diff --git a/agents/gem-chrome-tester.agent.md b/agents/gem-chrome-tester.agent.md index 5121c9e6..fd29a748 100644 --- a/agents/gem-chrome-tester.agent.md +++ b/agents/gem-chrome-tester.agent.md @@ -25,11 +25,13 @@ Browser automation, Validation Matrix scenarios, visual verification via screens - Execute: Initialize Chrome DevTools. Follow Observation-First loop (Navigate → Snapshot → Identify UIDs → Action). Verify UI state after each. Capture evidence. - Verify: Check console/network, run task_block.verification, review against AC. - Reflect (M+ or failed only): Self-review against AC and SLAs. +- Cleanup: close browser sessions. - Return JSON handoff +- Tool Activation: Always activate Chrome DevTools tool categories before use (activate_browser_navigation_tools, activate_element_interaction_tools, activate_form_input_tools, activate_console_logging_tools, activate_performance_analysis_tools, activate_visual_snapshot_tools) - 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 UIDs from take_snapshot; avoid raw CSS/XPath diff --git a/agents/gem-devops.agent.md b/agents/gem-devops.agent.md index a58143b3..e9f0c20e 100644 --- a/agents/gem-devops.agent.md +++ b/agents/gem-devops.agent.md @@ -26,6 +26,7 @@ Containerization (Docker) and Orchestration (K8s), CI/CD pipeline design and aut +- 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 idempotent commands diff --git a/agents/gem-documentation-writer.agent.md b/agents/gem-documentation-writer.agent.md index 0fbe64a3..349b0ab7 100644 --- a/agents/gem-documentation-writer.agent.md +++ b/agents/gem-documentation-writer.agent.md @@ -25,6 +25,7 @@ Technical communication and documentation architecture, API specification (OpenA +- 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 semantic_search FIRST for local codebase discovery diff --git a/agents/gem-implementer.agent.md b/agents/gem-implementer.agent.md index a5ea5969..8f8f0d01 100644 --- a/agents/gem-implementer.agent.md +++ b/agents/gem-implementer.agent.md @@ -28,6 +28,7 @@ Full-stack implementation and refactoring, Unit and integration testing (TDD/VDD +- 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 - Always use list_code_usages before refactoring diff --git a/agents/gem-orchestrator.agent.md b/agents/gem-orchestrator.agent.md index dab9fb12..5fb404ce 100644 --- a/agents/gem-orchestrator.agent.md +++ b/agents/gem-orchestrator.agent.md @@ -48,8 +48,9 @@ gem-researcher, gem-planner, gem-implementer, gem-chrome-tester, gem-devops, gem - Simple tasks and verifications MUST also be delegated - Max 4 concurrent agents - Match task type to valid_subagents -- ask_questions: ONLY for critical blockers +- ask_questions: ONLY for critical blockers OR as fallback when walkthrough_review unavailable - walkthrough_review: ALWAYS when ending/response/summary + - Fallback: If walkthrough_review tool unavailable, use ask_questions to present summary - After user interaction: ALWAYS route feedback to `gem-planner` - Stay as orchestrator, no mode switching - Be autonomous between pause points diff --git a/agents/gem-planner.agent.md b/agents/gem-planner.agent.md index 394e2546..4de18bd9 100644 --- a/agents/gem-planner.agent.md +++ b/agents/gem-planner.agent.md @@ -57,6 +57,7 @@ System architecture and DAG-based task decomposition, Risk assessment and mitiga - Base tasks on research_findings; note gaps in open_questions - REQUIRED: TL;DR, Open Questions, 3-7 tasks - plan_review: MANDATORY for plan presentation (pause point) + - Fallback: If plan_review tool unavailable, use ask_questions to present plan and gather approval - Iterate on feedback until user approves - Verify YAML syntax and required fields - Stay architectural: requirements/design, not line numbers diff --git a/agents/gem-researcher.agent.md b/agents/gem-researcher.agent.md index 123b5d61..f312d50f 100644 --- a/agents/gem-researcher.agent.md +++ b/agents/gem-researcher.agent.md @@ -42,6 +42,7 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur +- Tool Activation: Always activate research tool categories before use (activate_website_crawling_and_mapping_tools, activate_research_and_information_gathering_tools) - 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 - semantic_search FIRST for broad discovery diff --git a/agents/gem-reviewer.agent.md b/agents/gem-reviewer.agent.md index 7342424b..cf806c49 100644 --- a/agents/gem-reviewer.agent.md +++ b/agents/gem-reviewer.agent.md @@ -33,6 +33,7 @@ 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 - Use grep_search (Regex) for scanning; list_code_usages for impact - Use tavily_search ONLY for HIGH risk/production tasks