Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/aerozb/postman-cn/agents-mdgit clone --depth 1 https://github.com/Aerozb/Postman-cnWrote 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/aerozb/postman-cn/agents-md)<a href="https://agentmods.dev/instructions/aerozb/postman-cn/agents-md"><img src="https://agentmods.dev/badge/instructions/aerozb/postman-cn/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 | $0.07398 | $0.07398 |
| Opus 5 | $0.03699 | $0.03699 |
| Sonnet 5 | $0.01480 | $0.01480 |
| Haiku 4.5 | $0.00740 | $0.00740 |
Grade A, and why
Postman-cn 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Postman 汉化工具链维护指南
本文件是本项目对 AI 助手（Claude Code、Codex 等）的权威说明。任何自动化助手打开本项目都应先读本文件。
CLAUDE.md通过@AGENTS.md导入本文件，内容以本文件为准。面向普通人类用户的使用说明见README.md。
1. 这个项目是什么
给 Windows 版 Postman 桌面端做中文汉化的补丁工具链。做法：解包 Postman 的 resources/app.asar → 注入运行时汉化脚本 zh-localize.js → 重新打包，不修改用户数据。
汉化是运行时 DOM 翻译：zh-localize.js 在页面里用 MutationObserver 监听 DOM，把英文文本节点和属性按词典替换成中文。不是改源码字符串，因此对 Postman 版本升级有较好的兼容性。
关键事实：Postman 的请求编辑器等界面从 desktop.postman.com 远程加载，服务端会随时下发新的英文文案。因此没有一劳永逸的 100% 覆盖——必须周期性审计、补词条。这个工具链的核心价值就是让这个"发现漏翻 → 补词条 → 验证"的闭环尽量自动化。
2. 目录布局
Desktop\Postman\ ← Postman 官方 Squirrel 安装目录（勿动其官方文件）
Postman.exe Update.exe
app-12.26.3\ ← 当前版本；resources\app.asar 是补丁目标
resources\app.asar.original ← 首次安装时自动备份的英文原版
packages\ ← 官方安装包 + RELEASES
postman-zh-workspace\ ← 所有非官方内容都在这里
Postman-cn\ ← 本工具链（= 本项目根）
payload\
zh-localize.js ← 汉化主体：词典 + 翻译逻辑 + 收集器（唯一的"数据源"）
zh-auth-webview-preload.js ← 登录/授权 webview 的预加载汉化
zh-version-check-main.js ← 汉化版本更新检查（主进程侧，走 IPC）
scripts\
统一入口.ps1 ← 命令分发器（唯一实现入口）
internal\ ← 安装、启动、停止等内部 PowerShell 实现
audit\ ← 点击、悬停、右键等 CDP 审计
runtime\ ← 运行时收集和页面探测
data\ ← 静态扫描和译文合并
maintenance\ ← 发布脚本
.agents\skills\ ← skill 正文（`.agents/skills/` 是 Codex 的约定位置）
.claude\skills\ ← 同名薄指针，只为让 Claude Code 也能发现该 skill；
正文不复制，改 description 时两处要同步
docs\ ← 汉化教程、维护指南，以及第 8 节索引里的三份正文
AGENTS.md CLAUDE.md README.md
postman-zh.bat ← 普通用户唯一入口（双击）
_generated\ ← 审计、扫描和翻译临时产物（可再生，可被随时删除）
_release\ ← `publish` 生成的正式发布包（跑过 publish 才出现）
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 · +2 lines · +150 tokens per session 7b801efa8db9
- yesterday Changed · -110 lines · -3,152 tokens per session 09206758cfec
- 5d ago First seen · 352 lines · 10,400 tokens per session scan A ce6599eec3a3
Postman-cn AGENTS.md is an instructions file published in the GitHub repository Aerozb/Postman-cn (56 stars, last pushed yesterday), licensed MIT. It adds 7,398 tokens to every session, about $0.0370 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
xcstrings-crud CLAUDE.md
Claude Code instructions for Ryu0118/xcstrings-crud, covering xcstrings-crud, build & test, architecture, code style and key files.
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
DialectOS CLAUDE.md
Claude Code instructions for KyaniteLabs/DialectOS, covering kyanitelabs engineering rules, project-specific context, kyanitelabs engineering rules, organization principles and issue-driven development.
DialectOS AGENTS.md
AGENTS.md instructions for KyaniteLabs/DialectOS, covering agents.md — dialectos, public agent skill, project structure, build and testing.
KKTerm CLAUDE.md
Claude Code instructions for ryantsai/KKTerm: Constitution, Repository workflow, domain language, source-area boundaries, i18n rules, and engineering defaults live in AGENTS.md. Product terminology lives in CONTEXT.md. Read both before changing behavior or terminology.
kiwiki AGENTS.md
AGENTS.md instructions for natorus87/kiwiki, covering projekt-anweisungen, projekt-kontext, verbindliche lokalisierungsregel, regeln (automatisch geladen via .codex/rules/) and verfügbare sub-agenten.