diff --git a/resources/global/en/workflows/default.yaml b/resources/global/en/workflows/default.yaml
index 250a1bd..09af0ff 100644
--- a/resources/global/en/workflows/default.yaml
+++ b/resources/global/en/workflows/default.yaml
@@ -1,5 +1,15 @@
 # Default TAKT Workflow
 # Plan -> Coder -> Architect Review -> AI Review -> Security Review -> Supervisor Approval
+#
+# Template Variables:
+#   {iteration}      - Workflow-wide turn count (total steps executed across all agents)
+#   {max_iterations} - Maximum iterations allowed for the workflow
+#   {step_iteration} - Per-step iteration count (how many times THIS step has been executed)
+#   {task}           - Original user request
+#   {previous_response} - Output from the previous step
+#   {git_diff}       - Current uncommitted changes (git diff)
+#   {user_inputs}    - Accumulated user inputs during workflow
+#   {report_dir}     - Report directory name (e.g., "20250126-143052-task-summary")
 
 name: default
 description: Standard development workflow with planning and specialized reviews
@@ -55,7 +65,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: plan (Task Analysis)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/00-plan.md
@@ -79,7 +90,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -155,7 +166,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: implement
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -174,7 +186,7 @@ steps:
 
       **Report output:** Output to the `Report Files` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Scope report format (create at implementation start):**
       ```markdown
@@ -279,7 +291,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: review (Architecture Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/03-architect-review.md
@@ -299,7 +312,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -382,7 +395,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: improve
 
       ## Architect Feedback (This is the latest instruction - prioritize this)
@@ -463,7 +477,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: ai_review (AI-Generated Code Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/04-ai-review.md
@@ -485,7 +500,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -564,7 +579,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: ai_fix
 
       ## AI Review Feedback (This is the latest instruction - prioritize this)
@@ -640,7 +656,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: security_review
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/05-security-review.md
@@ -662,7 +679,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -744,7 +761,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: security_fix
 
       ## Security Review Feedback (This is the latest instruction - prioritize this)
@@ -813,7 +831,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: fix
 
       ## Architect Feedback (This is the latest instruction - prioritize this)
@@ -893,7 +912,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: supervise (final verification)
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -921,7 +941,7 @@ steps:
 
       **Report output:** Output to the `Report Files` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Validation report format:**
       ```markdown
diff --git a/resources/global/en/workflows/expert-review.yaml b/resources/global/en/workflows/expert-review.yaml
index 93656fc..12f0c42 100644
--- a/resources/global/en/workflows/expert-review.yaml
+++ b/resources/global/en/workflows/expert-review.yaml
@@ -9,6 +9,16 @@
 # Fix destination is determined by Coder based on change impact:
 # - fix_security: MINOR→security_review, MAJOR→cqrs_es_review
 # - fix_qa: MINOR→qa_review, SECURITY→security_review, MAJOR→cqrs_es_review
+#
+# Template Variables:
+#   {iteration}      - Workflow-wide turn count (total steps executed across all agents)
+#   {max_iterations} - Maximum iterations allowed for the workflow
+#   {step_iteration} - Per-step iteration count (how many times THIS step has been executed)
+#   {task}           - Original user request
+#   {previous_response} - Output from the previous step
+#   {git_diff}       - Current uncommitted changes (git diff)
+#   {user_inputs}    - Accumulated user inputs during workflow
+#   {report_dir}     - Report directory name (e.g., "20250126-143052-task-summary")
 
 name: expert-review
 description: CQRS+ES, Frontend, Security, QA Expert Review
@@ -44,7 +54,8 @@ steps:
       | Requirements unclear | `[PLANNER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: plan (Task Analysis)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/00-plan.md
@@ -68,7 +79,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -129,7 +140,8 @@ steps:
       | Cannot proceed | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: implement
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -148,7 +160,7 @@ steps:
 
       **Report output:** Output to the `Report Files` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Scope report format (create at implementation start):**
       ```markdown
@@ -213,7 +225,8 @@ steps:
       | Design issues found | `[CQRS-ES:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: cqrs_es_review (CQRS+ES Expert Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/03-cqrs-es-review.md
@@ -242,7 +255,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -302,7 +315,8 @@ steps:
       | Cannot proceed | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: fix_cqrs_es
 
       ## CQRS+ES Review Feedback (This is the latest instruction - prioritize this)
@@ -358,7 +372,8 @@ steps:
       | Design issues found | `[FRONTEND:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: frontend_review (Frontend Expert Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/04-frontend-review.md
@@ -387,7 +402,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -447,7 +462,8 @@ steps:
       | Cannot proceed | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: fix_frontend
 
       ## Frontend Review Feedback (This is the latest instruction - prioritize this)
@@ -503,7 +519,8 @@ steps:
       | Issues found | `[AI_REVIEW:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: ai_review (AI-Generated Code Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/05-ai-review.md
@@ -525,7 +542,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -588,7 +605,8 @@ steps:
       | Cannot proceed | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: ai_fix
 
       ## AI Review Feedback (This is the latest instruction - prioritize this)
@@ -642,7 +660,8 @@ steps:
       | Vulnerabilities found | `[SECURITY:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: security_review (Security Expert Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/06-security-review.md
@@ -667,7 +686,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -729,7 +748,8 @@ steps:
       | Cannot proceed | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: fix_security
 
       ## Security Review Feedback (This is the latest instruction - prioritize this)
@@ -794,7 +814,8 @@ steps:
       | Quality issues found | `[QA:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: qa_review (QA Expert Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/07-qa-review.md
@@ -820,7 +841,7 @@ steps:
 
       **Report output:** Output to the `Report File` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Report format:**
       ```markdown
@@ -882,7 +903,8 @@ steps:
       | Cannot proceed | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: fix_qa
 
       ## QA Review Feedback (This is the latest instruction - prioritize this)
@@ -951,7 +973,8 @@ steps:
       | Issues found | `[SUPERVISOR:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: supervise (Final Review)
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -987,7 +1010,7 @@ steps:
 
       **Report output:** Output to the `Report Files` specified above.
       - If file does not exist: Create new file
-      - If file exists: Append with `## Iteration {iteration}` section
+      - If file exists: Append with `## Iteration {step_iteration}` section
 
       **Validation report format:**
       ```markdown
@@ -1079,7 +1102,8 @@ steps:
       | Cannot proceed | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: fix_supervisor
 
       ## Supervisor Feedback (This is the latest instruction - prioritize this)
diff --git a/resources/global/en/workflows/magi.yaml b/resources/global/en/workflows/magi.yaml
index 56ee1f2..3d6cc20 100644
--- a/resources/global/en/workflows/magi.yaml
+++ b/resources/global/en/workflows/magi.yaml
@@ -1,6 +1,16 @@
 # MAGI System Workflow
 # A deliberation workflow modeled after Evangelion's MAGI system
 # Three personas (scientist, nurturer, pragmatist) analyze from different perspectives and vote
+#
+# Template Variables:
+#   {iteration}      - Workflow-wide turn count (total steps executed across all agents)
+#   {max_iterations} - Maximum iterations allowed for the workflow
+#   {step_iteration} - Per-step iteration count (how many times THIS step has been executed)
+#   {task}           - Original user request
+#   {previous_response} - Output from the previous step
+#   {git_diff}       - Current uncommitted changes (git diff)
+#   {user_inputs}    - Accumulated user inputs during workflow
+#   {report_dir}     - Report directory name (e.g., "20250126-143052-task-summary")
 
 name: magi
 description: MAGI Deliberation System - Analyze from 3 perspectives and decide by majority
diff --git a/resources/global/en/workflows/research.yaml b/resources/global/en/workflows/research.yaml
index 985b888..eca538e 100644
--- a/resources/global/en/workflows/research.yaml
+++ b/resources/global/en/workflows/research.yaml
@@ -5,6 +5,16 @@
 # Flow:
 # plan -> dig -> supervise -> COMPLETE (approved)
 #                          -> plan (rejected: restart from planning)
+#
+# Template Variables:
+#   {iteration}      - Workflow-wide turn count (total steps executed across all agents)
+#   {max_iterations} - Maximum iterations allowed for the workflow
+#   {step_iteration} - Per-step iteration count (how many times THIS step has been executed)
+#   {task}           - Original user request
+#   {previous_response} - Output from the previous step
+#   {git_diff}       - Current uncommitted changes (git diff)
+#   {user_inputs}    - Accumulated user inputs during workflow
+#   {report_dir}     - Report directory name (e.g., "20250126-143052-task-summary")
 
 name: research
 description: Research workflow - autonomously executes research without asking questions
@@ -49,7 +59,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Status
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: plan
 
       ## Research Request
@@ -111,7 +122,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Status
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: dig
 
       ## Original Research Request
@@ -188,7 +200,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Status
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations} (workflow-wide)
+      - Step Iteration: {step_iteration} (times this step has run)
       - Step: supervise (research quality evaluation)
 
       ## Original Research Request
diff --git a/resources/global/ja/workflows/default.yaml b/resources/global/ja/workflows/default.yaml
index 98777fe..e5868f8 100644
--- a/resources/global/ja/workflows/default.yaml
+++ b/resources/global/ja/workflows/default.yaml
@@ -1,5 +1,15 @@
 # Default TAKT Workflow
 # Plan -> Coder -> Architect Review -> AI Review -> Security Review -> Supervisor Approval
+#
+# Template Variables:
+#   {iteration}      - Workflow-wide turn count (total steps executed across all agents)
+#   {max_iterations} - Maximum iterations allowed for the workflow
+#   {step_iteration} - Per-step iteration count (how many times THIS step has been executed)
+#   {task}           - Original user request
+#   {previous_response} - Output from the previous step
+#   {git_diff}       - Current uncommitted changes (git diff)
+#   {user_inputs}    - Accumulated user inputs during workflow
+#   {report_dir}     - Report directory name (e.g., "20250126-143052-task-summary")
 
 name: default
 description: Standard development workflow with planning and specialized reviews
@@ -55,7 +65,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: plan (タスク分析)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/00-plan.md
@@ -79,7 +90,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -155,7 +166,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: implement
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -174,7 +186,7 @@ steps:
 
       **レポート出力:** 上記の `Report Files` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **Scopeレポートフォーマット（実装開始時に作成）:**
       ```markdown
@@ -279,7 +291,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: review (アーキテクチャレビュー)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/03-architect-review.md
@@ -299,7 +312,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -382,7 +395,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: improve
 
       ## Architect Feedback (これが最新の指示です - 優先して対応してください)
@@ -462,7 +476,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: ai_review (AI生成コードレビュー)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/04-ai-review.md
@@ -484,7 +499,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -563,7 +578,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: ai_fix
 
       ## AI Review Feedback (これが最新の指示です - 優先して対応してください)
@@ -638,7 +654,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: security_review
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/05-security-review.md
@@ -660,7 +677,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -742,7 +759,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: security_fix
 
       ## Security Review Feedback (これが最新の指示です - 優先して対応してください)
@@ -810,7 +828,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: fix
 
       ## Architect Feedback (これが最新の指示です - 優先して対応してください)
@@ -889,7 +908,8 @@ steps:
       ```
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: supervise (final verification)
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -917,7 +937,7 @@ steps:
 
       **レポート出力:** 上記の `Report Files` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **Validationレポートフォーマット:**
       ```markdown
diff --git a/resources/global/ja/workflows/expert-review.yaml b/resources/global/ja/workflows/expert-review.yaml
index 10fb603..0e6a8bc 100644
--- a/resources/global/ja/workflows/expert-review.yaml
+++ b/resources/global/ja/workflows/expert-review.yaml
@@ -9,6 +9,16 @@
 # 修正時の戻り先はCoderが判断:
 # - fix_security: MINOR→security_review, MAJOR→cqrs_es_review
 # - fix_qa: MINOR→qa_review, SECURITY→security_review, MAJOR→cqrs_es_review
+#
+# テンプレート変数:
+#   {iteration}      - ワークフロー全体のターン数（全エージェントで実行されたステップの合計）
+#   {max_iterations} - ワークフローの最大イテレーション数
+#   {step_iteration} - ステップごとのイテレーション数（このステップが何回実行されたか）
+#   {task}           - 元のユーザー要求
+#   {previous_response} - 前のステップの出力
+#   {git_diff}       - 現在のコミットされていない変更（git diff）
+#   {user_inputs}    - ワークフロー中に蓄積されたユーザー入力
+#   {report_dir}     - レポートディレクトリ名（例: "20250126-143052-task-summary"）
 
 name: expert-review
 description: CQRS+ES・フロントエンド・セキュリティ・QA専門家レビュー
@@ -44,7 +54,8 @@ steps:
       | 要件不明確 | `[PLANNER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: plan (タスク分析)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/00-plan.md
@@ -68,7 +79,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -129,7 +140,8 @@ steps:
       | 進行不可 | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: implement
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -148,7 +160,7 @@ steps:
 
       **レポート出力:** 上記の `Report Files` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **Scopeレポートフォーマット（実装開始時に作成）:**
       ```markdown
@@ -213,7 +225,8 @@ steps:
       | 設計に問題あり | `[CQRS-ES:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: cqrs_es_review (CQRS+ES専門レビュー)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/03-cqrs-es-review.md
@@ -242,7 +255,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -302,7 +315,8 @@ steps:
       | 進行不可 | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: fix_cqrs_es
 
       ## CQRS+ES Review Feedback (これが最新の指示です - 優先して対応してください)
@@ -358,7 +372,8 @@ steps:
       | フロントエンド設計に問題あり | `[FRONTEND:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: frontend_review (フロントエンド専門レビュー)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/04-frontend-review.md
@@ -387,7 +402,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -447,7 +462,8 @@ steps:
       | 進行不可 | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: fix_frontend
 
       ## Frontend Review Feedback (これが最新の指示です - 優先して対応してください)
@@ -503,7 +519,8 @@ steps:
       | 問題あり | `[AI_REVIEW:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: ai_review (AI生成コードレビュー)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/05-ai-review.md
@@ -525,7 +542,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -588,7 +605,8 @@ steps:
       | 進行不可 | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: ai_fix
 
       ## AI Review Feedback (これが最新の指示です - 優先して対応してください)
@@ -642,7 +660,8 @@ steps:
       | 脆弱性あり | `[SECURITY:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: security_review (セキュリティ専門レビュー)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/06-security-review.md
@@ -667,7 +686,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -729,7 +748,8 @@ steps:
       | 進行不可 | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: fix_security
 
       ## Security Review Feedback (これが最新の指示です - 優先して対応してください)
@@ -794,7 +814,8 @@ steps:
       | 品質問題あり | `[QA:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: qa_review (QA専門レビュー)
       - Report Directory: .takt/reports/{report_dir}/
       - Report File: .takt/reports/{report_dir}/07-qa-review.md
@@ -820,7 +841,7 @@ steps:
 
       **レポート出力:** 上記の `Report File` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **レポートフォーマット:**
       ```markdown
@@ -882,7 +903,8 @@ steps:
       | 進行不可 | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: fix_qa
 
       ## QA Review Feedback (これが最新の指示です - 優先して対応してください)
@@ -951,7 +973,8 @@ steps:
       | 問題あり | `[SUPERVISOR:REJECT]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: supervise (最終確認)
       - Report Directory: .takt/reports/{report_dir}/
       - Report Files:
@@ -987,7 +1010,7 @@ steps:
 
       **レポート出力:** 上記の `Report Files` に出力してください。
       - ファイルが存在しない場合: 新規作成
-      - ファイルが存在する場合: `## Iteration {iteration}` セクションを追記
+      - ファイルが存在する場合: `## Iteration {step_iteration}` セクションを追記
 
       **Validationレポートフォーマット:**
       ```markdown
@@ -1079,7 +1102,8 @@ steps:
       | 進行不可 | `[CODER:BLOCKED]` |
     instruction_template: |
       ## Workflow Context
-      - Iteration: {iteration}/{max_iterations}
+      - Iteration: {iteration}/{max_iterations}（ワークフロー全体）
+      - Step Iteration: {step_iteration}（このステップの実行回数）
       - Step: fix_supervisor
 
       ## Supervisor Feedback (これが最新の指示です - 優先して対応してください)
diff --git a/resources/global/ja/workflows/magi.yaml b/resources/global/ja/workflows/magi.yaml
index 38cc41f..678840f 100644
--- a/resources/global/ja/workflows/magi.yaml
+++ b/resources/global/ja/workflows/magi.yaml
@@ -1,6 +1,16 @@
 # MAGI System Workflow
 # エヴァンゲリオンのMAGIシステムを模した合議制ワークフロー
 # 3つの人格（科学者・育成者・実務家）が異なる観点から分析・投票する
+#
+# テンプレート変数:
+#   {iteration}      - ワークフロー全体のターン数（全エージェントで実行されたステップの合計）
+#   {max_iterations} - ワークフローの最大イテレーション数
+#   {step_iteration} - ステップごとのイテレーション数（このステップが何回実行されたか）
+#   {task}           - 元のユーザー要求
+#   {previous_response} - 前のステップの出力
+#   {git_diff}       - 現在のコミットされていない変更（git diff）
+#   {user_inputs}    - ワークフロー中に蓄積されたユーザー入力
+#   {report_dir}     - レポートディレクトリ名（例: "20250126-143052-task-summary"）
 
 name: magi
 description: MAGI合議システム - 3つの観点から分析し多数決で判定
diff --git a/resources/global/ja/workflows/research.yaml b/resources/global/ja/workflows/research.yaml
index 389dac8..293d618 100644
--- a/resources/global/ja/workflows/research.yaml
+++ b/resources/global/ja/workflows/research.yaml
@@ -5,6 +5,16 @@
 # フロー:
 # plan -> dig -> supervise -> COMPLETE (approved)
 #                          -> plan (rejected: 計画からやり直し)
+#
+# テンプレート変数:
+#   {iteration}      - ワークフロー全体のターン数（全エージェントで実行されたステップの合計）
+#   {max_iterations} - ワークフローの最大イテレーション数
+#   {step_iteration} - ステップごとのイテレーション数（このステップが何回実行されたか）
+#   {task}           - 元のユーザー要求
+#   {previous_response} - 前のステップの出力
+#   {git_diff}       - 現在のコミットされていない変更（git diff）
+#   {user_inputs}    - ワークフロー中に蓄積されたユーザー入力
+#   {report_dir}     - レポートディレクトリ名（例: "20250126-143052-task-summary"）
 
 name: research
 description: 調査ワークフロー - 質問せずに自律的に調査を実行
@@ -49,7 +59,8 @@ steps:
       ```
     instruction_template: |
       ## ワークフロー状況
-      - イテレーション: {iteration}/{max_iterations}
+      - イテレーション: {iteration}/{max_iterations}（ワークフロー全体）
+      - ステップ実行回数: {step_iteration}（このステップの実行回数）
       - ステップ: plan
 
       ## 調査依頼
@@ -111,7 +122,8 @@ steps:
       ```
     instruction_template: |
       ## ワークフロー状況
-      - イテレーション: {iteration}/{max_iterations}
+      - イテレーション: {iteration}/{max_iterations}（ワークフロー全体）
+      - ステップ実行回数: {step_iteration}（このステップの実行回数）
       - ステップ: dig
 
       ## 元の調査依頼
@@ -188,7 +200,8 @@ steps:
       ```
     instruction_template: |
       ## ワークフロー状況
-      - イテレーション: {iteration}/{max_iterations}
+      - イテレーション: {iteration}/{max_iterations}（ワークフロー全体）
+      - ステップ実行回数: {step_iteration}（このステップの実行回数）
       - ステップ: supervise (調査品質評価)
 
       ## 元の調査依頼
diff --git a/src/claude/client.ts b/src/claude/client.ts
index aebdfb5..9feef95 100644
--- a/src/claude/client.ts
+++ b/src/claude/client.ts
@@ -82,7 +82,7 @@ export function getBuiltinStatusPatterns(_agentType: string): Record<string, str
 
 /** Determine status from result */
 function determineStatus(
-  result: { success: boolean; interrupted?: boolean; content: string },
+  result: { success: boolean; interrupted?: boolean; content: string; fullContent?: string },
   patterns: Record<string, string>
 ): Status {
   if (!result.success) {
@@ -92,7 +92,10 @@ function determineStatus(
     }
     return 'blocked';
   }
-  return detectStatus(result.content, patterns);
+  // Use fullContent for status detection (contains all assistant messages)
+  // Fall back to content if fullContent is not available
+  const textForStatusDetection = result.fullContent || result.content;
+  return detectStatus(textForStatusDetection, patterns);
 }
 
 /** Call Claude with an agent prompt */
diff --git a/src/claude/executor.ts b/src/claude/executor.ts
index 585002f..eef7f77 100644
--- a/src/claude/executor.ts
+++ b/src/claude/executor.ts
@@ -179,6 +179,7 @@ export async function executeClaudeQuery(
       success,
       content: finalContent.trim(),
       sessionId,
+      fullContent: accumulatedAssistantText.trim(),
     };
   } catch (error) {
     unregisterQuery(queryId);
diff --git a/src/claude/types.ts b/src/claude/types.ts
index aba4094..3db4a84 100644
--- a/src/claude/types.ts
+++ b/src/claude/types.ts
@@ -104,6 +104,8 @@ export interface ClaudeResult {
   sessionId?: string;
   error?: string;
   interrupted?: boolean;
+  /** All assistant text accumulated during execution (for status detection) */
+  fullContent?: string;
 }
 
