Borrowing it
Nothing to install: this file belongs to omdsh-dev/dsh-genui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/omdsh-dev/dsh-genui/main/AGENTS.mdgit clone --depth 1 https://github.com/omdsh-dev/dsh-genuiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/omdsh-dev/dsh-genui/agents-md)<a href="https://agentmods.dev/instructions/omdsh-dev/dsh-genui/agents-md"><img src="https://agentmods.dev/badge/instructions/omdsh-dev/dsh-genui/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/omdsh-dev/dsh-genui/agents-md"><img src="https://agentmods.dev/badge/instructions/omdsh-dev/dsh-genui/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00742 | $0.00742 |
| Opus 5.5 | $0.00297 | $0.00297 |
| Sonnet 5.5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
dsh-genui AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
dsh-genui 协作守则
面向在本仓库里改东西的 agent。只写会被反复违反、且有具体代价的规则；风格偏好不进来。
汇报改动：默认用 compare
只要回答里要呈现同一处界面的前后差异，就用 compare 节点，不要并排两张 markdown 图片、也不要表格：
```dsh-ui
{"title":"改了什么","items":[{"type":"compare","mode":"side","height":360,
"before":{"src":"/api/file?path=<绝对路径，percent-encoded>","label":"改动前","caption":"…"},
"after":{"src":"/api/file?path=<绝对路径，percent-encoded>","label":"改动后","caption":"…"}}]}
```
- 本机截图走宿主已鉴权的
/api/file?path=路由，不用起服务、不用搬文件。 - 为什么不是两张图：读者得自己推理"哪边是改前"；
compare的标签常显，还能拖动分割线看细节。 - 规则失效过一次（当天写进 SKILL，第一次汇报就没用），所以放在这个每次都会加载的位置。
- 没有截图时用文字讲清楚，不要用表格凑出一张"看起来有结构"的回答。
视觉改动：没渲染过就不算完成
- 视觉/布局/交互改动必须在真实浏览器里看过再声称完成。本地有固定管线：
.e2e-artifacts/pw/（playwright-core）+.e2e-artifacts/.browsers/（chromium），PLAYWRIGHT_BROWSERS_PATH指过去即可截图。 - 导出页（standalone artifact）没有宿主
--dsw-*token：判断颜色/表面/字体时必须把宿主 token 一起注入，否则看到的是兜底色（过去因此误判过diagram是"白板"）。 - 断言要随行为变化说明新规则是什么，不要只把期望值改成实际值。
新增节点：一份清单
spec.ts（类型 + union）→ genui-runtime/schema.ts（字段 + 嵌套记录）→ guard.ts（repair + 校验）→ blocks/render-node.tsx（dispatch）→ 组件 + CSS module → i18n/{en,zh}.ts（键集必须一致）→ SKILL.md → 测试（渲染 + 交互 + guard）。
系统提示里那段组件清单有 3400 字符硬预算（tests/plugin-genui.spec.ts 会拦），新增类型先看够不够位置。
隐藏与禁用：必须交代"值怎么办"
任何让控件消失或不可用的改动，同时回答两个问题：
- 值还提交吗？（
when：不提交，也不占"已填"名额） - 读者看不见的旧值会不会被当成有效输入？（不能）
只做视觉隐藏、不处理提交语义，等于给用户塞一个陷阱。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 43 lines · 742 tokens per session scan A 810a05001e31
dsh-genui AGENTS.md is an instructions file published in the GitHub repository omdsh-dev/dsh-genui (832 stars, last pushed yesterday), licensed MIT. It adds 742 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.