Plugins

Directed fuzzing driven by an LLM agent: from a target repository and a bug (CVE description, patch, crash trace, or file:line), it runs a PLAN, IMPLEMENT, EXECUTE, REFLECT loop in which the model writes Python input generators, until an input triggers the campaign's stderr-pattern oracle or the campaign stops.

Windows workspace pre-authorization: adds an explicit full-control DACL ACE (including WRITE_OWNER, required by dsh >=0.1.7 sandbox startup) to user-declared workspace directories, removing the repeated full-access escalation prompt. Grants only on explicit intent — new workspace records or paths added in the plugin settings page; system directories are hard-blocked. Windows only.

Chat-operated multi-database admin plugin for DeepSeek Harness: query and manage MySQL, PostgreSQL, GaussDB, MongoDB, Redis, Oracle, DM and SQLite from the conversation with project-scoped ro/rw grants, a sidebar management panel, schema browsing and data preview, and confirmation-gated dangerous operations.

Installs an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an omoslim CLI and a Web inspector button showing the current subagent models.

Fortune-telling toolkit: bazi, ziwei doushu, meihua yijing, liuyao (six-line coin oracle with najia), almanac, chenggu bone-weight, zodiac, date selection, qimen dunjia, fengshui, name scoring, compatibility, numerology, a life K-line chart, tarot and xiaoliuren — 16 tools whose ganzhi, stars, hexagrams and bone weights are all computed by deterministic local engines, with the model only interpreting results. Supports solar and lunar dates with leap months, China DST and true solar time correction, plus a ten-page read-only side panel.

Transactional uninstall engine: every destructive action runs validate/preview/execute/undo with Saga rollback, WAL crash recovery, hash-chain audit, hardlink dedup, and a Bayesian oracle that predicts success probability before you commit.

Reuses hooks declared in Claude Code, Codex and opencode configs on dsh, executing shell, webhook, oracle and proxy handlers with zero runtime dependencies.

Role-based expert subagents for DeepSeek Harness with a task sidebar: explorer, librarian, oracle, designer and fixer delegate in parallel, each with its own model and reasoning depth.

Search the documents and pictures in your Quberi knowledge base, browse its spaces and documents, save notes to it, and upload files into it with your approval for each one, from DeepSeek Harness over OAuth.

Tailscale remote-access operations panel for the dsh web GUI: health checks, HTTPS entry toggle via tailscale serve, macOS proxy bypass, relay server ops, and ACL snippet generation.

Strongly read-only, secret-aware Oracle second-opinion subagent.

Registers six native DeepSeek Harness tools for deterministic fixture-based or read-only Microsoft SQL Server and Oracle database analysis, planning, preview, and readback.

Windows sandbox ACL-repair plugin for DeepSeek Harness (dsh) — fix the grantWrite failure (SetNamedSecurityInfoW Win32 5) and retry the command invisibly

Connect DeepSeek Harness Web to MySQL, MariaDB, PostgreSQL, SQL Server, Oracle and MongoDB for schema discovery and read-only queries through session-authorized MCP tools.

Alibaba Cloud MCP connection for DeepSeek Harness: static AccessKey credentials + local Alibaba Cloud MCP Proxy (uvx alibabacloud.mcp-proxy) connecting to the official OpenAPI MCP Server, with tools under mcp__aliyun__* and a web settings panel

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Specialist subagent delegation preset (orchestrator + 5 roles: oracle/designer/fixer/explorer/librarian) that seeds itself into your DSH home — background-first delegation, JSON-driven models/effort/tool permissions, scoped MCP for research.

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.