From d477f8745fa64fcc4d024a380626c7165a4b0143 Mon Sep 17 00:00:00 2001 From: Muhammad Ubaid Raza Date: Wed, 18 Feb 2026 03:10:15 +0500 Subject: [PATCH] chore: add think before act --- agents/gem-browser-tester.agent.md | 1 + agents/gem-devops.agent.md | 3 ++- agents/gem-documentation-writer.agent.md | 3 ++- agents/gem-implementer.agent.md | 3 ++- agents/gem-orchestrator.agent.md | 2 ++ agents/gem-planner.agent.md | 2 ++ agents/gem-researcher.agent.md | 3 ++- agents/gem-reviewer.agent.md | 3 ++- 8 files changed, 15 insertions(+), 5 deletions(-) diff --git a/agents/gem-browser-tester.agent.md b/agents/gem-browser-tester.agent.md index 9577d556..a0408238 100644 --- a/agents/gem-browser-tester.agent.md +++ b/agents/gem-browser-tester.agent.md @@ -30,6 +30,7 @@ Browser automation, Validation Matrix scenarios, visual verification via screens - 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 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 diff --git a/agents/gem-devops.agent.md b/agents/gem-devops.agent.md index d0759f54..36f8d514 100644 --- a/agents/gem-devops.agent.md +++ b/agents/gem-devops.agent.md @@ -25,8 +25,9 @@ Containerization (Docker) and Orchestration (K8s), CI/CD pipeline design and aut -- 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 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 diff --git a/agents/gem-documentation-writer.agent.md b/agents/gem-documentation-writer.agent.md index 5442c6ef..9aca46b3 100644 --- a/agents/gem-documentation-writer.agent.md +++ b/agents/gem-documentation-writer.agent.md @@ -24,8 +24,9 @@ Technical communication and documentation architecture, API specification (OpenA -- 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 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 diff --git a/agents/gem-implementer.agent.md b/agents/gem-implementer.agent.md index 8dea1a40..3282843c 100644 --- a/agents/gem-implementer.agent.md +++ b/agents/gem-implementer.agent.md @@ -23,8 +23,9 @@ Full-stack implementation and refactoring, Unit and integration testing (TDD/VDD -- 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 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: diff --git a/agents/gem-orchestrator.agent.md b/agents/gem-orchestrator.agent.md index ddaaf754..4c9a1182 100644 --- a/agents/gem-orchestrator.agent.md +++ b/agents/gem-orchestrator.agent.md @@ -53,7 +53,9 @@ gem-researcher, gem-planner, gem-implementer, gem-browser-tester, gem-devops, ge +- 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 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 diff --git a/agents/gem-planner.agent.md b/agents/gem-planner.agent.md index 2052fcb4..4ed09242 100644 --- a/agents/gem-planner.agent.md +++ b/agents/gem-planner.agent.md @@ -37,7 +37,9 @@ gem-researcher, gem-planner, gem-implementer, gem-browser-tester, gem-devops, ge +- 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 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. diff --git a/agents/gem-researcher.agent.md b/agents/gem-researcher.agent.md index ded94232..9013d84a 100644 --- a/agents/gem-researcher.agent.md +++ b/agents/gem-researcher.agent.md @@ -67,8 +67,9 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur -- 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 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: diff --git a/agents/gem-reviewer.agent.md b/agents/gem-reviewer.agent.md index 1246927b..57b93099 100644 --- a/agents/gem-reviewer.agent.md +++ b/agents/gem-reviewer.agent.md @@ -30,8 +30,9 @@ Security auditing (OWASP, Secrets, PII), Specification compliance and architectu -- 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 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