready reasoning-effort declaration guidance for custom-provider models.

会话归位：把游离（未分组）会话按 canonical cwd 重新归属到匹配的工作区，只修 workspace 归属记录，不动会话文件。

Turn approved tracker tickets into review-ready pull requests with DeepSeek Harness.

Maintained fork of godchen520/dsh-web-search-bing adapted to DSH 0.1.5-rc.1: Bing-backed provider for the built-in web_search tool, scraping the public cn.bing.com HTML results page with no API key, reachable from mainland China, and keeping searches off the model's own search quota. Endpoint and result count configurable.

Lists the Docker Compose projects of your DSH workspaces in the right sidebar, one group per project directory, with container status, project- and service-level up/stop/restart, and streamed per-service logs.

One install for the community's verified DeepSeek Harness fixes: a bundle that mounts every guard and patch in a single profile line, plus a read-only projection-cache footprint report.

Cross-project experience recall for DeepSeek Harness: when the running work matches something your memory store already learned elsewhere, that lesson is injected before the next step. Runs fully locally, judged by a local small model.

Local file recall: indexes the folders you choose into one local SQLite database, so 'where did I put that file?' is one query instead of a disk walk. Caches, VCS and program folders are pruned per directory; each folder keeps its own incremental anchor, so a folder added later is backfilled in full. Read-only: it never modifies, moves or deletes your files. Works on DeepSeek Harness 0.1.7 through 0.2.x, tested on 0.2.0-rc.1.