Files
mcn-short-video/project/短视频脚本创作/V1.0/subskill/browser-harness/AGENTS.md
T
maogeigei afbe52e809 refactor(skill): browser-harness 移出 mcn-dou-analysis 挂到主技能 subskill 下
- 目录移动: subskill/mcn-dou-analysis/subskills/browser-harness → subskill/browser-harness (envs 完整保留, git 仅跟踪源码)
- mcn-dou-analysis/SKILL.md browser-harness 依赖红线: 技能本体位置更新为 主技能 subskill (09-02 调整)
- references/浏览器搜索抖音账号操作规范.md: 环境说明+技能本体两处更新新路径
- V1.0/SKILL.md: 新增「外部技能依赖: 浏览器工具(browser-harness)」小节登记新位置
2026-09-02 10:27:44 +08:00

1.3 KiB

browser-harness is a thin layer that connects agents to browsers via an editable CDP harness.

Code priorities

  • Clarity
  • Precision
  • Low verbosity
  • Versatility

Overview

Core code lives in src/browser_harness/:

  • admin.py — daemon lifecycle, diagnostics, updates, profile management
  • daemon.py — the long-lived middleman process between the browser and the agent
  • helpers.py — CDP wrapper and core browser primitives auto-imported into -c scripts
  • run.py — the browser-harness CLI

SKILL.md tells agents how to use the harness and CLI. install.md tells agents how to install it, attach a browser, and troubleshoot. In this checkout, invoke the current source with ./browser-harness; do not use a globally installed browser-harness binary.

For recording or video tasks, follow SKILL.md and interaction-skills/make-video.md. A natural request to show, record, or demo the work opts in; significant work alone does not. Keep the exact path returned by start_recording() and never reenact a finished task.

An agent operating the harness only edits inside agent-workspace/:

  • agent_helpers.py — task-specific browser helpers the agent adds
  • domain-skills/ — skills the agent writes and reads

Contributing

Consider what is really needed. Prefer the smallest diff that fixes the bug.