No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by xiaobright · Agent Tool · ★ 3.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dsh-anchored-standard safe to install? View the security audit →
dsh-anchored-standard 中文说明 An experimental DeepSeek Harness agent preset that bootstraps the first model request with a Minimal-aligned prompt, the Minimal preset's real tool schema ( + ), and no auto-injected workspace/skill context, then exposes the complete Standard tool catalog after the first durable tool call or reply. This is a community project. It is not an official DeepSeek preset and is not affiliated with or endorsed by DeepSeek. Why DeepSeek V4 Pro conditions strongly on the API-visible tool catalog. In the Project2 evaluation, Standard and PTC produced scores of 91 and 92, while the official Minimal preset produced 99 and 96. Permanently staying on Minimal, however, gives up the Standard preset's broader tool set. Anchored Standard separates initial trajectory selection from later tool use: Keep the Minimal complete system prompt. Expose the Minimal preset's REAL tool schemas — persistent + , byte-identical to the official Minimal composition — on the first model request.
| Stars | 3,817 |
| Forks | 120 |
| Language | JavaScript |
| Category | Agent Tool |
| Quality Score | 69.8815962244933/100 |
| Open Issues | 18 |
| Last Updated | 2026-09-10 |
| Created | 2026-08-14 |
| Platforms | node |
| Est. Tokens | ~15k |
These tools work well together with dsh-anchored-standard for enhanced workflows:
Looking for a dsh-anchored-standard alternative? If you're comparing dsh-anchored-standard with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
收录最全、更新最快的技能Skills商店：精选原创技能包（涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流），全部打包好可直接安装使用！同时自动抓取GitHub上万个Skills项目，按分类、更新时间、Star数
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown a
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving acro
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill r
Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget
Explore other popular agent tool tools:
dsh-anchored-standard is Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99). It is categorized as a Agent Tool with 3.8k GitHub stars.
dsh-anchored-standard is primarily written in JavaScript. It covers topics such as deepseek, deepseek-harness, dsh-plugin.
You can find installation instructions and usage details in the dsh-anchored-standard GitHub repository at github.com/xiaobright/dsh-anchored-standard. The project has 3.8k stars and 120 forks, indicating an active community.
The top alternatives to dsh-anchored-standard on Agent Skills Hub include skill, memsearch, EverOS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: