From gemini
Perform a code review using Gemini CLI. This gives you a second opinion from a different AI model.
How this command is triggered — by the user, by Claude, or both
Slash command
/gemini:reviewThe summary Claude sees in its command listing — used to decide when to auto-load this command
Perform a code review using Gemini CLI. This gives you a second opinion from a different AI model. ## Step 1: Parse --model parameter Check if $ARGUMENTS contains `--model <value>`: - If yes: extract the value as MODEL, remove `--model <value>` from $ARGUMENTS - If no: set MODEL = pro Valid model values: flash, pro, flash-lite, or any full model name. ## Step 2: Determine input If $ARGUMENTS (after --model removal) is provided: - If it contains glob characters (* or ?), use the Glob tool to expand it, then Read each matched file - Otherwise, Read the single file directly - Concatenate ...
Perform a code review using Gemini CLI. This gives you a second opinion from a different AI model.
Check if $ARGUMENTS contains --model <value>:
--model <value> from $ARGUMENTSValid model values: flash, pro, flash-lite, or any full model name.
If $ARGUMENTS (after --model removal) is provided:
If $ARGUMENTS is empty:
git diff HEAD 2>/dev/nullgit diff --cachedDetermine the absolute path to the plugin root (the parent of the commands/ directory containing this file).
system-prompts/review.md → SYSTEM_PROMPT_PATHpolicies/readonly.toml → POLICY_PATHRun the following bash command, passing REVIEW_INPUT via stdin to avoid shell escaping issues:
output=$(printf "%s" "$REVIEW_INPUT" | GEMINI_SYSTEM_MD="$SYSTEM_PROMPT_PATH" gemini -m $MODEL --admin-policy "$POLICY_PATH" 2>&1)
exit_code=$?
if [ $exit_code -ne 0 ] && echo "$output" | grep -qi "429\|quota\|RESOURCE_EXHAUSTED\|rate limit\|overloaded"; then
echo "[Fallback] $MODEL unavailable (quota/rate limit), retrying with flash..." >&2
output=$(printf "%s" "$REVIEW_INPUT" | GEMINI_SYSTEM_MD="$SYSTEM_PROMPT_PATH" gemini -m flash --admin-policy "$POLICY_PATH" 2>&1)
fi
echo "$output"
Note: We pipe input via stdin instead of -p flag to handle large diffs and special characters safely. If the preferred model hits quota limits, it automatically falls back to flash.
Show the Gemini response directly to the user. Do not modify, summarize, or reformat it.
gemini command is not found: suggest running /gemini:setup firstgemini interactively to re-authenticate via Google OAuthnpx claudepluginhub haunchen/gemini-plugin-cc --plugin gemini/reviewReviews staged changes or recent commits across five axes—correctness, readability, architecture, security, performance—producing categorized findings with file:line references and fixes.
/reviewRuns Codex code review on local git state (working tree or vs base branch). Supports --wait/--background, --base <ref>, --scope auto|working-tree|branch.
/reviewInvokes multiple external AI CLIs (Gemini, Claude, Codex, etc.) to independently review a phase plan and produces a structured REVIEWS.md with per-reviewer feedback.
/reviewRuns an enhanced multi-LLM PR review with inline comments, checking availability of local and API-based providers for cross-model escalation.
/reviewReviews HTML file for design anti-patterns, principles violations, and accessibility issues. Generates markdown report with status tables and recommendations.
/reviewReviews specified code scope via four specialists (quality, security, performance, architecture), producing summary, detailed findings, refactoring suggestions, prioritized action plan.