Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/bgreenwell/claude-plugins/gemini-reviewgit clone --depth 1 https://github.com/bgreenwell/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/bgreenwell/claude-plugins/gemini-review)<a href="https://agentmods.dev/commands/bgreenwell/claude-plugins/gemini-review"><img src="https://agentmods.dev/badge/commands/bgreenwell/claude-plugins/gemini-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01869 |
| Opus 5 | $0.00018 | $0.00934 |
| Sonnet 5 | $0.00007 | $0.00374 |
| Haiku 4.5 | $0.00004 | $0.00187 |
Grade A, and why
gemini-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gemini-review Command
Quick, explicit Gemini review with sensible defaults and structured output.
Syntax
/gemini-review [file-pattern] [--model flash|pro] [--focus area]
Arguments
file-pattern (optional)
- File path, glob pattern, or directory to review
- If omitted: Reviews git staged files (
git diff --cached --name-only) - Examples:
src/auth/*,src/auth/login.js,tests/*.test.js
--model (optional)
- Model to use for review
- Options:
flash(fast, default) orpro(thorough) - Default:
gemini-2.5-flash
--focus (optional)
- Specific area to focus review on
- Examples:
security,performance,maintainability,testing - Default: General code quality review
How It Works
When user invokes this command:
-
Parse Arguments
- Extract file pattern (or use git staged files)
- Determine model (Flash or Pro)
- Identify focus area if specified
-
Validate Files
- Check gemini-cli is installed and authenticated
- Verify files exist and are accessible
- Filter out binary/build files
-
Construct Prompt
- Build focused Gemini prompt based on review type
- Include @ file references
- Add focus-specific criteria if --focus provided
-
Execute Review
- Call gemini-cli with
--output-format json - Use specified model (--model flag)
- Capture structured JSON response
- Call gemini-cli with
-
Parse Results
- Extract review findings from JSON
- Extract token usage statistics
- Parse for errors, warnings, suggestions
-
Format Output
- Display file-by-file breakdown
- Show severity levels (✓ OK, ⚠ Warning, ❌ Error)
- Present actionable recommendations
- Show token usage at bottom
Examples
Review Git Staged Files
/gemini-review
Behavior: Reviews all files in git staging area
Review Specific Files
/gemini-review src/auth/login.js src/auth/session.js
Behavior: Reviews just those two files
Review with Pattern
/gemini-review src/auth/*
Behavior: Reviews all files in src/auth/
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 300 lines · 37 tokens per session scan A 2d7995a303b8
gemini-review is a command published in the GitHub repository bgreenwell/claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 37 tokens to every session and 1,869 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.