Borrowing it
Nothing to install: this file belongs to Aisland-SJL/dsh-worktable. 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/Aisland-SJL/dsh-worktable/main/AGENTS.mdgit clone --depth 1 https://github.com/Aisland-SJL/dsh-worktableWrote 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/aisland-sjl/dsh-worktable/agents-md)<a href="https://agentmods.dev/instructions/aisland-sjl/dsh-worktable/agents-md"><img src="https://agentmods.dev/badge/instructions/aisland-sjl/dsh-worktable/agents-md.svg" alt="Measured on agentmods" 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 | $0.06776 | $0.06776 |
| Opus 5 | $0.03388 | $0.03388 |
| Sonnet 5 | $0.01355 | $0.01355 |
| Haiku 4.5 | $0.00678 | $0.00678 |
Grade A, and why
dsh-worktable 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 today.
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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dsh-worktable 项目规则
工作台容器插件:侧边栏里收纳 agent 级项目的「应用抽屉」。纯增量,不替换官方插件。
协作方式(用户定案,最高优先级)
与全局
~/.dsh/AGENTS.md同步;外部 Agent(如 Codex)不加载全局文件,故此处保留全文。
- 设计先给最小版:任何 UI/文案/方案先交「最少元素」版本给用户拍板,确认后再增量; 默认克制——没有存在理由的元素不放;不一次搭「完整版」再返工。
- 长任务拆 checkpoint:每个可验收阶段完成后停下汇报,等用户确认再进下一段; 不一口气跑完长任务。
- 对外动作永远先审:发布、评论、给观众的内容、任何公开操作,一律先给用户过目, 用户不点头不执行。
- 改完必读回:每次编辑后读回改动处的完整行/段落,确认无残留、无断尾 (教训:改一半的 URL 留下旧尾巴,被复审抓为发布阻断)。
- 验收用最终产物,不用中间信号:任何交付物(tgz、命令、文档、UI)的验收动作必须是 「解包 / 复制 / 实跑用户路径」;「构建成功」「bundle 里有字符串」「退出码 0」不算验收。
- 发布前自跑最终产物清单:干净目录安装、最终包逐文件核对、双资产哈希、关键行逐字 grep —— 先自查再报告,不等外部复审来抓。
- 发布包验收=结构检查 + 真实安装,两道都保留:npm pack 标准格式(package/ 前缀 + files 白名单精确 7 文件,不含 src/、不含 .map)与「独立目录 npm install + import() 断言」 缺一不可。教训:v0.3.0 手工 tar 出无前缀平铺包且误卷源码树,「解包核对(文件都在)」发现不了, 只有 npm install 复现失败;「文件都在」 ≠ 「消费方(npm/dsh plugin add)能装」。
- 声明可证伪,不许写满:验收结论只写已验证范围。「通知全覆盖」「等价端到端」这类表述会被 反向检查打脸——只写「版本比较逻辑上重新激活」「验证了安装与服务端模块导入」。
- 同 tag 资产不可覆盖(用户已拍板):坏包处理 = 发新版本号 + 旧 Release 正文标注问题, 默认不替换旧资产;仅经用户明确批准的紧急补救例外,且须:不改名(保持原 URL 名)、 用已验证包、不删不盖现有资产、上传后从完整 URL 下载核对、旧 Release 注明补救经过。
边界
- 插件包根目录 =
01_content/;本仓库其余目录是项目文档与本地工具。 - 不替换、不禁用任何官方插件(ui-sidebar / ui-workspace / ui-layout)。
- 所有状态只存 localStorage(键
dsh.worktable.view.v1),不读写工作区文件。 - dsh-travelatlas 是入驻项目而非本仓库的一部分;协议见
02_process/PRD.md§5.3/5.4。 - 平台边界:Windows 是当前完整验证平台;macOS 为实验性支持(核心文件路径代码已做跨平台适配,
尚未真机端到端验证)。路径拼接必须走
pathutil.tshelper 或 NodepathAPI,不手写分隔符。
构建与验证
cd 01_content
npm install
npm run build # lib/index.js + lib/client.js
node --check lib/index.js
- 客户端 bundle 必须保持
window.__ModuleLoader__.load握手与 external react/@deepseek-ai/*。 - 变更视图状态结构时同步更新 PRD 的持久化说明。
- 构建必须
cd 01_content后执行:误在仓库根跑会把 lib 写到仓库根lib/,宿主仍加载01_content/lib旧 bundle,出现「改完不生效」假象(已有教训,见工作日志)。 - 发布打包唯一入口 =
npm run pack(01_content/release-prep.mjs):身份断言(package/manifest/cordis.patch.yml 严格结构)→ 版本一致性 → 构建(cwd 固定 01_content)→ node --check → npm pack → 结构清单断言(package/ 前缀 + 精确 7 文件, 无 src/、无 .map)→ 独立临时目录 npm install + import() 断言(apply 函数/inject 含 webServer+sessions/name/ HEALTH_PATH/包内双 bundle 版本)→ 客户端工厂求值门禁(ModuleLoader 恰好注册一次 + ID 校验 + 精确外部依赖 白名单 react/react/jsx-runtime + apply/inject 断言)→ 分栏锚点 DOM 回归(8 场景,评估安装产物 lib/client.js; 测试接受包路径参数)→ 服务端数据目录回归(3 组场景,评估安装产物 lib/index.js)→ dist/v版本号/ 双资产(终态恰好 2 文件 + 双 SHA 同源)。 脚本零 git/gh 动作,发布上传由 gh 手动完成。 发布禁止裸 npm pack 或手工 tar 生成发布包;脚本从仓库任意目录调用均安全(以自身位置解析)。 - 配套检查入口:
npm run test:gate= 工厂门禁 10 个失败/正向用例;node 04_test/anchor-dom.test.mjs [lib/client.js 路径]= 分栏锚点 8 场景(缺省用工作目录构建产物);node 04_test/server-home.test.mjs [lib/index.js 路径]= 数据目录解析 3 组场景(子进程隔离夹具; 突变体验证法:把 loadPkg 兜底的 baseDshHome() 故意改回 resolveDshHomeSafe() 恢复循环,测试必须红)。npm run verify:remote -- --expect-sha <release-prep 输出的 SHA> [tag]= 发布后只读核对 (远端固定名+版本化双资产文件名/结构/版本/双 SHA 同源且等于本地验收 SHA/安装/导入; 远端只读,本地仅临时目录)。上传后必须跑 verify:remote 并用 --expect-sha 比对, 防「双资产同错」;tag 模式断言 tag==='v'+包内版本。
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.
- today Changed · +13 lines · +706 tokens per session cd61439df350
- 2d ago Changed · +29 lines · +1,207 tokens per session a20b2ff5762d
- 7d ago First seen · 194 lines · 4,863 tokens per session scan A 9a8a743cbcdf
dsh-worktable AGENTS.md is an instructions file published in the GitHub repository Aisland-SJL/dsh-worktable (502 stars, last pushed today), licensed MIT. It adds 6,776 tokens to every session, about $0.0339 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.