Security News
Deno Goes the Way of the Dinosaur
Cloudflare is acquiring Deno’s team, which will provide another year of bug fixes and security updates before ending support for the runtime.
By Sarah Gooding - Oct 16, 2026
New:Introducing Socket Scanning for VS Code Marketplace Extensions.Learn more →
dsh-agent-policy
Advanced tools
dsh-agent-policy
全局 Agent 行为策略:向所有会话注入「纯文本模型能力边界(识图走 ocr.py,不用 read_image)」与「指令冲突时技能摘要优先」的独立 systemPrompt section,不受 preset persona 遮蔽
dsh-agent-policy
全局 Agent 行为策略:向所有会话注入「纯文本模型能力边界」与「指令优先级」的独立 systemPrompt section。
工作原理
在 host 平面注册独立命名的 systemPrompt section(user:agent-policy),注入两条策略:
- 能力边界: 当前路由是纯文本模型,不能直接接收图片,识图走 ocr.py
- 指令优先级: 技能摘要优先于通用工具指引
配置
| 字段 | 默认 | 说明 |
|---|---|---|
text | (见源码) | 注入的策略文本 |
order | 2 | section 顺序 |
官方规范参考
FAQs
全局 Agent 行为策略:向所有会话注入「纯文本模型能力边界(识图走 ocr.py,不用 read_image)」与「指令冲突时技能摘要优先」的独立 systemPrompt section,不受 preset persona 遮蔽
We found that dsh-agent-policy demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Package last updated on 17 Aug 2026
Related posts
Security News
Anthropic Gives Open Source Maintainers a Fast Track to Mythos Vulnerability Findings
Anthropic’s free OSS Scanner uses Mythos and other Claude models to find open source vulnerabilities and send maintainers reports with proposed fixes.
By Sarah Gooding - Oct 15, 2026
Security News
Front Lines Podcast: What Founders Get Wrong When Pitching CISOs
On Front Lines’ Early Adopters: CISO podcast, Andrew Becherer shares lessons from Datadog, weighs the long-term costs of AI-built tools, and explains how founders can actually gain a CISO’s trust.
By Jerod Santo - Oct 14, 2026