Plugins

Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。

Matt Pocock full promoted skill set (25 SKILL.md: grilling, writing-for-agents, wait-what, TDD, code review, wayfinder, ask-matt router) ported to DSH.

Detects prompt-injection, jailbreak, and secret-leak patterns on the agent/pre-step, tools/pre-execute, and tools/post-execute seams with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.

Claude-style drag-and-drop/paperclip file upload with content sniffing, document-to-Markdown via Microsoft MarkItDown (built-in JS fallback), text inlining, and a read_document tool for agents.

DeepSeek Harness bundle plugin: a process-discipline system-prompt section plus a deterministic nudge that makes agents narrate progress between silent tool steps.

aginxbrowser plugin for DeepSeek Harness: fetch JS-rendered / Cloudflare-protected pages as clean markdown, aggregated web search (Baidu/Sogou/WeChat and 11 more), and indexed interactive sessions (click / type / scroll / eval / screenshot) against a host

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT): 76 skills, 49 agents, hook bridge.

Terminal-native TUI frontend for DeepSeek Harness that presents sessions, models, plugins, jobs, subagents, todos, and provider configuration through Harness capabilities while preserving real terminal scrollback.

Role-based LLM retry & fallback strategies.

Recoverable file and Git operations for coding agents, with shared recovery and redaction tools, a DSH shell adapter and audit records; optional native text-read protection is off by default.

Goal lifecycle management for dsh with an interactive kanban board: goals, criteria, attempts and reviews live in the workspace, driven by graph_* tools, with a two-lane board rendered in the conversation view.

Live flowgraph visualization for DeepSeek Harness sessions, including tool calls, parallel groups, subagent branches, and drill-down details.

Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.

Windows desktop computer-use tools (click, type, key, screenshot) with freshness checks, approval gating, process-identity verification around every action, and a sanitized audit trail.

DeepSeek Harness Cordis tools for All in Flash, powered by All in Luna

Provides a better model experience, including but not limited to: filling model parameters in multiple ways, improving model compatibility, remembering reasoning efforts, subagents following the parent's model and reasoning effort in real time, and AI self-adjusting reasoning effort.

A read-only mirror for installed DeepSeek Harness plugins: capability inventory with evidence, cross-plugin conflicts, and a diff of what changed since the last scan

A shared kanban board that lets people and DSH agents manage workspace tasks through a Board tab and kanban tools.

Agent-Native document handling for DSH — addressable blocks let an agent read and edit one section instead of the whole file. Ships the geml MCP server and the authoring and code-graph skills.

Read any page as clean main content: charset auto-detect (GBK/GB2312/UTF-8/Big5), noise stripping, compact text/Markdown, offset continuation, optional SPA rendering, batch reads and site crawling.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

Disciplined engineering workflow system for AI coding agents: planning, TDD, auto-fix loops, codebase knowledge graphs, and multi-agent wave execution. Needs codebase-memory-mcp (pip install "codebase-memory-mcp>=0.10.8,<0.11.0"); /scan stops without it.