Borrowing it
Nothing to install: this file belongs to Chael-Chael/dsh-reference-anything. 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/Chael-Chael/dsh-reference-anything/main/AGENTS.mdgit clone --depth 1 https://github.com/Chael-Chael/dsh-reference-anythingWrote 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/chael-chael/dsh-reference-anything/agents-md)<a href="https://agentmods.dev/instructions/chael-chael/dsh-reference-anything/agents-md"><img src="https://agentmods.dev/badge/instructions/chael-chael/dsh-reference-anything/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/chael-chael/dsh-reference-anything/agents-md"><img src="https://agentmods.dev/badge/instructions/chael-chael/dsh-reference-anything/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 | $0.01021 | $0.01021 |
| Opus 5.5 | $0.00408 | $0.00408 |
| Sonnet 5.5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
dsh-reference-anything 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 6d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 工作入口
先读本文件与 LESSONS.md，再按任务读取对应文档，不一次性加载整个仓库。
| 当前任务 | 必读入口 |
|---|---|
| 开始/继续开发 | 开发闭环与命令、代码与验收标准 |
| 定位改动、找调用方和测试 | 子系统地图 |
| 设计引用返回协议、精简本地 Agent 输出 | 引用协议重设计（协议契约与实施入口） |
| 规划网页 AI 引用改进 | 未来方案：网页 AI 引用（待实施；阅读不代表授权开发） |
| 查看后续方案与待办 | Ideas 清单 |
| 启动、build、浏览器测试、Desktop 同步 | 四环境约定 |
| 修改 UI | 设计规范、浏览器验收 |
| 功能测试失败 | 官方 Session Log 诊断：导出失败会话、分析事件链、修复并保留复测证据 |
| npm 发布 | 发版规程，使用 agent:release:prepare / agent:release:gate |
| 输出/更新验收报告 | 累计完整报告要求：交付本版本全部记录，不能只报本轮增量 |
| README、发布说明、新功能 GIF | 发布素材与用户审稿、Release 正文模板；Agent 完成初稿和录制，最终文字必须交用户审核 |
| 任务完成、返工或复盘 | 复盘与经验晋升 |
| 制作 GIF | 演示流程 |
不变量
- 用户明确的产品决定和环境分工优先；不混用演示、用户亲测、Desktop 和 Agent 测试环境。
- 保留已有未提交改动。修 bug 先复现，遍查共享实现的调用方，再修根因；只改任务必要范围。
- 本地 @ 引用只读；导入必须单独确认。用户于 2026-10-18 授权在 agent-browser-test 中引用其实际对话/来源并使用其 DeepSeek 官方账号模型额度发送验收消息；按发版规程执行真实读取与回答核验，其他普通菜单测试仍不发送，结束清空草稿。
- 本地历史会话不再要求逐对话引用授权；每次预览、正文、工具记录、搜索、图片读取均检查当前来源开关与允许目录，关闭来源后旧引用也不可新读取。保留真实路径与会话身份校验；不放宽 DSH 沙箱、不改变导入确认。已进入对话的历史内容不会因关闭来源自动撤回。
- 每次 build 同步刷新 agent-browser-test 和 Desktop；自动化 UI 实验放在前者，Desktop 做实际窗口验收。
- 没跑的写 NOT_RUN / BLOCKED，不伪造证据；构建成功不能代替真实 UI 或 npm 包验收。
- 每次发版逐项验证所有已提供功能，不轮换抽样。失败先查官方 Session Log（无会话时查宿主/浏览器日志），根因修复并真实复测后才可标 PASS。
- 官方日志 ZIP 及解压副本用完即清理：先保留脱敏诊断/复测报告，再删除本次临时副本并核实；不删除 DSH 原始会话或待发布 npm 包。
- 长期项目信息写入对应仓库文档并保持此入口可达，不只存个人记忆。稳定规则不复制多份，复盘教训进入 LESSONS.md。
- 发布、推送、合并按用户实际授权执行；实现本流程不代表授权发布 npm 或创建定时任务。
- 发布前由 Agent 主动更新中英文 README、发布说明/功能卡并制作适用的新功能 GIF；汇总最终文字及演示预览交用户明确审核，不得自行代审。审核后的文字或候选内容改变则重新交审。
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.
- 6d ago Changed · -2 lines · -81 tokens per session 16a5ef550b5f
- 14d ago Changed · +1 lines · +23 tokens per session fdeae160b7e2
- 16d ago Changed · +2 lines · +80 tokens per session d1d3448a2d00
- 17d ago Changed · +1 lines · +39 tokens per session bcc9b20f3b69
- 18d ago First seen · 32 lines · 960 tokens per session scan A 3bc134e5e4cd
dsh-reference-anything AGENTS.md is an instructions file published in the GitHub repository Chael-Chael/dsh-reference-anything (27 stars, last pushed 7d ago), licensed MIT. It adds 1,021 tokens to every session, about $0.0041 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 2026-10-19.
dsh-reference-anything AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dsh-reference-anything AGENTS.mdChael-Chael/dsh-reference-anything | Instructions file | 27 | 7d ago | MIT | A | 1,021 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |