google-ecosystem

PROACTIVELY use when analyzing large codebases (100K+ tokens) that exceed Claude's context. Leverages Gemini's large context window for architecture review, dependency analysis, and pattern detection.

PROACTIVELY use when attempting high-risk code modifications. Runs experimental refactors, migrations, and breaking changes using Gemini CLI's checkpointing with instant rollback capability.

PROACTIVELY use before delegating to Gemini CLI to ensure context sync. Detects drift between CLAUDE.md and GEMINI.md, performs one-way sync with CLAUDE.md as source of truth.

PROACTIVELY use when exploring unfamiliar codebases that exceed 50K tokens. Leverages Gemini's large context window to produce Claude-actionable exploration reports with architecture, patterns, and implementation guidance.

PROACTIVELY use when researching Gemini CLI features, searching documentation, resolving doc_ids, or finding guidance on Gemini CLI topics (checkpointing, model routing, tools, extensions, MCP, memport, etc.). Auto-loads gemini-cli-docs skill.

PROACTIVELY use when interactive TUI commands are needed (vim, htop, git rebase -i, nano). Claude cannot handle interactive shells - this agent bridges the gap via Gemini CLI.

PROACTIVELY use when generating architectural plans or implementation strategies. Leverages Google Gemini CLI as a second brain for high-level planning across ANY technology stack.

PROACTIVELY use when running risky operations that need verification and automatic rollback. Combines Gemini's checkpointing and sandboxing for safe experimentation with failure recovery.

PROACTIVELY use when safety isolation is required for risky shell operations. Executes untrusted code analysis and destructive commands in Gemini CLI's sandboxed environment.

PROACTIVELY use when validation of analysis, plans, or decisions is needed. Obtains Gemini's independent perspective via headless mode for structured responses with alternative viewpoints.

Manage Gemini CLI documentation lifecycle. Actions: scrape, validate, refresh, rebuild-index, clear-cache.

Send a file to Gemini CLI for structured code analysis. Use when you need security audits, performance reviews, architecture analysis, or bug detection.

Central authority for Gemini CLI Checkpointing. Covers git-based file snapshots, automatic state saving, /restore command, and rollback. Use when enabling checkpointing, restoring previous states, undoing changes, or planning experimental workflows with Gemini. Delegates 100% to gemini-cli-docs for official documentation.

Single source of truth and librarian for ALL Gemini CLI documentation. Manages local documentation storage, scraping, discovery, and resolution. Use when finding, locating, searching, or resolving Gemini CLI documentation; discovering docs by keywords, category, tags, or natural language queries; scraping from llms.txt; managing index metadata (keywords, tags, aliases); or rebuilding index from filesystem. Run scripts to scrape, find, and resolve documentation. Handles doc_id resolution, keyword search, natural language queries, category/tag filtering, alias resolution, llms.txt parsing, markdown subsection extraction for internal use, hash-based drift detection, and comprehensive index maintenance.

Expert guide for executing the Google Gemini CLI in non-interactive and headless modes. Covers command syntax, piping input, output handling, and automation patterns. Use when running gemini commands, piping context to Gemini, scripting Gemini workflows, or using interactive shell mode. Delegates to gemini-cli-docs for official command references.

Expert guide for creating custom Gemini CLI commands. Covers slash command definitions (.toml), argument parsing, and shell execution. Use when creating custom Gemini commands, defining TOML command files, adding command arguments, or building extension-based commands. Delegates to gemini-cli-docs.

Expert guide for configuring Google Gemini CLI. Covers global vs project settings.json, Trusted Folders, Policy Engine, and environment variables. Use when configuring Gemini settings, managing trusted folders, setting up security policies, or troubleshooting configuration precedence. Delegates to gemini-cli-docs for official references.

Facilitates context sharing and strategic delegation between Claude Code and Gemini CLI. Syncs CLAUDE.md to GEMINI.md and provides agent selection guidance. Use when onboarding Gemini to a project, syncing instructions between agents, or deciding whether to use Claude or Gemini for a specific task.

Strategic patterns for Claude-to-Gemini delegation. Covers decision criteria, execution patterns, result parsing, and error handling. Use when determining if a task should be delegated to Gemini CLI.

Strategic patterns for codebase exploration using Gemini's large context window. Covers token thresholds, model routing, and exploration strategies. Use when deciding between Claude and Gemini for exploration, analyzing large codebases, or choosing between Flash and Pro models for context size.

Explore entire codebase with Gemini's large context window. Use when starting on unfamiliar codebases or mapping dependencies across large projects.

Expert guide for building and managing Gemini CLI Extensions. Covers extension anatomy, GEMINI.md context, commands, MCP integration, and publishing. Use when creating Gemini extensions, linking local extensions, packaging MCP servers, or installing extensions from GitHub. Delegates to gemini-cli-docs.

Parse Gemini CLI headless output (JSON and stream-JSON formats). Covers response extraction, stats interpretation, error handling, and tool call analysis. Use when processing Gemini CLI programmatic output.

Expert guide for Model Context Protocol (MCP) integration with Gemini CLI. Covers MCP server configuration (HTTP, SSE, Stdio), connection management, and tool permissions. Use when adding MCP servers to Gemini, configuring transports, troubleshooting MCP connections, or managing tool permissions. Delegates to gemini-cli-docs.

Synchronization patterns for CLAUDE.md and GEMINI.md memory files. Covers import syntax, drift detection, and one-way sync. Use when setting up GEMINI.md, detecting context drift between memory files, understanding @import syntax, or troubleshooting sync issues.

Generate Claude-executable implementation plans using Gemini's reasoning

Send a quick headless query to Gemini CLI and display the response with stats

Central authority for Gemini CLI sandboxing and isolation. Covers Docker, Podman, macOS Seatbelt profiles, and security boundaries. Use when enabling sandboxing, choosing sandbox methods, configuring Seatbelt profiles, or troubleshooting sandbox issues. Delegates 100% to gemini-cli-docs for official documentation.

Get Gemini's independent analysis on recent context or specified topic

Central authority for Gemini CLI session management. Covers session resume, retention policies, session browser, and cleanup. Use when resuming Gemini sessions, configuring retention, browsing past sessions, or managing session storage. Delegates 100% to gemini-cli-docs for official documentation.

Optimize token usage when delegating to Gemini CLI. Covers token caching, batch queries, model selection (Flash vs Pro), and cost tracking. Use when planning bulk Gemini operations.

Central authority for Claude-Gemini shared workspace architecture. Defines directory structure, artifact exchange, and file naming conventions. Use when setting up dual-CLI workflows, deciding where to store AI artifacts, or managing cross-CLI file exchange.

Guide for creating Gemini CLI policy engine TOML rules. Covers rule syntax, priority tiers, conditions, and MCP wildcards. Use when restricting Gemini tools, creating security policies, controlling MCP server permissions, or setting up approval workflows.

Synchronize CLAUDE.md to GEMINI.md and check for context drift

Guide for building Gemini CLI TOML custom commands. Covers syntax, templates, argument handling, shell injection, and file injection. Use when creating Gemini TOML commands, adding {{args}} argument handling, injecting shell output with !{}, or troubleshooting command issues.

1 hook across 1 event