Plugins

Letter of credit document check against UCP600: documents, periods and discrepancies.

Repair order settlement check: item amounts, labour/parts totals and grand total.

Flags ICD coding pairs that need a coder's attention - dagger and asterisk combinations, combination codes - against GB/T 14396-2016 and published ICD usage notes. Reports the pairs it finds rather than resolving them; the coding decision stays with the coder.

Checks supervision logs for cross-day continuity and for on-site supervision coverage, against GB/T 50319-2013 and other published documents. Reports gaps and coverage differences for a human to review.

Checks a bid evaluation scoring matrix for internal arithmetic consistency: that each factor's maximum, the scores recorded and the total agree with each other. Reports the differences it finds; it does not judge whether the evaluation itself was correct or fair.

Solo murder-mystery (jubensha) in a session tab: the AI hosts the game and plays every other seat, each knowing only its own role book, while the player's seat stays yours — with a stage bar, a per-seat timeline, a clue page and a reveal that unseals the truth only at the end.

Control surface for the dsh-lan-gate LAN gateway: a button beside Settings that shows whether the gateway is running and how many phones or tablets are waiting for approval, opens the loopback-only approval page in one click instead of typing its URL, and starts the gateway through its scheduled task first when it is not running. Not rendered on phone or tablet surfaces.

Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.

Governs the persistent information and project constraints an agent works with - project orientation and scope, information and document lifecycle, and persistent workspace mutation - through one additive system-prompt section plus deterministic runtime checks.

Fork of amlyczz/dsh-lark-link (MIT), maintained by Very12345. Per-conversation reasoning-effort controls, multi-app isolation, and streamed task-status cards.

Pushes DSH session events to phone IM and lets you reply straight under that message, injecting the text back into the right session. Covers nine event kinds: task completion, execution error, execution blocked, manual abort, token limit reached, abnormal interruption, waiting for your answer, permission request, and waiting for plan confirmation. Channels are QQ single-chat bots and Feishu custom apps, both over WebSocket long connections — no public IP, domain or tunneling needed. Several bots can be configured at once, each subscribing to the sessions it cares about. Approvals and questions arrive with tappable buttons, and replies route home through three layers (button, quoted reply, explicit short-id prefix), falling back to the most recent intervention-needed notification and echoing which session it went to.

Source Control panel in the DSH Web left rail: search, switch and create branches with ahead/behind counts, a topo-order commit graph, and a click-to-expand preview of any commit showing its files (A/M/D), insertions and deletions, message, author and timestamp. An always-on footer dock above Settings carries the branch dropdown and recent commits and follows the open session; fetch and fast-forward pull are one button, and a git_worktree agent tool creates, lists and removes worktrees.

A code review workflow that reviews uncommitted changes, changes against a base branch, a single commit, a GitHub pull request, or a file.

Gated four-stage video pipeline: brief, script, assets and compose, turning one sentence into a narrated explainer with ComfyUI workflows or image/video APIs and FFmpeg assembly.

Session-scoped research evidence ledger with sources, linked claims, open questions, and explicit user review; provides a tool, slash command, and conversation panel, with selected-claim Markdown export that omits excerpts, review notes, and local paths by default; does not fetch sources or verify their truth.

Session-scoped delivery receipts for local artifacts: compare current file hashes with a recorded baseline, keep agent claims separate from explicit user acceptance, flag changed or unavailable files, and export a Markdown receipt through a tool, slash command, and conversation panel.

Provide a LeLogin skill for credential injection and authenticated business applications without exposing plaintext secrets.

Knowledge-point notebook for DeepSeek Harness: turns a Markdown notes folder into a card canvas — folder = chapter, file = section, body = knowledge points — with masked-answer questions for self-testing, KaTeX formulas, Mermaid flowcharts, a mind map view and in-panel editing.

Eyes for text-only models: mounts the bundled stdio MCP server as mcp__opencode_eyes__describe_image, which sends an image file to StepFun step-3.7-flash and returns a detailed description.

Adds a "Check updates" tab to the Built-in plugins settings: one row per installed bundle, with its latest npm version and an update button. Each row also reports DSH-runtime compatibility. The registry is read through the .npmrc chain (environment, then profile, then user, first hit wins); with nothing configured it races a mirror against the public registry, and a private registry is never raced against a public one. A version is installed from the registry it was read from.

RSS/Atom reader with grouped subscriptions and unread/total counts, FreshRSS account sync over the Google Reader API with read/star written back, local image proxy, optional BYOK AI summary/translate/Q&A, podcast audio playback and full-text fetch.

Observes consecutive identical tool failures and optionally pauses before the next model step, preserving original results and successful repeats, with an in-chat report in DSH Web.

Mounts the hosted Reaudit MCP server (https://mcp.reaudit.io/mcp) through the in-box @deepseek-ai/dsh-mcp-client bridge with a REAUDIT_API_KEY bearer token: 238 mcp__reaudit__* tools for brand visibility in AI answers (ChatGPT, Perplexity, Gemini, Google AI Overviews), competitor and citation analysis, site audits, content generation and social scheduling.

Low-token web search that returns only {title, url, snippet} per hit — vendor extras such as answer, score and raw_content never enter the context. Five interchangeable backends (Tavily, Brave, SearXNG, Google CSE, Exa) with automatic failover to the next usable one in fallback / chain order when the primary fails, deduplicating repeated providers. Returned URLs and snippets are sanitized of tracking parameters.