Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

Incident-derived guardrail hooks and a plan→implement→verify→crosscheck delivery loop for Claude Code. Hook cost measured; 35 bats tests.

DSH bundle: key-free web search, page fetch and one web_tools action tool for verticals, platforms and cited research; eight engines fused with RRF, 34 vertical sources, arXiv research lookups and readable papers, official release facts, a replayable benc

Point-and-shoot screenshot capture for DeepSeek Harness: clipboard watcher + system floating window (comment & key-point, copy/save-doc/save-image) + zero-config OCR through the host's own multimodal model (Tongyi Qianwen fallback) + Obsidian per-day merg

AI coding assistant skills for building CrowdStrike Falcon Foundry apps: scaffolding, deployment, and best practices for API integrations, collections, functions, UI extensions, UI pages, and workflows.

Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

Nexus 个人编码助理：在桌面端和消息渠道中安排、跟进与验收本机编码任务。Personal coding assistant for DSH.

二游活动/卡池排期速查：侧边栏底部按钮，点击展开各游戏当前版本、卡池与活动起止；覆盖 28 款游戏，支持联网自动刷新与刷新频率设置。

Use a SuperGrok or X Premium Grok Build subscription in DeepSeek Harness

Run Codex and Cursor as background workers inside Claude Code. Reviews, tasks, and rescues with tracked jobs, live progress, and session handoffs.

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research with citations & branded HTML reports. 13 commands, no Node runtime.

Claude Code scaffolding and first steps for complex brownfield projects

MetalBear Skills for our users

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI, Claude plans and reviews the diff, Sol writes the code. Multi-model AI coding where the model that wrote the diff never grades it.

Mission control for every Claude Code session on your machine.

Reverse engineer anything with agents, from app behavior down to native binaries.

Games above the Claude Code prompt: snake, Tetris, 2048, Minesweeper, Flappy, Pong, a typing test and Space Invaders, plus a pet that grows as Claude tests, commits and edits

DeepSeek Harness MCP Connector: connect servers, search tools across active connections, and troubleshoot discovery. Includes a continuously updated catalog; supports OAuth 2.0 PKCE, API keys, Streamable HTTP/stdio, and mcpServers JSON import.

DSH 划词追问（侧边卡片作答）：在聊天区与任务区选中文本就地追问，答案由独立子代理在侧边卡片里流式呈现，也可选择落回主对话。

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.