browser-session-handoff
Skill11 starsChanged 54 days agoMITView on GitHub
按站点加密迁移已授权的 Chrome 登录 Cookie。
In this repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- deep-researchSkill
- find-skillsSkill
- github-desktop-releaseSkill
- gpt6-pro-consultSkill
- santa-methodSkill
- skill-creatorSkill
- skill-lifecycle-managerSkill
- yq-clear-contextSkill
- yq-pre-push-checksSkill
- yq-simplify-codeSkill
- yq-stable-testsSkill
- yq-windows-trash-cleanerSkill
- electron-developmentSkill
- frontend-designSkill
- netlify-cliSkill
- yq-vps-vpn-deploySkill
- data-scraper-agentSkill
- docxSkill
- general-videoSkill
- github-readme-visualsSkill
- html-design-polishSkill
- hyperframes-animationSkill
- hyperframes-audioSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-keyframesSkill
- hyperframes-registrySkill
- hyperframesSkill
- imagegenSkill
- impeccableSkill
- jianying-editorSkill
- make-interfaces-feel-betterSkill
- media-useSkill
- pdfSkill
- ppt-nanoSkill
- pptxSkill
- remotion-video-creationSkill
- ui-ux-pro-maxSkill
- wechat-articleSkill
- xlsxSkill
- yq-editorial-presentation-htmlSkill
- yq-ui-checksSkill
- yq-article-style-imitationSkill
- yq-doc-maintenanceSkill
- yq-remove-reasoning-leaksSkill
- yq-technical-writingSkill
- yq-translate-docsSkill
- contract-reviewSkill
- creating-financial-modelsSkill
- dxy-task-clarifySkill
- healthcare-cdss-patternsSkill
- healthcare-emr-patternsSkill
- healthcare-eval-harnessSkill
- healthcare-phi-complianceSkill
- xhs-pharma-social-listeningSkill
The file
Files
Chrome 登录状态交接
用于把用户已授权的 Chrome 登录状态交给其指定设备或 Agent。先确认源 Chrome 配置、目标配置、允许操作的站点,以及接收方能打开的独立口令交付渠道。已经接入的官方 API 或 OAuth 继续使用原接入方式。
导出
- 在源配置打开已授权站点的 HTTPS 后台,确认账号及登录状态。优先使用当前浏览器工具已获准的按标签页读取能力。若提供 CDP,按 操作手册 调用带显式 URL 的
Network.getCookies。仅在本地受控运行时接收返回值。 - 逐站点筛选第一方、未分区、未过期的 Cookie。保留域、路径、HostOnly、Secure、HttpOnly、SameSite 和会话期限。若工具未提供合规读取能力,可使用随附扩展,在 Chrome 中由用户确认该站点权限。权限被拒绝时停止该站点。
- 在内存中规范化和加密。每站点生成一份经认证的密文,用独立随机 salt 和 IV,并把格式及站点绑定到认证数据。将已生成文件回读解密,在内存中与原记录比对。
- 将各站点密文、匹配的导入器和通用说明合为一个私下交接的 ZIP。检查清单并记录 SHA-256 和各站点的预期记录数。通过已确认的独立渠道交付可用口令,让接收方确认能在目标设备读取。源设备的系统凭据存储只作为恢复副本。
导入与验收
在目标 Agent 实际使用的专用 Chrome 配置中导入。检查归档哈希、站点和格式。保留配置中原有的 Cookie。打开相应平台后台,用只读方式核对账号和评论入口。平台要求重新验证时,由用户在目标设备完成。
交接完成需要目标端确认收到 ZIP 和口令,并用收到的口令逐站点解包核对预期记录数。缺少确认时报告「待签收」或「待解包验收」。另行记录写入和后台登录结果。交接记录只写状态、数量和操作人可识别的口令条目名称。Cookie 值、口令和真实密文留在获准的私有渠道。
操作手册包含字段映射、单 ZIP 清单、目标端操作和故障分流。随附本地扩展支持抖音、小红书、知乎和 TikTok。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

