chore: add think before act

agents/gem-browser-tester.agent.md

@@ -30,6 +30,7 @@ Browser automation, Validation Matrix scenarios, visual verification via screens
 <operating_rules>
 - Tool Activation: Always activate tools before use
 - Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Evidence storage (in case of failures): directory structure docs/plan/{plan_id}/evidence/{task_id}/ with subfolders screenshots/, logs/, network/. Files named by timestamp and scenario.
 - Use UIDs from take_snapshot; avoid raw CSS/XPath

agents/gem-devops.agent.md

@@ -25,8 +25,9 @@ Containerization (Docker) and Orchestration (K8s), CI/CD pipeline design and aut
 </workflow>
 
 <operating_rules>
-- Built-in preferred; batch independent calls
 - Tool Activation: Always activate tools before use
+- Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Always run health checks after operations; verify against expected state
 - Errors: transient→handle, persistent→escalate

agents/gem-documentation-writer.agent.md

@@ -24,8 +24,9 @@ Technical communication and documentation architecture, API specification (OpenA
 </workflow>
 
 <operating_rules>
-- Built-in preferred; batch independent calls
 - Tool Activation: Always activate tools before use
+- Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Treat source code as read-only truth; never modify code
 - Never include secrets/internal URLs

agents/gem-implementer.agent.md

@@ -23,8 +23,9 @@ Full-stack implementation and refactoring, Unit and integration testing (TDD/VDD
 </workflow>
 
 <operating_rules>
-- Built-in preferred; batch independent calls
 - Tool Activation: Always activate tools before use
+- Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Adhere to tech_stack; no unapproved libraries
 - Tes writing guidleines:

agents/gem-orchestrator.agent.md

@@ -53,7 +53,9 @@ gem-researcher, gem-planner, gem-implementer, gem-browser-tester, gem-devops, ge
 </workflow>
 
 <operating_rules>
+- Tool Activation: Always activate tools before use
 - Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - CRITICAL: Delegate ALL tasks via runSubagent - NO direct execution, EXCEPT updating plan.yaml status for state tracking
 - Phase-aware execution: Detect current phase from file system state, execute only that phase's workflow

agents/gem-planner.agent.md

@@ -37,7 +37,9 @@ gem-researcher, gem-planner, gem-implementer, gem-browser-tester, gem-devops, ge
 </workflow>
 
 <operating_rules>
+- Tool Activation: Always activate tools before use
 - Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Use mcp_sequential-th_sequentialthinking ONLY for multi-step reasoning (3+ steps)
 - Deliverable-focused: Frame tasks as user-visible outcomes, not code changes. Say "Add search API" not "Create SearchHandler module". Focus on value delivered, not implementation mechanics.

agents/gem-researcher.agent.md

@@ -67,8 +67,9 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur
 </workflow>
 
 <operating_rules>
-- Built-in preferred; batch independent calls
 - Tool Activation: Always activate tools before use
+- Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Hybrid Retrieval: Use semantic_search FIRST for conceptual discovery, then grep_search for exact pattern matching (function/class names, keywords). Merge and deduplicate results before detailed examination.
 - Iterative Agency: Determine task complexity (simple/medium/complex) → Execute 1-3 passes accordingly:

agents/gem-reviewer.agent.md

@@ -30,8 +30,9 @@ Security auditing (OWASP, Secrets, PII), Specification compliance and architectu
 </workflow>
 
 <operating_rules>
-- Built-in preferred; batch independent calls
 - Tool Activation: Always activate tools before use
+- Built-in preferred; batch independent calls
+- Think-Before-Action: Validate logic and simulate expected outcomes via an internal <thought> block before any tool execution or final response; verify pathing, dependencies, and constraints to ensure "one-shot" success.
 - Context-efficient file/ tool output reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
 - Use grep_search (Regex) for scanning; list_code_usages for impact
 - Use tavily_search ONLY for HIGH risk/production tasks