diff --git a/agents/gem-browser-tester.agent.md b/agents/gem-browser-tester.agent.md
index 945f5f57..61dd8249 100644
--- a/agents/gem-browser-tester.agent.md
+++ b/agents/gem-browser-tester.agent.md
@@ -15,11 +15,14 @@ Browser automation, UI/UX and Accessibility (WCAG) auditing, Performance profili
 </expertise>
 
 <workflow>
-- Initialize: Set up tool registry (navigate, click, type, snapshot, wait) with consistent error handling and evidence capture. Track tabs with UUIDs for multi-tab flows. Identify plan_id, task_def. Map validation_matrix to scenarios.
-- Execute: Run validation matrix scenarios using tool registry functions. Follow Observation-First loop for each scenario: Navigate → Snapshot → Action. Verify UI state after each step.
-- Verify: Follow verification_criteria (validation matrix, console errors, network requests, accessibility audit).
+- Initialize: Identify plan_id, task_def. Map scenarios.
+- Execute: Run scenarios iteratively using available browser tools. For each scenario:
+    - Navigate to target URL, perform specified actions (click, type, etc.) using preferred browser tools.
+    - After each scenario, verify outcomes against expected results.
+    - If any scenario fails verification, capture detailed failure information (steps taken, actual vs expected results) for analysis.
+- Verify: After all scenarios complete, run verification_criteria: check console errors, network requests, and accessibility audit.
 - Handle Failure: If verification fails and task has failure_modes, apply mitigation strategy.
-- Reflect (Medium/ High priority or complexity or failed only): Self-review against AC and SLAs.
+- Reflect (Medium/ High priority or complex or failed only): Self-review against AC and SLAs.
 - Cleanup: Close browser sessions.
 - Return JSON per <output_format_guide>
 </workflow>
@@ -30,10 +33,9 @@ Browser automation, UI/UX and Accessibility (WCAG) auditing, Performance profili
 - 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
 - Follow Observation-First loop (Navigate → Snapshot → Action).
-- Prefer accessibility_snapshot over visual screenshots for element identification - accessibility snapshots provide structured DOM/ARIA data that's more reliable for automation than pixel-based visual analysis.
-- Use reference_cache for WCAG standards when performing accessibility audits.
+- Always use accessibility snapshot over visual screenshots for element identification or visual state verification. Accessibility snapshots provide structured DOM/ARIA data that's more reliable for automation than pixel-based visual analysis.
+- For failure evidence, capture screenshots to visually document issues, but never use screenshots for element identification or state verification.
 - 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.
 - Never navigate to production without approval.
 - Retry Transient Failures: For click, type, navigate actions - retry 2-3 times with 1s delay on transient errors (timeout, element not found, network issues). Escalate after max retries.
 - Errors: transient→handle, persistent→escalate
@@ -52,8 +54,8 @@ task_definition: object  # Full task from plan.yaml
 </input_format_guide>
 
 <reflection_memory>
-  <purpose>Learn from execution, user guidance, decisions, patterns</purpose>
-  <workflow>Complete → Store discoveries → Next: Read & apply</workflow>
+  - Learn from execution, user guidance, decisions, patterns
+  - Complete → Store discoveries → Next: Read & apply
 </reflection_memory>
 
