Plugins

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.

A chemistry workbench panel in the DSH web UI. Draw structures on a Ketcher canvas (a script downloads the build; it renders locally in the browser with no backend), then compute on the current molecule with RDKit without calling a model — formula, molecular weight, exact mass, logP, TPSA, hydrogen-bond donors and acceptors, ring counts, Fsp3, stereocentres, Lipinski and Veber rule-by-rule checks, QED, PAINS/BRENK structural alerts and the Murcko scaffold, plus SMARTS substructure matching, fingerprint similarity, format conversion, standardisation and batch clean-up. A retrosynthesis tab talks to a pluggable backend (Retro* by default) over a single JSON-in/JSON-out process, and states what is missing when the backend is not installed instead of inventing a route. The calculations run in this repository's Python package (rdkit), which is installed with pip separately.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

macOS menu bar app for the DSH web server, plus the host plugin it reads: the plugin writes the running server's port, PID and tokenized URL to ~/.config/dsh-launcher/runtime.json and removes it on shutdown, so start, open, restart and stop work from the status bar even for a server started from a terminal.

Team cost captain: meters every model call (subagents included), attributes each call to a member by workspace rules, prices it with the built-in DeepSeek 2026-09 catalog (peak/off-peak, CNY/USD) or user overrides, and appends it to a local JSONL ledger. Adds hot-reloadable member budgets, 80%/100% webhook alerts, optional over-budget enforcement, a team_cost_report tool with CSV export, and a settings-page team dashboard served over a Typert RPC service.

Render GeoJSON or vector data into an interactive GeoLibre map in a sidebar tab, and let agents operate the live map through tools: layers, styles, view, feature identification, GeoLibre processing algorithms, and the Whitebox toolbox (WASM in the browser).

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

Parse Chinese e-invoice PDFs (XML attachment first, text-layer regex fallback) into structured JSON with amount cross-check, and generate expense reports (Markdown / xlsx).

A dsh web plugin that wraps the running Harness in a native Windows desktop window: it bundles a Wails v3 desktop client (so installing the plugin is enough), probes the web port and writes the ~/.dsh/dsh-web-port.json protocol file for the client, registers a system tray, desktop/Start Menu shortcuts and a startup autostart toggle, and the client can start dsh itself if it is not running.

界面草图：会话输入框内绘制界面草图，一键转为 JSONL 语义嵌入输入框，随需求发给 DSH agent

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 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.

Session manager panel under Settings → Plugins: list all sessions with title, cwd, agent preset, updated time, turns and steps, expand a row to view message history, delete non-running sessions, and export a session as JSON or Markdown via a browser Blob URL.

Session export and compliance archiving for DeepSeek Harness: deterministic redaction, Markdown/JSONL/PDF outputs, on-disk archive management, and a trend/audit view.

Safe, audited SQLite/PostgreSQL/MySQL access for dsh agents: schema introspection, enforced read-only queries, a write approval gate, and a durable JSONL SQL audit trail.

Windows desktop UI context picker for Codex, DeepSeek Harness, and MCP clients: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, and local OCR, then review and approve Markdown/JSON context before output.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.

Kubernetes ops for the agent: get resources with structured JSON output, describe, logs, exec, apply/delete (user-confirmed) and port-forward.

Native A2A (Agent-to-Agent) server for dsh: expose this dsh as a callable agent over HTTP with JSON-RPC tasks.

Bridges Multica to DeepSeek Harness through a versioned JSONL process protocol.

Anti-bot HTTP fetch tools hardened by SXS's production scraping stack (millions of requests/day): UA-pool rotation, retry with exponential backoff, anti-bot wall detection (captcha / verification challenges) and adaptive rate limiting — tools: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Independent browser acceptance testing for agent deliverables: JSON spec in, real-Chromium verdict out.