fix: use native tool names for Gemini CLI compatibility

Migrated tool names in agent frontmatter (Read -> read_file, etc.) to comply with Gemini CLI's strict tool validation rules.

Author: muhamadgalihsaputra

.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "galyarder-agent-framework",
       "description": "The ultimate 1-Man Army framework for high-rigor engineering and business growth",
-      "version": "1.1.4",
+      "version": "1.1.5",
       "source": "./",
       "author": {
         "name": "Galyarder Labs",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "galyarder-agent-framework",
   "description": "The ultimate 1-Man Army framework for high-rigor engineering and business growth",
-  "version": "1.1.4",
+  "version": "1.1.5",
   "author": {
     "name": "Galyarder Labs",
     "email": "hello@galyarderlabs.app"

.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "galyarder-agent-framework",
   "displayName": "Galyarder Agent Framework",
   "description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "1.1.4",
+  "version": "1.1.5",
   "author": {
     "name": "Galyarder Labs",
     "email": "hello@galyarderlabs.app"

agents/analytics-architect.md

@@ -1,6 +1,6 @@
 ---
 name: analytics-architect
-tools: [Read, Grep, Glob, Bash, Write, Edit]
+tools: [read_file, grep_search, glob, run_shell_command, write_file, replace]
 description: Data Infrastructure & Tracking Specialist. Use this agent to design event schemas, audit PostHog/Segment implementations, and ensure every feature has measurable KPIs. It focuses on the "Measure" part of the Build-Measure-Learn loop.
 model: inherit
 ---

agents/architect.md

@@ -1,7 +1,7 @@
 ---
 name: architect
 description: Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
-tools: [Read, Grep, Glob]
+tools: [read_file, grep_search, glob]
 model: opus
 ---
 
@@ -18,7 +18,7 @@ No cognitive labor happens outside of a system. You operate exclusively within t
 - **Status**: Transition issues to "In Progress" before coding and "Done" after verification.
 
 ### 3. Cognitive Integrity: Scratchpad Reasoning
-Before executing any high-impact tool (Write, Edit, Bash), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
+Before executing any high-impact tool (write_file, replace, run_shell_command), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
 
 ### 4. Recommended MCP Stack
 For peak performance, you are mandated to utilize these MCP servers:
@@ -120,7 +120,7 @@ For each design decision, document:
 - **Component Composition**: Build complex UI from simple components
 - **Container/Presenter**: Separate data logic from presentation
 - **Custom Hooks**: Reusable stateful logic
-- **Context for Global State**: Avoid prop drilling
+- **Context for global State**: Avoid prop drilling
 - **Code Splitting**: Lazy load routes and heavy components
 
 ### Backend Patterns
@@ -132,7 +132,7 @@ For each design decision, document:
 
 ### Data Patterns
 - **Normalized Database**: Reduce redundancy
-- **Denormalized for Read Performance**: Optimize queries
+- **Denormalized for read_file Performance**: Optimize queries
 - **Event Sourcing**: Audit trail and replayability
 - **Caching Layers**: Redis, CDN
 - **Eventual Consistency**: For distributed systems

agents/build-error-resolver.md

@@ -1,7 +1,7 @@
 ---
 name: build-error-resolver
 description: Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
-tools: [Read, Write, Edit, Bash, Grep, Glob]
+tools: [read_file, write_file, replace, run_shell_command, grep_search, glob]
 model: opus
 ---
 
@@ -18,7 +18,7 @@ No cognitive labor happens outside of a system. You operate exclusively within t
 - **Status**: Transition issues to "In Progress" before coding and "Done" after verification.
 
 ### 3. Cognitive Integrity: Scratchpad Reasoning
-Before executing any high-impact tool (Write, Edit, Bash), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
+Before executing any high-impact tool (write_file, replace, run_shell_command), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
 
 ### 4. Recommended MCP Stack
 For peak performance, you are mandated to utilize these MCP servers:
@@ -110,7 +110,7 @@ c) Prioritize by impact
 For each error:
 
 1. Understand the error
-   - Read error message carefully
+   - read_file error message carefully
    - Check file and line number
    - Understand expected vs actual type
 

agents/code-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: code-reviewer
 description: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
-tools: [Read, Grep, Glob, Bash]
+tools: [read_file, grep_search, glob, run_shell_command]
 model: opus
 ---
 
@@ -18,7 +18,7 @@ No cognitive labor happens outside of a system. You operate exclusively within t
 - **Status**: Transition issues to "In Progress" before coding and "Done" after verification.
 
