Borrowing it
Nothing to install: this file belongs to Nwflower/dsh-chat-import. 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/Nwflower/dsh-chat-import/main/AGENTS.mdgit clone --depth 1 https://github.com/Nwflower/dsh-chat-importWrote 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/nwflower/dsh-chat-import/agents-md)<a href="https://agentmods.dev/instructions/nwflower/dsh-chat-import/agents-md"><img src="https://agentmods.dev/badge/instructions/nwflower/dsh-chat-import/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/nwflower/dsh-chat-import/agents-md"><img src="https://agentmods.dev/badge/instructions/nwflower/dsh-chat-import/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 | $0.03190 | $0.03190 |
| Opus 5.5 | $0.01276 | $0.01276 |
| Sonnet 5.5 | $0.00638 | $0.00638 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
dsh-chat-import 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 3d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
dsh-chat-import 是 DeepSeek Harness(DSH)插件:把 32 种来源格式(含 DSH 自身的会话日志)的聊天记录导入为可继续的 DSH 会话,支持反向导出。
原则
- 本仓库只做插件,不修改 DSH 引擎、apiproxy 或官方 UI 包。
- 宿主侧零构建,纯 ESM,
lib/就是发布产物。唯一的例外是浏览器侧的 bundlelib/client.js:它由src/client/的分片组装而成,外加白名单内联的lib/纯模块,组装器是scripts/build-client.mjs。之所以要组装,是因为 DSH 客户端加载器没有相对 require,产物必须是一个单文件(见docs/architecture.mdD7)。 - 同口径逻辑只留一份,来源清单由一张表派生(
docs/architecture.mdD21):写新代码之前先找共用件,不要复制相邻来源的实现。 - 根目录只放发布到 GitHub / npm 的文件;本地工程文件收进
dev/,不提交。 - 公开文档(README 双语、docs、CHANGELOG、ROADMAP)不出现 REQ、issue 号一类内部编号。
- 结构性改动之前先读
docs/architecture.md(架构决策与权衡),不要违背已记录的决策。确实需要推翻某条决策时,先在该文档里说明旧决策为什么不再成立。 - 冲突时按这个顺序取舍:用户当次的指令 > 仓库代码现状 > 本文件 >
docs/。被当次指令推翻的约定要不要回填进文档,由用户决定,AI 不现场猜。
体量停止线(机械触发,不靠判断)
lib/下任何手工维护的源文件超过 1000 行(convert / export 纯函数层放宽到 800 行):停止往里加新功能,先写一份拆分提案等用户确认;提案批准之前,该文件只修 bug。拆分方向见docs/architecture.mdD6。lib/client.js是生成产物,不受这条限制,同样的界线作用在src/client/的各个分片上。- 同一个来源的解析或发现逻辑出现第 3 处副本时,同样停下来提案,不写第 4 处。
test/*.test.mjs单个文件超过 1200 行:同第一条,先拆再往里加用例。test/_support/与test/fixtures/不受这条限制。测试面另有一项机械检查(npm run check:tests):每个来源格式至少有一个测试锚点。- 这几条停止线给执行模型用,触发即停,不必先判断「是否值得」。
命令
npm test # node --test 跑 test/*.test.mjs
npm run lint # eslint
npm run coverage # 覆盖率护栏:line >= 75%
npm run check:coverage # 覆盖率结构:逐文件下限 + 逐目录均值下限(只看全局数字会盖住单文件的空洞)
npm run check:linux # 跨平台路径纪律静态检查
npm run check:leaks # 敏感信息泄漏扫描
npm run check:links # 文档相对链接检查
npm run check:tests # 测试面纪律:每个来源有测试锚点 + 单测文件停止线
npm run release:notes -- --version x.y.z # 校验并预览该版本的发布说明(release workflow 用的是同一份)
npm run build:client # 由 src/client/ 的分片组装 lib/client.js(改过面板必须重跑)
npm run build # 发布面自检:client bundle 是否最新、files 是否完整、入口可达的模块是否都在 files 里、语法、lockfile
仓库布局
lib/index.mjs是插件入口(package.json的 main),只做组装。lib/convert/*与lib/export/*是纯函数层,不读盘、不 import 宿主模块,有测试守护。共用件在convert/util.mjs、convert/ir.mjs、convert/core.mjs与export/common.mjs。设计同源的来源共用一个转换引擎,各自只留差异描述(pi 与 omp 共用convert/pi-family.mjs,见 D21)。convert/index.mjs只转出经它导入的名字;export/index.mjs是公开子路径./export.mjs。lib/sources/*是按来源命名的 host 面适配器,与lib/convert/<src>.mjs一一对应;SQLite 读取统一经sources/sqlite.mjs。- 导入编排分布在几处:
lib/import-core.mjs是单会话源与多会话源共用的状态机,lib/import-state.mjs管已知记录与「源未变」短路径,lib/import-batch.mjs管文件收集与批量计数,lib/import-variants.mjs管 chatgpt / grokbuild / hermes / kimi 等特殊形态;registry 在lib/imports.mjs。 lib/discovery.mjs是门面,实现放在lib/discovery/:registry.mjs是来源描述符表,其余是按来源族划分的扫描器模块。lib/tools.mjs是门面,负责注册与档位对账,工具定义都在lib/tools/。import_chat的分发器与来源表在lib/toolkit.mjs。工具 schema 只放一次调用需要的东西,长文说明在docs/IMPORT-GUIDE.md,由运行时 skilldsh-chat-import-usage按需加载。lib/client.js是浏览器面板的 bundle,属生成产物,不要手改。源在src/client/,组装器是scripts/build-client.mjs。bin/dsh-chat-import.mjs是独立 CLI。docs/放面向最终用户的文档(含 ROADMAP、CONTRIBUTING)。test/放测试与合成 fixtures,假宿主这类测试共用件在test/_support/,不要在测试文件里另写一份。dev/、node_modules/、.dsh-file-claim/不入库。
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.
- 3d ago Changed 24f50cccaa5d
- 4d ago Changed faa30059196b
- 8d ago Changed · +328 tokens per session 2c2795ba8bbf
- 10d ago Changed · +1 lines · +161 tokens per session 4a5fc675bcef
- 20d ago Changed · +3 lines · +196 tokens per session 5c6eac506ada
- 22d ago Changed · +5 lines · +574 tokens per session 021f11212ae2
- 24d ago Changed · +32 tokens per session 4b052eceb698
- 29d ago Changed · +45 tokens per session 7a66cab1f9b5
- 1mo ago Changed · +12 lines · +423 tokens per session 918d5fe0edb2
- 1mo ago First seen · 68 lines · 1,431 tokens per session scan A 4e95811327bd
dsh-chat-import AGENTS.md is an instructions file published in the GitHub repository Nwflower/dsh-chat-import (259 stars, last pushed 3d ago), licensed MIT. It adds 3,190 tokens to every session, about $0.0128 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 2026-08-30.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.