yaks: Agent for Claude Code

.pi/agents/deep-review-gemini.md

deep-review-gemini is an agent for Claude Code from mattwynne/yaks. It costs 14 tokens per session (123 once invoked), scanned A, a copy of deep-review-claude, MIT.

An independent technical code-review agent that uses Google Gemini to inspect a repository and write a review report.

In plain words
What is it for?
Reviewing code structure and quality, finding technical issues, and documenting file-based evidence and suggested improvements.
Why use it?
It provides a separate assessment with evidence and recommendations while leaving the repository unchanged.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is mattwynne/yaks's own configuration. It tells Claude Code how to work on yaks 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 yaks configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mattwynne/yaks. 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/mattwynne/yaks/main/.pi/agents/deep-review-gemini.md
Clone the repo
git clone --depth 1 https://github.com/mattwynne/yaks

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 deep-review-gemini

README.md
[![agentmods](https://agentmods.dev/badge/agents/mattwynne/yaks/deep-review-gemini/github.svg)](https://agentmods.dev/agents/mattwynne/yaks/deep-review-gemini)
Your own site
<a href="https://agentmods.dev/agents/mattwynne/yaks/deep-review-gemini"><img src="https://agentmods.dev/badge/agents/mattwynne/yaks/deep-review-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 deep-review-gemini

Your own site · 80×15
<a href="https://agentmods.dev/agents/mattwynne/yaks/deep-review-gemini"><img src="https://agentmods.dev/badge/agents/mattwynne/yaks/deep-review-gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 123 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 91% copy Near-identical to another mod 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 $0.00014 $0.00123
Opus 5 $0.00007 $0.00062
Sonnet 5 $0.00003 $0.00025
Haiku 4.5 $0.00001 $0.00012

Measured 10d ago against content hash 7389a9e13ba3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deep-review-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 10d 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.

Origin

This is a copy

91% identical to deep-review-claude — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.pi/agents/deep-review-gemini.md · 13 lines

What it actually says

You are an independent senior technical reviewer. You must not modify repository files. Use bash for read-only exploration only (ls/find/rg/git grep/git log/test commands are OK if non-mutating).

The only file you may write is the final review report path explicitly given in the task, and that path must be inside a temporary directory.

Produce a rigorous report with concrete evidence, file paths, and recommendations.

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. 10d ago First seen · 13 lines · 14 tokens per session scan A 7389a9e13ba3

Subscribe to this mod's changes

deep-review-gemini is an agent published in the GitHub repository mattwynne/yaks (58 stars, last pushed 28d ago), licensed MIT. It adds 14 tokens to every session and 123 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to deep-review-claude, differing in 6 lines, and is treated as a copy.

Related

Other agents, from other repositories

silent-failure-hunter

Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk of work that involves error handling, catch blocks, fallback logic, or any code that could…

troykelly/claude-skills · 0 tokens

comment-analyzer

Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes: (1) After generating large documentation comments or docstrings, (2) Before finalizing a pull request that adds or modifies comments, (3) When reviewing existing comments for potential…

troykelly/claude-skills · 0 tokens

code-reviewer

MUST BE USED after implementing code changes. Performs comprehensive 7-criteria code review and posts mandatory review artifact to GitHub issue. Invoke proactively before any PR creation.

troykelly/claude-skills · 38 tokens

code-simplifier

Use this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. This agent should be triggered automatically after completing a coding task or writing a logical chunk of code. It simplifies code by following project best…

troykelly/claude-skills · 86 tokens

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

troykelly/claude-skills · 0 tokens

type-design-analyzer

Use this agent when you need expert analysis of type design in your codebase. Specifically use it: (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, (2) during pull request creation to review all types being added, (3) when refactoring existing types to…

troykelly/claude-skills · 0 tokens