Borrowing it
Nothing to install: this file belongs to XJungit/omdp. 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/XJungit/omdp/master/AGENTS.mdgit clone --depth 1 https://github.com/XJungit/omdpWrote 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/xjungit/omdp/agents-md)<a href="https://agentmods.dev/instructions/xjungit/omdp/agents-md"><img src="https://agentmods.dev/badge/instructions/xjungit/omdp/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/xjungit/omdp/agents-md"><img src="https://agentmods.dev/badge/instructions/xjungit/omdp/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 | $0.02124 | $0.02124 |
| Opus 5.5 | $0.00850 | $0.00850 |
| Sonnet 5.5 | $0.00425 | $0.00425 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
omdp 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — OMDP 仓库开发规范
本文档约束任何在 D:\WorkSpace\omdp 仓库内工作的 agent(含后续会话)。
仓库 = @omdp/* 系列 DSH 插件 monorepo(当前活跃:dsh-connector、
dsh-key-fallback、dsh-archived-sessions;历史归档在 archive/,
含 2026-10-18 起停用的视觉插件 dsh-vision-bridge)。
工作前提(先读再做)
- 动手改动任何 DSH 插件前,先研读 DSH 源码/官方文档/相关插件真实实现, 禁止凭印象或猜 API(维护/优化/编写插件铁律)。
- 删除任何文件前,逐条列出完整绝对路径核对;有价值先备份;删后立即验证。
- 本仓库是普通 JavaScript(无构建步骤),本地优先用
link:安装调试。
规范 1:文档随插件同步更新
插件有任何更新(源码、配置、版本号、行为变化、发布动作)时,必须主动同步更新所有相关文档:
- 对应插件自己的
README.md(及双语README.zh-CN.md)——功能、版本、Requirements; - 根
README.md——插件列表/版本号/目录树有变化时; docs/下相关文档——plugin-compatibility.md(兼容性矩阵)、npm-publish.md(发布流程)等;- 若改动产生了新的坑或经验,同时遵守规范 2 追加笔记。
判定标准:一次插件改动完成后,git 提交里应同时包含「代码/配置改动」与 「所有受影响文档更新」,不允许只改代码不带文档提交。
规范 2:教训经验主动沉淀为文档笔记
在维护、创建、修改插件过程中产生的教训、经验、坑、决策依据、可复用结论, 都要在工作完成后主动写入文档笔记,结构为三层:
notes/ # 第一层:文档笔记
└── <yyyy-MM-dd>/ # 第二层:时间(按日期排序)
└── <category>/ # 第三层:按功能/主题分类
└── <描述性名称>.md # 一篇笔记一个主题
- 时间层:
YYYY-MM-DD格式(如2026-08-28/),自然排序即时间线。 - 分类层(第三层),按主题归类,先有稳定分类再用新分类:
dsh-compat/— DSH 版本适配/兼容性排查plugin-dev/— 插件开发/重构/架构dsh-internals/— DSH 源码研究(API 契约、事件载荷)deploy/— 部署、发布、npmdebug/— 排障记录(根因→修复→验证)tooling/— 环境、工具链、git/npm/sandbox 坑
- 一篇笔记一个主题,文件名用简短描述(kebab 或直接中文皆可); 内容至少含:背景/问题 → 结论或根因 → 可复用要点(含相关文件或命令)。
- 写完笔记在当次回复中提一句,随同一提交入库。
笔记索引
notes/README.md 维护目录结构与命名约定(见上)。笔记不需要全局索引——
按「时间 → 分类」定位即可,必要时在 docs/ 里放跨笔记的汇总文档。
规范 3:版本声明严谨性(peerDependencies 用「三元组区间」放行)
插件声明对 DSH 生态包(@deepseek-ai/*)的 peerDependencies 时,用按
[major,minor,patch] 三元组划分的闭区间,上界必须带 -0:
- ✅
>=0.1.7-rc.1 <0.1.8-0 || >=0.2.0-rc.1 <0.2.1-0(每个已实测三元组一段,||串联) - ✅
>=0.2.0-rc.1 <0.2.1-0(实测 rc.1 ⇒ 自动放行 rc.2 / rc.3 / 正式版0.2.0) - ❌
0.1.7-rc.1 || 0.1.7-rc.2 || 0.2.0-rc.1(逐版本枚举:每发一个 rc 都要改声明 + 重发包) - ❌
>=0.1.0-rc.6 <0.2.0、^0.1.0-rc.6(跨 minor 的开放范围,覆盖未测版本)
🔴 上界必须写 <下一 patch>-0,绝不能写 <下一 patch>:
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.
- 22d ago Changed · +2 lines · +64 tokens per session aecfa209cee5
- 1mo ago Changed · +35 lines · +847 tokens per session 9b6e17a71d4b
- 2mo ago Changed · +16 lines · +303 tokens per session 5f2c0dc78d31
- 2mo ago First seen · 58 lines · 910 tokens per session scan A 66519e0fa5d3
omdp AGENTS.md is an instructions file published in the GitHub repository XJungit/omdp (1 stars, last pushed yesterday), licensed MIT. It adds 2,124 tokens to every session, about $0.0085 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 2026-08-31.
omdp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omdp AGENTS.mdXJungit/omdp | Instructions file | 1 | yesterday | MIT | A | 2,124 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |