convert-gemini-extension

A conversion command that turns a Gemini extension into the file format used by Claude Code plugins. Gemini extensions are add-ons configured with a gemini-extension.json file.

In plain words
What is it for?
Checking an extension path, reading its configuration, creating the Claude plugin folders and manifest, copying MCP server settings, and converting command files from TOML to Markdown.
Why use it?
It avoids manually copying settings and rewriting command files when moving an extension between the two systems.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/pleaseai/claude-code-plugins/convert-gemini-extension
Clone the repo
git clone --depth 1 https://github.com/pleaseai/claude-code-plugins

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 845 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00009 $0.00845
Opus 5 $0.00005 $0.00423
Sonnet 5 $0.00002 $0.00169
Haiku 4.5 $0.00001 $0.00085

Measured 2d ago against content hash 92d3398fce3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

convert-gemini-extension 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 2d 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/convert-gemini-extension.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are tasked with converting a Gemini extension to Claude Code plugin format. Follow these steps precisely:

Input

The user will provide a path to a Gemini extension directory containing gemini-extension.json.

Path to convert: $ARGUMENTS

Conversion Steps

1. Validate Input

  • Check if the provided path exists and contains gemini-extension.json
  • If not found, ask the user for the correct path

2. Read Gemini Extension Configuration

  • Read the gemini-extension.json file
  • Extract: name, description, version, mcpServers configuration

3. Create Plugin Directory Structure

  • Create .claude-plugin directory in the extension path
  • Create commands directory if it doesn't exist (it should already exist for extensions with commands)

4. Generate plugin.json

Create .claude-plugin/plugin.json with the following structure:

{
  "name": "<name from gemini-extension.json>",
  "version": "<version from gemini-extension.json>",
  "description": "<description from gemini-extension.json>",
  "commands": ["./commands"],
  "mcpServers": <copy mcpServers object from gemini-extension.json>
}

5. Convert Command Files (TOML to Markdown)

For each .toml file in the commands/ directory:

  • Read the TOML file
  • Extract description and prompt fields
  • Create a new .md file with the same base name
  • Format as:
    ---
    description: <description from TOML>
    ---
    
    <prompt from TOML with {{args}} replaced by $ARGUMENTS>
    
  • IMPORTANT: Replace all instances of {{args}} with $ARGUMENTS in the prompt
  • Keep the original TOML file (don't delete it) for reference

6. Update Marketplace Configuration

  • Read .claude-plugin/marketplace.json at the repository root
  • Add a new entry to the plugins array if not already present:
    {
      "name": "<plugin name>",
      "description": "<plugin description>",
      "source": {
        "source": "github",
        "repo": "pleaseai/<plugin-name>"
      }
    }
    
  • If the plugin already exists in marketplace.json, update its description

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 9 tokens per session scan A 92d3398fce3e

Subscribe to this mod's changes

convert-gemini-extension is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 7d ago), licensed MIT. It adds 9 tokens to every session and 845 once invoked, about $0.0000 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 2026-08-30.