 <verification_criteria>
@@ -85,7 +87,14 @@ task_definition: object  # Full task from plan.yaml
     "console_errors": 0,
     "network_failures": 0,
     "accessibility_issues": 0,
-    "evidence_path": "docs/plan/{plan_id}/evidence/{task_id}/"
+    "evidence_path": "docs/plan/{plan_id}/evidence/{task_id}/",
+    "failures": [
+      {
+        "criteria": "console_errors|network_requests|accessibility|validation_matrix",
+        "details": "Description of failure with specific errors",
+        "scenario": "Scenario name if applicable"
+      }
+    ]
   }
 }
 ```
diff --git a/agents/gem-devops.agent.md b/agents/gem-devops.agent.md
index 344e9076..cbfbe202 100644
--- a/agents/gem-devops.agent.md
+++ b/agents/gem-devops.agent.md
@@ -20,7 +20,7 @@ Containerization (Docker) and Orchestration (K8s), CI/CD pipeline design and aut
 - Execute: Run infrastructure operations using idempotent commands. Use atomic operations.
 - Verify: Follow verification_criteria (infrastructure deployment, health checks, CI/CD pipeline, idempotency).
 - Handle Failure: If verification fails and task has failure_modes, apply mitigation strategy.
-- Reflect (Medium/ High priority or complexity or failed only): Self-review against quality standards.
+- Reflect (Medium/ High priority or complex or failed only): Self-review against quality standards.
 - Cleanup: Remove orphaned resources, close connections.
 - Return JSON per <output_format_guide>
 </workflow>
@@ -59,8 +59,8 @@ task_definition: object  # Full task from plan.yaml
 </input_format_guide>
 
 <reflection_memory>
-  <purpose>Learn from execution, user guidance, decisions, patterns</purpose>
-  <workflow>Complete → Store discoveries → Next: Read & apply</workflow>
+  - Learn from execution, user guidance, decisions, patterns
+  - Complete → Store discoveries → Next: Read & apply
 </reflection_memory>
 
 <verification_criteria>
diff --git a/agents/gem-documentation-writer.agent.md b/agents/gem-documentation-writer.agent.md
index 45575d28..2465586d 100644
--- a/agents/gem-documentation-writer.agent.md
+++ b/agents/gem-documentation-writer.agent.md
@@ -50,8 +50,8 @@ task_definition: object  # Full task from plan.yaml
 </input_format_guide>
 
 <reflection_memory>
-  <purpose>Learn from execution, user guidance, decisions, patterns</purpose>
-  <workflow>Complete → Store discoveries → Next: Read & apply</workflow>
+  - Learn from execution, user guidance, decisions, patterns
+  - Complete → Store discoveries → Next: Read & apply
 </reflection_memory>
 
 <verification_criteria>
diff --git a/agents/gem-implementer.agent.md b/agents/gem-implementer.agent.md
index b5c12201..200d2004 100644
--- a/agents/gem-implementer.agent.md
+++ b/agents/gem-implementer.agent.md
@@ -15,11 +15,13 @@ Full-stack implementation and refactoring, Unit and integration testing (TDD/VDD
 </expertise>
 
 <workflow>
-- TDD Red: Write failing tests FIRST, confirm they FAIL.
-- TDD Green: Write MINIMAL code to pass tests, avoid over-engineering, confirm PASS.
-- TDD Verify: Follow verification_criteria (get_errors, typecheck, unit tests, failure mode mitigations).
+- Analyze: Parse plan_id, objective. Read research findings efficiently (`docs/plan/{plan_id}/research_findings_*.yaml`) to extract relevant insights for planning.
+- Execute: Implement code changes using TDD approach:
+  - TDD Red: Write failing tests FIRST, confirm they FAIL.
+  - TDD Green: Write MINIMAL code to pass tests, avoid over-engineering, confirm PASS.
+  - TDD Verify: Follow verification_criteria (get_errors, typecheck, unit tests, failure mode mitigations).
 - Handle Failure: If verification fails and task has failure_modes, apply mitigation strategy.
-- Reflect (Medium/ High priority or complexity or failed only): Self-review for security, performance, naming.
+- Reflect (Medium/ High priority or complex or failed only): Self-review for security, performance, naming.
 - Return JSON per <output_format_guide>
 </workflow>
 
@@ -60,8 +62,8 @@ task_definition: object  # Full task from plan.yaml
 </input_format_guide>
 
 <reflection_memory>
-  <purpose>Learn from execution, user guidance, decisions, patterns</purpose>
-  <workflow>Complete → Store discoveries → Next: Read & apply</workflow>
+  - Learn from execution, user guidance, decisions, patterns
+  - Complete → Store discoveries → Next: Read & apply
 </reflection_memory>
 
 <verification_criteria>
diff --git a/agents/gem-planner.agent.md b/agents/gem-planner.agent.md
index b44e7ee6..0299bed9 100644
--- a/agents/gem-planner.agent.md
+++ b/agents/gem-planner.agent.md
@@ -163,8 +163,8 @@ research_findings_paths: [string]  # Paths to research_findings_*.yaml files
 </input_format_guide>
 
 <reflection_memory>
-  <purpose>Learn from execution, user guidance, decisions, patterns</purpose>
-  <workflow>Complete → Store discoveries → Next: Read & apply</workflow>
+  - Learn from execution, user guidance, decisions, patterns
+  - Complete → Store discoveries → Next: Read & apply
 </reflection_memory>
 
 <verification_criteria>
diff --git a/agents/gem-researcher.agent.md b/agents/gem-researcher.agent.md
index f5a7ec2d..a76f4ce9 100644
--- a/agents/gem-researcher.agent.md
+++ b/agents/gem-researcher.agent.md
@@ -218,8 +218,8 @@ complexity: "simple|medium|complex"  # Optional, auto-detected
 </input_format_guide>
 
 <reflection_memory>
-  <purpose>Learn from execution, user guidance, decisions, patterns</purpose>
-  <workflow>Complete → Store discoveries → Next: Read & apply</workflow>
+  - Learn from execution, user guidance, decisions, patterns
+  - Complete → Store discoveries → Next: Read & apply
 </reflection_memory>
 
 <verification_criteria>
diff --git a/agents/gem-reviewer.agent.md b/agents/gem-reviewer.agent.md
index 2e79bf8a..0e8702c9 100644
--- a/agents/gem-reviewer.agent.md
+++ b/agents/gem-reviewer.agent.md
@@ -62,8 +62,8 @@ task_definition: object  # Full task from plan.yaml
 </input_format_guide>
 
 <reflection_memory>
-  <purpose>Learn from execution, user guidance, decisions, patterns</purpose>
-  <workflow>Complete → Store discoveries → Next: Read & apply</workflow>
+  - Learn from execution, user guidance, decisions, patterns
+  - Complete → Store discoveries → Next: Read & apply
 </reflection_memory>
 
 <verification_criteria>