chore(技能): 浏览器起法收敛为「会话后台任务」＋ 关窗即停手；补索引与自测清理

- browser-harness/SKILL.md：§1 起法整段重写为「只允许这一种 —— 本会话的后台任务」（字面命令／
  为什么只许这一种／守卫语义／已知代价／起不来对照表）；§3 补一条排障 —— 认进程命令行与它自己的日志，
  ⛔ 别信 pid 父链；**「删掉脚本」≠「停掉进程」**（依据 2026-10-10 实测：孤儿守卫在脚本已删后仍把浏览器拉回）
- browser-harness/agent-workspace/bh_chrome_keepalive.py：守卫语义分两档 —— Chrome 正常关窗(rc=0) ⇒ 停手退出；
  异常退出(rc≠0) ⇒ 重拉（依据：用户手关被无条件拉回，连关三次弹三次）
- session-mechanism/scripts/selftest.py：删掉重复定义的 `t_check_cooldown_no_pileup`（两段逐字相同）；自测 PASS 109 / FAIL 0
- session-mechanism/references/humanizer-en/SKILL.md：与顶层 `humanizer` 技能同名冲突 ⇒ 去掉本包这份的注册
  （`user-invocable: false` ＋ `disable-model-invocation: true`），6 个文件正文一字未动
- session-mechanism/references/01-文档索引.md：补登 `04-决策方法论.md`／`dsh-decision-method/`／`作业规矩/`／`humanizer-en/`

session-mechanism/references/humanizer-en/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: humanizer
 description: Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when editing a Markdown file in place. Triggers on phrases like "humanize this", "make this sound less AI", "make this sound human", "remove AI tells", "does this read like ChatGPT", and "rewrite so it does not sound AI-generated". Pure Markdown, zero dependencies, no network calls.
-user-invocable: true
+user-invocable: false
+disable-model-invocation: true
 argument-hint: '"your text" [--mode detect|rewrite|edit] [--voice casual|professional|technical|warm|blunt] [--file path/to/file.md] [--aggressive] [--iterate N] [--score] [--purpose essay|email|marketing|technical|general] [--openings N] [--ignore-code] [--ignore-quotes]'
 allowed-tools:
   - Read