unity-editor-mcp: Command for Claude Code

.claude/commands/discuss-with-gemini.md

discuss-with-gemini is a command for Claude Code from akiojin/unity-editor-mcp. It costs 0 tokens per session (741 once invoked), scanned A, original, MIT.

A command that uses the Gemini command-line tool to discuss the current software project from several perspectives. It gathers Git status, staged and unstaged changes, and recent commits before starting the discussion.

In plain words
What is it for?
Use it to review ongoing code changes with Gemini, identify design or quality concerns, and refine the work through an iterative discussion.
Why use it?
It gives you an additional review of architecture, performance, scalability, maintainability, security, and best-practice concerns without preparing the project context by hand.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Claude Code; mentions Gemini CLI.

This is akiojin/unity-editor-mcp's own configuration. It tells Claude Code how to work on unity-editor-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unity-editor-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to akiojin/unity-editor-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/akiojin/unity-editor-mcp/main/.claude/commands/discuss-with-gemini.md
Clone the repo
git clone --depth 1 https://github.com/akiojin/unity-editor-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for discuss-with-gemini

README.md
[![agentmods](https://agentmods.dev/badge/commands/akiojin/unity-editor-mcp/discuss-with-gemini/github.svg)](https://agentmods.dev/commands/akiojin/unity-editor-mcp/discuss-with-gemini)
Your own site
<a href="https://agentmods.dev/commands/akiojin/unity-editor-mcp/discuss-with-gemini"><img src="https://agentmods.dev/badge/commands/akiojin/unity-editor-mcp/discuss-with-gemini/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for discuss-with-gemini

Your own site · 80×15
<a href="https://agentmods.dev/commands/akiojin/unity-editor-mcp/discuss-with-gemini"><img src="https://agentmods.dev/badge/commands/akiojin/unity-editor-mcp/discuss-with-gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 741 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00741
Opus 5 $0.00000 $0.00370
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 8d ago against content hash 2e49dfb3e1cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

discuss-with-gemini 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 8d 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.

.claude/commands/discuss-with-gemini.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

discuss-with-gemini

Use Gemini CLI to conduct in-depth discussions about current work, enhancing Claude Code's accuracy through multi-perspective analysis and iterative refinement.

Prerequisites

Before using this command, ensure:

  • Gemini CLI is installed (gemini command available)
  • Authenticated via gcloud auth application-default login

Execution Steps

  1. Gather Current Context First, I'll collect information about your current work:

    # Check Git status and recent changes
    !git status --porcelain
    !git diff --cached
    !git diff
    !git log --oneline -10
    
  2. Prepare Discussion Topics Based on the context, I'll prepare discussion points covering:

    • Architecture and design patterns
    • Performance and scalability
    • Maintainability and code quality
    • Security considerations
    • Best practices alignment
  3. Initiate Gemini Discussion I'll create a comprehensive prompt and start the discussion:

    # Create temporary file with context and questions
    !echo "[Discussion prompt will be here]" > /tmp/gemini_discussion.md
    
    # Start interactive discussion with Gemini
    !gemini -p < /tmp/gemini_discussion.md
    
  4. Iterative Refinement Based on Gemini's initial response, I'll:

    • Identify areas needing deeper analysis
    • Formulate follow-up questions
    • Continue the discussion for 3-5 rounds

    Each round will explore:

    • Alternative approaches and trade-offs
    • Implementation specifics with code examples
    • Potential risks and edge cases
    • Priority recommendations
  5. Generate Action Plan After the discussion rounds, I'll synthesize an actionable plan:

    • Immediate implementation items (High priority)
    • Short-term improvements (Medium priority)
    • Long-term considerations (Low priority)
    • Implementation guidelines and anti-patterns to avoid
  6. Save Discussion Log The complete discussion will be saved for future reference:

    # Create discussion log directory if needed
    !mkdir -p .claude/discussion_logs
    
    # Save timestamped log
    !echo "[Discussion content]" > .claude/discussion_logs/gemini_discussion_$(date +%Y%m%d_%H%M%S).md
    

Read the full file on GitHub · 110 lines

Changes

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.

  1. 8d ago First seen · 110 lines · 0 tokens per session scan A 2e49dfb3e1cc

Subscribe to this mod's changes

discuss-with-gemini is a command published in the GitHub repository akiojin/unity-editor-mcp (11 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 741 tokens. 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 2026-08-30.