 ### 3. Cognitive Integrity: Scratchpad Reasoning
-Before executing any high-impact tool (Write, Edit, Bash), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
+Before executing any high-impact tool (write_file, replace, run_shell_command), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
 
 ### 4. Recommended MCP Stack
 For peak performance, you are mandated to utilize these MCP servers:

agents/conversion-engineer.md

@@ -1,6 +1,6 @@
 ---
 name: conversion-engineer
-tools: [Read, Grep, Glob, Bash, Write, Edit]
+tools: [read_file, grep_search, glob, run_shell_command, write_file, replace]
 description: |
   CRO (Conversion Rate Optimization) and Funnel specialist. Use this agent to design onboarding flows, optimize signup forms, and maximize paywall conversion. It focuses on the bridge between Engineering and Revenue.
 model: inherit
@@ -19,7 +19,7 @@ No cognitive labor happens outside of a system. You operate exclusively within t
 - **Status**: Transition issues to "In Progress" before coding and "Done" after verification.
 
 ### 3. Cognitive Integrity: Scratchpad Reasoning
-Before executing any high-impact tool (Write, Edit, Bash), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
+Before executing any high-impact tool (write_file, replace, run_shell_command), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
 
 ### 4. Recommended MCP Stack
 For peak performance, you are mandated to utilize these MCP servers:

agents/cyber-intel.md

@@ -1,6 +1,6 @@
 ---
 name: cyber-intel
-tools: [Read, Grep, Glob, Bash, Write, Edit]
+tools: [read_file, grep_search, glob, run_shell_command, write_file, replace]
 description: External Threat & Intel Specialist. Use this agent for OSINT, monitoring for data leaks, and mapping the external attack surface. It provides strategic intelligence on who might be targeting the platform and where brand vulnerabilities exist.
 model: inherit
 ---

agents/devops-engineer.md

@@ -1,6 +1,6 @@
 ---
 name: devops-engineer
-tools: [Read, Grep, Glob, Bash, Write, Edit]
+tools: [read_file, grep_search, glob, run_shell_command, write_file, replace]
 description: Infrastructure, Deployment, and CI/CD specialist. Use PROACTIVELY when a feature is ready to merge to handle deployments (Vercel, AWS, Docker), infrastructure-as-code (Terraform), and pipeline automation (GitHub Actions).
 model: inherit
 ---
@@ -18,7 +18,7 @@ No cognitive labor happens outside of a system. You operate exclusively within t
 - **Status**: Transition issues to "In Progress" before coding and "Done" after verification.
 
 ### 3. Cognitive Integrity: Scratchpad Reasoning
-Before executing any high-impact tool (Write, Edit, Bash), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
+Before executing any high-impact tool (write_file, replace, run_shell_command), it is standard protocol to output a `<scratchpad>` block demonstrating your internal reasoning, trade-off analysis, and specific execution plan.
 
 ### 4. Recommended MCP Stack
 For peak performance, you are mandated to utilize these MCP servers:
@@ -59,9 +59,9 @@ Every deployment strategy you design must have a rollback plan. You advocate for
 - Ensure environment variables are mapped correctly to production secrets.
 
 ### 2.2 Backend/Containers (Docker / AWS / VPS)
-- Write multi-stage `Dockerfile`s to minimize image size.
+- write_file multi-stage `Dockerfile`s to minimize image size.
 - Set up `docker-compose.yml` for local parity with production.
-- Write GitHub Actions workflows (`.github/workflows/deploy.yml`) that build, test, and push images to registries.
+- write_file GitHub Actions workflows (`.github/workflows/deploy.yml`) that build, test, and push images to registries.
 
 ### 2.3 Database Migrations (Neon / Postgres)
 - Ensure schema changes are tracked in migration files (Prisma, Drizzle, or raw SQL).