DSH Web 工作段折叠：保留原生一级，将正文之间的思考、工具、上下文合为一个二级，展开后显示原生三级。

Audit and fix your Mac's security in one command. No agent, no signup, open source.

Use AI agents from the DSH session UI.

Local-first memory & context harness for coding agents

Official-grade GitHub CI for DeepSeek Harness: composite action (review PRs / fix CI / report), polling PR review bot with idempotent inline comments, a status-check gate, and approval-gated PR/issue/repo/file tools

Outline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing, atomic commits.

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.

Browser automation clicks buttons. OpenTabs calls APIs.

记忆核心（Memory Eternal）：自研的 DeepSeek Harness 记忆插件，不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault（自研去重、自研 CJK 检索、可 git 管理），设置页提供图形化知识库（统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗），Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。

:star: AI-assisted development workflow that produces understanding alongside code. Teach, capture decisions, document, assemble reviews.

DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.

Lives inside your Claude Code session. Capture work as structured experience, then render resumes, Korean cover letters, interview answers, and project ideas from it.

Portable skills, agents, hooks, and Pi extensions for Claude Code, Codex CLI, Copilot, Cursor, Grok, and Pi.

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

Use Cursor CLI from Claude Code to delegate coding tasks to Composer 2.5+ and other Cursor models.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Cross-platform native desktop control tools for DeepSeek Harness (Windows first): screen_shot, screen_read (accessibility tree + pixel description for text-only models), click/type/scroll/key, and app_list/app_launch — every mutating action gated by appro

Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

AI-powered development tools. 18 agents, 19 commands, 29 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.

Enterprise Gitea & Forgejo integration for DeepSeek Harness: 20+ issue/PR/worktree tools and a real-time Git status chip in chat.

可自定义收录清单的 DSH 插件市场：收录、安装、卸载、升级一站完成，附 agent 工具与 dshm CLI。