Plugins

DogCatTrace attribution parody as a right-sidebar tab: draw three integer challenges, paste each model reply into one box at a time, read the 24-breed dog and cat ranking.

Browses the awesome-claude-video-skills catalog (373 entries) inside DSH settings and installs a chosen skill into ~/.claude/skills and/or ~/.dsh/skills: it downloads the GitHub archive of that repository and copies the skill directory, and executes no code from the repository. Installs run as background jobs with live progress (bytes downloaded, files copied) and can be cancelled; skills installed by the plugin can be uninstalled, while directories without its marker are left untouched. Rows show an approximate repository size reported by GitHub. The same actions are exposed to the agent as the video_skill_search, video_skill_install and video_skill_uninstall tools.

IDE tab in the dsh web client: a Monaco editor with the Dark Modern theme plus a file tree, git source control (stage/commit/push), an integrated xterm terminal and ripgrep workspace search, opened as a conversation view tab.

Git tab in the DSH web UI right sidebar for the current session repository — switches branches from a dropdown of local and remote branches (with ahead/behind counts), stages files in staged/unstaged/untracked/conflicted groups, commits, fetches, pulls and pushes with automatic upstream setup, drafts a Conventional Commits message from the staged diff with the default model and falls back to a plain chore message when none is available, and renders git log --graph with per-branch colors plus a word-level highlighted diff.

Runs the model's bash commands in a local shell chosen in Settings (Niubash, Git Bash, MSYS2, Cygwin, or any bash.exe on PATH) instead of rewriting them for PowerShell, and hides the pwsh tool on Windows.

Forked from j62268781-alt/dsh-skills-mcp-manager (MIT) at its 0.5.6 baseline and substantially reworked since; it registers the same plugin id, so it cannot be installed alongside the original. Adds lossless cordis.patch.yml writes (JS expression values preserved), save-gated per-tool filters, skills governance over the DSH roots plus 10 external agent directories with per-skill/per-source switches enforced through the agent-scope skills provider (disabling actually hides a skill from the model), categories and a restorable trash, GitHub-repository install/update/rollback, zip and SKILL.md import, skills.sh/ClawHub market, workspace view, sidebar panel, dark/light contrast fixes, and update checks against the published npm package (same source as market installs; npm publication carries OIDC provenance).

Read-only GitHub research tools for the agent - repository search, repo health check (stars, license, last push, size, archived), dependency manifests, and single-file reads over the raw channel - plus an oss-reuse skill that makes the agent search GitHub and check real dependencies before writing code, so features are assembled from existing open-source projects instead of rewritten; nothing is cloned and no disk space is used.

Lists the skills in the shared skills directory with their source and version, installs and updates them from a GitHub repo, removes them to a recycle bin kept for 7 days, and controls which agents can see each skill and whether the model may invoke it.

DeepSeek Harness plugin that stops shell commands that would hang a turn (editors, REPLs, pagers, watch modes, dev servers, tail -f, interactive logins, git commit without -m) and tells the model the non-interactive alternative.

Sentry for DeepSeek Harness: the tools of Sentry MCP server, a result card, and an issue panel with resolve, ignore and assign.

Reads a GitNexus index in the DSH sidebar, reports skipped files, index freshness and language coverage, searches symbols, and reviews recent Git activity.

Merge requests, review threads and pipeline job logs for GitLab over its REST API with a personal access token, in a side panel, with comment, reply, resolve and approve actions that wait for confirmation. Reads need the read_api scope, writes need api.

A timer wakes a DSH session to read the GitHub repos and topics you follow, decide which changes are worth your time, and write a dated report while keeping a table of what it already saw. A sidebar panel keeps the run history and the GitHub trending list. Read-only.

Prepares a repository README before pushing: scans repo facts, renders banner and process-diagram images (needs Pillow and the Microsoft YaHei font), lints layout and section numbering, then commits and pushes with retry.

Jira and Confluence for DeepSeek Harness: the tools of Atlassian remote MCP server, a result card for issues and pages, and an issue panel.

Markdown-as-database project knowledge base for DSH agents: ten kb_* tools (including kb_register for registering existing notes), stable TIDs, `[[node]]` links that never copy text, `[[tscl]]` definitions expanded in place, bounded reads, structural lint covering tscl, workspace-first library discovery, inline git snapshots, a node-graph panel, and a bundled prompt section plus skill that make the agent reach for kb_* instead of hand-written docs/.

Adds a web device-code sign-in and sign-out entry for the built-in GitHub Copilot provider in DSH, presets an out-of-the-box Copilot provider route, keeps credentials in the built-in credential store, and manages the model catalog as a first-login fallback that never overwrites customized model entries.

Provider-reported quota snapshots for GLM Coding Plan and GitHub Copilot in DSH: a draggable floating capsule with detail panels for quota windows, reset times, per-model usage and Copilot credits, plus an optional sidebar card hidden by default; credentials are resolved by the DSH host and no quota history is stored.

Token usage dashboard and per-session tree statistics: provides time-range filtering, 6 summary metric cards, GitHub-style activity heatmap, model stacked-bar charts with cache hit rate curves, and Top-5 model/provider rankings; enhances the native session status bar to display aggregated token usage across main agents and all subagents with detailed breakdowns.

Finds wasted GitHub Actions runner time and proposes small, reviewable workflow patches, with explicit approval before any edit and a DSH settings page for analysis rules, history limits, storage, and cost estimation.

Two-pane model picker that replaces the composer model menu with a searchable provider-grouped list on the left and a detail card on the right showing the selected model's context window, output cap, capability tags and reasoning-effort levels, all read from that model's own provider. The npm name dsh-model-picker belongs to another author; install through this GitHub source.

In-conversation source deck for DSH Desktop (supports DSH 0.2.2-rc.2): the current chat model runs LLM search rounds, candidates render as GitHub-aware cards, and keep/exclude feedback, favorites, and the selected sources stay in the same conversation.

DSH pet plugin that adds an Arknights operator library and custom image pets: pick one of 486 operators and the plugin downloads that operator Codex v2 atlas from the pinned upstream revision, verifies every Git blob hash and installs it locally, or import your own Codex atlas (1536x1872 or 1536x2288) or a plain PNG/WebP/GIF; the pet then follows session activity, shows a bubble while a decision is pending, and can be dragged and resized.

A no-limit Texas holdem table where you are the only human. Eight seats: you plus seven LLM agents written on AI-founder personas (Altman, Dario Amodei, Musk, Liang Wenfeng, Jensen Huang, Lei Jun, Zhang Yiming). Each agent bets through the currently selected host model and falls back to its own heuristic style when no model is available; every agent only ever sees its own hole cards, because the prompt is built from that seat alone. A hand ends by revealing the winner hole cards, with a flip animation replayed on every community card, and a rail keeps a live action-and-table-talk timeline. LAN mode (off by default, single-machine play is unaffected) lets another install on the same network join this very table: the host shows a six-digit room code, UDP broadcast discovers nearby tables, and a joiner randomly takes over one bot seat, with the seat handed back to its character on leave or after twenty seconds of silence. The room code is never put on the wire and every snapshot is generated for one viewer seat, so nobody, not even the host, can read another player hole cards. Fork of BubblePtr/dsh-holdem (MIT), credited in the README and in the UI.