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 yjh051108 · Agent Tool · ★ 369
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dsh-router-standard safe to install? View the security audit →
dsh-router-standard # ⚠️⚠️⚠️ 重要勘误与道歉（必读） ⚠️⚠️⚠️ ## 我不需要被造神，也不配被造神 这篇 README 顶部必须放这段话：我错了，而且错得很有代表性。 - 论文不撤回，但其中理论解释部分（双吸引子假设 A1–A4 及"god/ghost"、"自路由不可能"等强归因）已正式标注作废。 - 心路历程：我最初把 "We need / Let me" 的差异当成"官方刻意设计的双模式"；后来才意识到那更可能是一条原生深度路径 + 一条后压未收敛的极简路径之间的断层/断裂带。这个断层本身就像一层路由层——我们实际做的是把它当路由层用，实现了 "Let me / We need" 自路由。 - 我们做对了一件事，也请记住这件事：利用后训练的一个小缺陷（断层/断裂带），我们实现了 V4 Flash 能力的可复现提升——这不是我聪明，是那个缺陷恰好可被工程利用。 - Pro 是另一场完全不同的硬仗：雷霆大思考、工具面敏感、内部路由不稳定。我已经找到方向（黑盒 logprobs / 嵌入向量层逆向 / 语义锚点指纹），初步数据已在仓库。这条路我会继续用实测走，而不是用叙事走。 📄 完整勘误声明：docs/statement.md ｜ 道歉函：docs/apology.md Task-aware reasoning-mode router for DeepSeek Harness. One preset, two routing modes (v0.2.0 naming), plus the measured three-band axis behind them: 选择：安装两个预设之一（Router Standard / Router Spec，见 Usage）。 显示当前路由模式。 This is a research artifact. It encodes a measured property of DeepSeek V4 Pro / V4 Flash: model behavior along the persona axis is not a continuum — it collapses into a few stable regions separated by phase transitions. The router therefore quantizes to
| Stars | 369 |
| Forks | 33 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 65.4944466099699/100 |
| Open Issues | 43 |
| Last Updated | 2026-08-23 |
| Created | 2026-08-14 |
| Platforms | node |
| Est. Tokens | ~15k |
Looking for a dsh-router-standard alternative? If you're comparing dsh-router-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.
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·
Reverse engineer anything with agents, from app behavior down to native binaries.
Composable mathematics tools for agents
One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher
Explore other popular agent tool tools:
dsh-router-standard is Task-aware reasoning-mode router for DeepSeek Harness: three measured behavior bands (spec/mixed/react) with phase-transition evidence, persona + first-turn tool injection, agent-visible tuning. Dual-. It is categorized as a Agent Tool with 369 GitHub stars.
dsh-router-standard is primarily written in JavaScript. It covers topics such as ai-agents, cordis, deepseek-harness.
You can find installation instructions and usage details in the dsh-router-standard GitHub repository at github.com/yjh051108/dsh-router-standard. The project has 369 stars and 33 forks, indicating an active community.
dsh-router-standard is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to dsh-router-standard on Agent Skills Hub include wesight, modsearch, memtrace-public. 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: