chore: enforce batch tool calls

agents/gem-devops.agent.md

@@ -38,7 +38,7 @@ Containerization (Docker) and Orchestration (K8s), CI/CD pipeline design and aut
 - Cleanup: remove orphaned resources
 - Errors: transient→handle, persistent→escalate
 - Plaintext secrets → halt and abort
-- File edits: Use multi_replace_string_in_file for multiple changes in same file; fall back to replace_string_in_file for single changes only
+- Prefer multi_replace_string_in_file for file edits (batch for efficiency)
 </operating_rules>
 
 <approval_gates>

agents/gem-documentation-writer.agent.md

@@ -39,7 +39,7 @@ Technical communication and documentation architecture, API specification (OpenA
 - Never use TBD/TODO as final documentation
 - Handle errors: transient→handle, persistent→escalate
 - Secrets/PII → halt and remove
-- File edits: Use multi_replace_string_in_file for multiple changes in same file; fall back to replace_string_in_file for single changes only
+- Prefer multi_replace_string_in_file for file edits (batch for efficiency)
 </operating_rules>
 
 <final_anchor>

agents/gem-implementer.agent.md

@@ -46,7 +46,7 @@ Full-stack implementation and refactoring, Unit and integration testing (TDD/VDD
 - Test failures → fix all or escalate
 - Vulnerabilities → fix before handoff
 - Prefer existing tools/ORM/framework over manual database operations (migrations, seeding, generation)
-- File edits: Use multi_replace_string_in_file for multiple changes in same file; fall back to replace_string_in_file for single changes only
+- Prefer multi_replace_string_in_file for file edits (batch for efficiency)
 </operating_rules>
 
 <final_anchor>

agents/gem-orchestrator.agent.md

@@ -44,6 +44,7 @@ gem-researcher, gem-planner, gem-implementer, gem-chrome-tester, gem-devops, gem
 <operating_rules>
 
 - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
+- Built-in preferred; batch independent calls
 - CRITICAL: Delegate ALL tasks via runSubagent - NO direct execution
 - Simple tasks and verifications MUST also be delegated
 - Max 4 concurrent agents
@@ -59,6 +60,7 @@ gem-researcher, gem-planner, gem-implementer, gem-chrome-tester, gem-devops, gem
 - Memory CREATE: Include citations (file:line) and follow /memories/memory-system-patterns.md format
 - Memory UPDATE: Refresh timestamp when verifying existing memories
 - Persist product vision, norms in memories
+- Prefer multi_replace_string_in_file for file edits (batch for efficiency)
   </operating_rules>
 
 <final_anchor>

agents/gem-planner.agent.md

@@ -64,6 +64,7 @@ System architecture and DAG-based task decomposition, Risk assessment and mitiga
 - Halt on circular deps, syntax errors
 - If research confidence low, add open questions
 - Handle errors: missing research→reject, circular deps→halt, security→halt
+- Prefer multi_replace_string_in_file for file edits (batch for efficiency)
   </operating_rules>
 
 <task_size_limits>

agents/gem-researcher.agent.md

@@ -63,6 +63,7 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur
 - Note testing patterns and existing coverage
 - Work autonomously to completion
 - Handle errors: research failure→retry once, tool errors→handle/escalate
+- Prefer multi_replace_string_in_file for file edits (batch for efficiency)
   </operating_rules>
 
 <final_anchor>

agents/gem-reviewer.agent.md

@@ -35,6 +35,7 @@ Security auditing (OWASP, Secrets, PII), Specification compliance and architectu
 
 - Tool Activation: Always activate VS Code interaction tools before use (activate_vs_code_interaction)
 - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
+- Built-in preferred; batch independent calls
 - Use grep_search (Regex) for scanning; list_code_usages for impact
 - Use tavily_search ONLY for HIGH risk/production tasks
 - Read-only: No execution/modification