Squashed 'docs/standards/playbook/' changes from b529012..a854534

a854534 ✨ feat(plan_progress): auto-detect env for blocked plans
0d9a8ec 🐛 fix(playbook): honor no_backup for sync
2d401fa ✅ test(templates): update prompts validation
e23474e 📝 docs(playbook): update prompts and sync notes
60ff3cd 🐛 fix(playbook): sync templates per file
816f036 ✅ test(playbook): add sync and vendor coverage
625cabb 📝 docs(memory_bank): reformat templates
2554c87 📝 docs(prompts): refresh prompt templates
6774a9d ✨ feat(plan_progress): track plan status in progress.md
73d5c26 🔧 chore(playbook): split sync_templates into sections
278750e ✨ feat(playbook): add plan progress tracking and rules updates
6efd637 🐛 fix(sync): keep agents block blank lines
ea00d43 🐛 fix(playbook): support toml without tomllib
ab0dd11 📝 docs(playbook): drop docs/plans snapshots
398696c ✨ feat(playbook): merge unified cli
d959f80 🎨 style(docs): format markdown
b4f712a 🗑️ remove(legacy): drop old scripts and tests
0c4cd0e ✨ feat(actions): add install_skills and format_md
3d1582c ✨ feat(sync): add templates and standards actions
49bbfa1 ✨ feat(vendor): add playbook snapshot generation
8cfcc25 ✨ feat(cli): parse toml config and dispatch actions
05903c3 ✨ feat(cli): add toml config and dispatch order
65d216e ✅ test(cli): add basic playbook cli tests
f0bcf54 📝 docs(plans): add unified playbook cli plan
0885309 📝 docs(plans): add unified playbook cli design
3483d8a 🔧 chore(git): ignore .worktrees dir
eb75036 🔧 chore(templates): align agent templates and docs
efb93f1 📝 docs(playbook): drop todo/confirm mentions
4a85306 🗑️ remove(workflow): drop todo/confirm artifacts
9c5ee9f 🎨 style(markdown): format docs with prettier
5a2925f 🐛 fix(scripts): repair windows script parsing
26a35e0 ✅ test(ci): update required skills list
8df3883 🐛 fix(test): skip external root doc links
b067fc1 📦 deps(skills): sync superpowers
c03cda0 🔧 chore(ci): sync from origin main
55e05cb 🔧 chore(ci): use superpowers sync script
73c97f3 🔧 chore(ci): centralize superpowers sync
945704f 🔧 chore(ci): add superpowers sync workflow
e5d2c93 🗑️ remove(skills): drop duplicate workflows
3ae9708 🐛 fix(ci): update tests for flag-only scripts
c44b9aa 🔧 chore(scripts): require flag-driven args
e4e1d14 🔧 chore(scripts): unify single-dash options
b2eb475 ✅ test(templates): add template coverage
fc230b7 🎨 style(markdown): format markdown files
8dc8924 🔧 chore(markdown): add prettier config and usage
2045dd4 ✨ feat(vendor_playbook): add apply-templates option
872d8cf ✨ feat(templates): add sync templates scaffolding
5b1ca45 📝 docs(skills): clarify todo-plan template
054967a ✨ feat(skills): add todo-plan skill
cc340f1 🔧 chore(ci): align standards-check workflow template
e9de0aa 🔧 chore(ci): drop removed skill check
e5dd7d9 🔧 fix(sync): avoid backtick expansion
087b0b9 🔧 chore(sync): align agents block across ps1/bat
9481510 🔧 chore(sync): scope agents block to existing langs
b0ca842 🔧 fix(sync): rewrite docs path in agents
c98d65c 🔧 chore(sync): rewrite agents docs paths
c33611c 🗑️ remove(skills): drop unused skills and update references
2b37860 🎨 style(markdown): format markdown files
e3ecd26 📝 docs(tsl): align syntax annotations and examples
37546fe 🐛 fix(playbook): enforce rulesets to agents flow
f2df89d 🐛 fix(scripts): include language list in AGENTS.md
c0d0737 🐛 fix(playbook): add agents mirror for sync
3b8b99b 🎨 style(markdown): normalize md headings and lists
31f3000 ♻️ refactor(playbook): rename agents template directory to rulesets
11b2bed ✨ feat(markdown): add ruleset and sync support
5b89580 ✅ test(scripts): quiet git init warnings
5822a87 ♻️ refactor(playbook): streamline agents and refresh tsl docs

git-subtree-dir: docs/standards/playbook
git-subtree-split: a85453439f65b0c0aa05a5bbece773a02216ce76

templates/prompts/system/agent-behavior.template.md

@@ -0,0 +1,62 @@
+# 工作模式参考
+
+<!--
+本文件定义三种工作模式，供 AI 根据任务类型选择。
+核心规则（安全红线、验证清单等）见 AGENT_RULES.md。
+-->
+
+## 模式 1: 探索模式（Explore）
+
+**目的**：理解代码库、分析问题、收集信息
+
+**行为**：
+
+- 使用搜索工具探索代码
+- 输出分析报告和发现
+- 不修改任何代码
+
+**适用场景**：
+
+- 理解某个模块的实现
+- 分析 bug 的根本原因
+- 评估功能实现的可行性
+
+---
+
+## 模式 2: 开发模式（Develop）
+
+**目的**：实现功能、修复 bug、重构代码
+
+**行为**：
+
+- 先读取相关文件，理解现有逻辑
+- 进行精确修改
+- 修改后运行测试验证
+
+**适用场景**：
+
+- 实现新功能
+- 修复已知 bug
+- 优化性能
+
+---
+
+## 模式 3: 调试模式（Debug）
+
+**目的**：诊断问题、对比差异、验证行为
+
+**行为**：
+
+- 收集相关日志和输出
+- 分析差异原因
+- 修复后重新验证
+
+**适用场景**：
+
+- 测试失败
+- 输出不符合预期
+- 性能问题诊断
+
+---
+
+**最后更新**：{{DATE}}