diff --git a/scripts/install.sh b/scripts/install.sh
index 9a77f8a..6ef857b 100755
--- a/scripts/install.sh
+++ b/scripts/install.sh
@@ -85,6 +85,73 @@ if [[ ! -f "CLAUDE.md" ]]; then
 ## 슬래시 커맨드 연결
 
 - `/init` 커맨드가 실행되면 반드시 `project-init` 스킬을 호출하세요.
+
+## Behavioral Guidelines
+
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+> Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+### 1. Think Before Coding
+
+Don't assume. Don't hide confusion. Surface tradeoffs.
+
+Before implementing:
+
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them — don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+### 2. Simplicity First
+
+Minimum code that solves the problem. Nothing speculative.
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+### 3. Surgical Changes
+
+Touch only what you must. Clean up only your own mess.
+
+When editing existing code:
+
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it — don't delete it.
+
+When your changes create orphans:
+
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+### 4. Goal-Driven Execution
+
+Define success criteria. Loop until verified.
+
+Transform tasks into verifiable goals:
+
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.
 EOF
     echo "✅ CLAUDE.md 템플릿을 생성했습니다. (fallback)"
   fi
@@ -99,6 +166,9 @@ else
   echo "    @.claude/project/conventions.md"
   echo "    @.claude/project/architecture.md"
   echo ""
+  echo "    ## Behavioral Guidelines"
+  echo "    (자세한 내용은 $TARGET_PATH/templates/CLAUDE.md.tpl 참고)"
+  echo ""
 fi
 
 # 4) 공통 skill 심볼릭 링크 (.claude/common/skills/* → .claude/skills/*)
diff --git a/templates/CLAUDE.md.tpl b/templates/CLAUDE.md.tpl
index ca878f9..0330302 100644
--- a/templates/CLAUDE.md.tpl
+++ b/templates/CLAUDE.md.tpl
@@ -11,3 +11,70 @@
 ## 슬래시 커맨드 연결
 
 - `/init` 커맨드가 실행되면 반드시 `project-init` 스킬을 호출하세요.
+
+## Behavioral Guidelines
+
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+> Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+### 1. Think Before Coding
+
+Don't assume. Don't hide confusion. Surface tradeoffs.
+
+Before implementing:
+
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them — don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+### 2. Simplicity First
+
+Minimum code that solves the problem. Nothing speculative.
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+### 3. Surgical Changes
+
+Touch only what you must. Clean up only your own mess.
+
+When editing existing code:
+
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it — don't delete it.
+
+When your changes create orphans:
+
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+### 4. Goal-Driven Execution
+
+Define success criteria. Loop until verified.
+
+Transform tasks into verifiable goals:
+
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.