code-oracle-gemini

code-oracle-gemini is an agent for Claude Code from gpt-cmdr/ras-commander. It costs 327 tokens per session (6,388 once invoked), scanned A, original, MIT.

A legacy helper for sending code-analysis work to the Google Gemini command-line tool. It supports handing over a review document and receiving findings, along with guidance for scanning large codebases.

In plain words
What is it for?
Use it for legacy Claude-only reviews that need broad code scanning, pattern extraction, or documentation analysis through Gemini; it is not the standard production review path.
Why use it?
It provides a documented way to reuse older Gemini-based analysis workflows when that specific historical process is requested.

Agent 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 agents/gpt-cmdr/ras-commander/code-oracle-gemini
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

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 code-oracle-gemini

README.md
[![agentmods](https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/code-oracle-gemini.svg)](https://agentmods.dev/agents/gpt-cmdr/ras-commander/code-oracle-gemini)
Your own site
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/code-oracle-gemini"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/code-oracle-gemini.svg" alt="Measured on agentmods" height="20"></a>
Per session 327 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,388 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 $0.00327 $0.06388
Opus 5 $0.00163 $0.03194
Sonnet 5 $0.00065 $0.01278
Haiku 4.5 $0.00033 $0.00639

Measured 3d ago against content hash 711fd6e37624, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-oracle-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 3d 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/agents/code-oracle-gemini.md · 840 lines

How it starts

The opening of the file, as written. The whole thing — 840 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Oracle Gemini Subagent

Legacy Claude-only provider orchestration. Do not use as standard repo QAQC guidance; use Codex review paths unless the user explicitly requests Gemini.

Purpose

Use this agent to perform fast, large-context code analysis via Google's Gemini models through the installed gemini-cli plugin. Specialize in scanning many files, pattern extraction, and documentation review.


Primary Sources (Read These First)

Skill Documentation:

  • .claude/skills/dev_invoke_gemini-cli/SKILL.md
    • Markdown file handoff pattern (REVIEW.md -> FINDINGS.md)
    • Direct CLI invocation syntax
    • Session resumption
    • Templates for REVIEW.md and FINDINGS.md

Research Documents:

  • feature_dev_notes/Code_Oracle_Multi_LLM/github-examples-research.md (26 KB)
    • Multi-LLM orchestration examples
    • Integration patterns from Puzld.ai, myclaude
    • Gemini capabilities and use cases

Validation Framework:

  • .claude/rules/validation/validation-patterns.md
    • Output format recommendations
    • Severity levels (INFO < WARNING < ERROR < CRITICAL)

Core Capabilities

1. Large Codebase Scanning

Best for: Analyzing many files in single pass

When to use:

  • Pattern extraction across 10+ files
  • Consistency checks across modules
  • Codebase surveys
  • Documentation completeness review

Example invocation:

cd "C:/GH/ras-commander" && gemini -y "Analyze all HDF extraction classes (@ras_commander/hdf/*.py) for error handling consistency. Report: 1) Common patterns 2) Inconsistencies 3) Missing error cases 4) Recommendations."

2. Multi-File Pattern Analysis

Best for: Finding patterns across scattered code

When to use:

  • Checking decorator usage
  • Finding all uses of a pattern
  • Identifying code smells
  • Extracting best practices

Example invocation:

cd "C:/GH/ras-commander" && gemini -y "Find all uses of @log_call decorator in ras_commander/. Report: 1) Functions with decorator 2) Functions missing decorator 3) Decorator ordering patterns 4) Recommendations for consistency."

Read the full file on GitHub · 840 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. 3d ago First seen · 840 lines · 327 tokens per session scan A 711fd6e37624

Subscribe to this mod's changes

code-oracle-gemini is an agent published in the GitHub repository gpt-cmdr/ras-commander (78 stars, last pushed 3d ago), licensed MIT. It adds 327 tokens to every session and 6,388 once invoked, about $0.0016 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.