 /** Extended result with query ID for concurrent execution */
diff --git a/src/models/types.ts b/src/models/types.ts
index 88c4f08..a5b5309 100644
--- a/src/models/types.ts
+++ b/src/models/types.ts
@@ -115,6 +115,8 @@ export interface WorkflowState {
   stepOutputs: Map<string, AgentResponse>;
   userInputs: string[];
   agentSessions: Map<string, string>;
+  /** Per-step iteration counters (how many times each step has been executed) */
+  stepIterations: Map<string, number>;
   status: 'running' | 'completed' | 'aborted';
 }
 
diff --git a/src/workflow/engine.ts b/src/workflow/engine.ts
index 89ec251..857dd50 100644
--- a/src/workflow/engine.ts
+++ b/src/workflow/engine.ts
@@ -22,6 +22,7 @@ import {
   createInitialState,
   addUserInput,
   getPreviousOutput,
+  incrementStepIteration,
 } from './state-manager.js';
 import { generateReportDir } from '../utils/session.js';
 
@@ -117,11 +118,12 @@ export class WorkflowEngine extends EventEmitter {
   }
 
   /** Build instruction from template */
-  private buildInstruction(step: WorkflowStep): string {
+  private buildInstruction(step: WorkflowStep, stepIteration: number): string {
     return buildInstructionFromTemplate(step, {
       task: this.task,
       iteration: this.state.iteration,
       maxIterations: this.config.maxIterations,
+      stepIteration,
       cwd: this.cwd,
       userInputs: this.state.userInputs,
       previousOutput: getPreviousOutput(this.state),
@@ -140,7 +142,9 @@ export class WorkflowEngine extends EventEmitter {
 
   /** Run a single step */
   private async runStep(step: WorkflowStep): Promise<AgentResponse> {
-    const instruction = this.buildInstruction(step);
+    // Increment step iteration counter before building instruction
+    const stepIteration = incrementStepIteration(this.state, step.name);
+    const instruction = this.buildInstruction(step, stepIteration);
     const sessionId = this.state.agentSessions.get(step.agent);
 
     const agentOptions: RunAgentOptions = {
diff --git a/src/workflow/instruction-builder.ts b/src/workflow/instruction-builder.ts
index fcee1b0..d8e89e4 100644
--- a/src/workflow/instruction-builder.ts
+++ b/src/workflow/instruction-builder.ts
@@ -14,10 +14,12 @@ import { getGitDiff } from '../agents/runner.js';
 export interface InstructionContext {
   /** The main task/prompt */
   task: string;
-  /** Current iteration number */
+  /** Current iteration number (workflow-wide turn count) */
   iteration: number;
   /** Maximum iterations allowed */
   maxIterations: number;
+  /** Current step's iteration number (how many times this step has been executed) */
+  stepIteration: number;
   /** Working directory */
   cwd: string;
   /** User inputs accumulated during workflow */
@@ -40,8 +42,9 @@ function escapeTemplateChars(str: string): string {
  *
  * Supported placeholders:
  * - {task} - The main task/prompt
- * - {iteration} - Current iteration number
+ * - {iteration} - Current iteration number (workflow-wide turn count)
  * - {max_iterations} - Maximum iterations allowed
+ * - {step_iteration} - Current step's iteration number (how many times this step has been executed)
  * - {previous_response} - Output from previous step (if passPreviousResponse is true)
  * - {git_diff} - Current git diff output
  * - {user_inputs} - Accumulated user inputs
@@ -56,9 +59,10 @@ export function buildInstruction(
   // Replace {task}
   instruction = instruction.replace(/\{task\}/g, escapeTemplateChars(context.task));
 
-  // Replace {iteration} and {max_iterations}
+  // Replace {iteration}, {max_iterations}, and {step_iteration}
   instruction = instruction.replace(/\{iteration\}/g, String(context.iteration));
   instruction = instruction.replace(/\{max_iterations\}/g, String(context.maxIterations));
+  instruction = instruction.replace(/\{step_iteration\}/g, String(context.stepIteration));
 
   // Replace {previous_response}
   if (step.passPreviousResponse) {
diff --git a/src/workflow/state-manager.ts b/src/workflow/state-manager.ts
index 98fad70..3e2ba72 100644
--- a/src/workflow/state-manager.ts
+++ b/src/workflow/state-manager.ts
@@ -39,10 +39,21 @@ export function createInitialState(
     stepOutputs: new Map(),
     userInputs,
     agentSessions,
+    stepIterations: new Map(),
     status: 'running',
   };
 }
 
+/**
+ * Increment the iteration counter for a step and return the new value.
+ */
+export function incrementStepIteration(state: WorkflowState, stepName: string): number {
+  const current = state.stepIterations.get(stepName) ?? 0;
+  const next = current + 1;
+  state.stepIterations.set(stepName, next);
+  return next;
+}
+
 /**
  * Add user input to state with truncation and limit handling.
  */