Plugins

Ships a skill about handing work to subagents instead of doing it inline - which tasks are worth fanning out, how many to run at once, how to send them in parallel, and how to check what they returned instead of trusting the summary.

Parse PRDs and PDFs, ask clarifying questions in batches, consolidate a BRIEF.md system brief, and package deliverables for upload.

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the prompt.

Ships a skill about writing DSH skills - SKILL.md frontmatter and root precedence, how to phrase a description so it actually triggers, length and splitting rules, and an A/B check that the finished skill changes agent behaviour. The package also carries the checker the skill uses to validate a skill directory.

Speaks or plays a sound at the end of every turn and plays a failure cue when a tool call or a turn errors. Ships 20 built-in effects (10 alert chimes + 10 nature sounds) and defaults to effect mode, so it needs no API key and no audio files; an optional Volcengine voice-clone route generates the three announcement clips in one click. Plays through winmm/waveOut as-is, never changing the system volume or mute state. Windows only.

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.

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.

Exa-backed web search provider for the ctx.web seam, with Exa Dynamic Highlights on by default and the Exa-Beta header that setting requires; exposes all eight Exa retrieval types, adds an /exa command to change highlights, search type and result count at runtime, and registers an exa_search tool that takes its own result count.

Generates 3Blue1Brown-style Manim animations to explain answers, with a right-column gallery and inline multi-modal file publishing.

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.

Live Android device pane next to your DSH conversation: scrcpy-server H.264 streaming (WebCodecs, 30-60 fps), agent tap/swipe/text with auto-screenshot verification, uiautomator element tree with tap coordinates, host-managed recording + logcat debug sessions. FLAG_SECURE pages are detected automatically with a mitigation chain and a tappable text-view fallback. Emulators and USB real phones, human+agent co-operation, session-isolated, loopback-only.

Shell tool with four Windows backends (PowerShell / Git Bash / WSL / MSYS2) plus an interactive PTY terminal; the MSYS2 backend starts bash.exe with -lc so /etc/profile puts /usr/bin and /mingw64/bin on PATH, and injects MSYSTEM=MINGW64 into the PTY environment. Written in TypeScript, targets DSH 0.1.2+.

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.

Memory archive and prompt viewer for DeepSeek Harness: read back what compaction folded out of context - browse past sessions or Tavern playthrough archives (summary, original text, state) with full-text search - and inspect the prompt each turn actually sent, listing every assembled system section with its order, character count, offset, hash and mutability, plus an assembly map, registry export, and honest diagnostics when a section is empty or its log cannot be read. Optionally provisions a roleplay agent preset.

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

Coordinates bounded project recall from compatible memory and learning providers, with shared settings and provider lifecycle management.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

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. 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 it comes due, search is relevance-ranked with Chinese matched by bigram, and a sidebar tab tells the lifecycle story instead of just listing files — entries are grouped into awaiting confirmation / in use / archived, viewable by type, tag or date, and the tab can promote a candidate, withdraw or archive a standing entry, restore an archived one and delete a candidate, alongside the global and workspace instruction files and the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

Fork of harness-session-delete that adds Delete to the native session action menu and a recycle-bin page with search, sort, workspace grouping, message preview, batch restore, and per-workspace permanent purge; active sessions are protected.

Session management: auto-archives stale sessions on a configurable threshold, with an archive panel, unarchive, and recycle-bin deletion with restore.

Adds DSH restart and stop controls with token-aware reconnect and policy-based recovery for interrupted web sessions.

Inject steering or correction into a running session while the model is thinking, or cancel the current turn, from a floating browser panel.

Gives the model a rename_session tool, so the agent can retitle a session from inside the conversation.

Model capability editor: edit each model reasoning-effort levels and image-input (multimodal) declarations inline in the official model page, written back to settings.yaml as a whole group, with a floating entry as fallback when the anchor breaks.