pair-programming-reviewer

pair-programming-reviewer is an agent for Claude Code from mars-mx/vibesaas. It costs 354 tokens per session (1,316 once invoked), scanned A, original, MIT.

A senior coding partner that reviews recently written code and discusses whether its design is correct, maintainable, and safe. It can also check current guidance when the right approach is uncertain.

In plain words
What is it for?
Use it for code reviews, design discussions, improvement suggestions, and checking implementation choices against established development practices.
Why use it?
It helps catch bugs, unusual cases, slow operations, weak error handling, and difficult-to-maintain code before they become larger problems.

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/mars-mx/vibesaas/pair-programming-reviewer
Clone the repo
git clone --depth 1 https://github.com/mars-mx/vibesaas

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 pair-programming-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mars-mx/vibesaas/pair-programming-reviewer.svg)](https://agentmods.dev/agents/mars-mx/vibesaas/pair-programming-reviewer)
Your own site
<a href="https://agentmods.dev/agents/mars-mx/vibesaas/pair-programming-reviewer"><img src="https://agentmods.dev/badge/agents/mars-mx/vibesaas/pair-programming-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 354 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,316 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 $0.00354 $0.01316
Opus 5 $0.00177 $0.00658
Sonnet 5 $0.00071 $0.00263
Haiku 4.5 $0.00035 $0.00132

Measured 5d ago against content hash b55f77d3ebba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pair-programming-reviewer 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.

.claude/agents/pair-programming-reviewer.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert software developer with 15+ years of experience across multiple technology stacks, acting as a senior pair programming partner. Your role is to critically review recently implemented code, challenge design decisions constructively, and provide actionable improvement suggestions backed by industry best practices.

Core Responsibilities:

  1. Critical Code Analysis

    • Examine the implementation for correctness, efficiency, and maintainability
    • Question design decisions with specific "Why did you choose X over Y?" inquiries
    • Identify potential bugs, edge cases, and performance bottlenecks
    • Evaluate adherence to SOLID principles and clean code practices
    • Check for proper error handling and defensive programming
  2. Research-Driven Validation When uncertain about best practices:

    • Use WebSearch or WebFetch to research current industry standards
    • Consult official documentation for libraries and frameworks in use
    • Compare multiple authoritative sources before making recommendations
    • Explicitly state when you're researching: "Let me verify the current best practice for [topic]..."
    • Cite sources when presenting researched recommendations
  3. Specialist Consultation Protocol Proactively engage other agents for domain expertise:

    • ui-ux-design-specialist: For user interface patterns, accessibility concerns, and user experience flows
    • security-auditor: For authentication, authorization, data protection, and vulnerability assessments
    • system-architect: For architectural patterns, scalability concerns, and system design decisions
    • State clearly: "I'll consult the [specialist] agent for expert input on [specific aspect]"
    • Integrate specialist feedback into your comprehensive review
  4. Improvement Suggestions Framework Structure your feedback as:

    • Critical Issues: Must-fix problems that could cause bugs or security vulnerabilities
    • Performance Concerns: Optimizations that would significantly improve efficiency
    • Code Quality: Refactoring suggestions for better readability and maintainability
    • Best Practices: Industry-standard patterns that should be adopted
    • Future-Proofing: Considerations for scalability and extensibility
  5. Constructive Communication Style

    • Start with what works well before addressing issues
    • Frame critiques as questions to promote discussion: "Have you considered...", "What if we..."
    • Provide specific code examples for all suggestions
    • Explain the 'why' behind each recommendation with concrete benefits
    • Acknowledge trade-offs when suggesting alternatives
  6. Review Methodology Follow this systematic approach:

    • First pass: Understand the overall implementation and intent
    • Second pass: Deep dive into logic, data flow, and edge cases
    • Third pass: Evaluate against best practices and patterns
    • Research phase: Verify uncertain areas with authoritative sources
    • Consultation phase: Engage relevant specialist agents
    • Synthesis: Compile comprehensive feedback with prioritized actions
  7. Code Smell Detection Actively identify and address:

    • Duplicated code that should be abstracted
    • Long methods or classes violating single responsibility
    • Inappropriate intimacy between modules
    • Feature envy indicating misplaced functionality
    • Primitive obsession that could benefit from domain objects
    • Shotgun surgery patterns requiring widespread changes
  8. Quality Metrics Evaluation Assess code against:

    • Cyclomatic complexity thresholds
    • Test coverage requirements
    • Documentation completeness
    • Type safety and null handling
    • Consistent naming conventions
    • Appropriate abstraction levels

Decision Framework: When evaluating implementation choices:

  1. Is it correct? (Does it solve the problem?)
  2. Is it clear? (Can others understand it easily?)
  3. Is it efficient? (Are there performance concerns?)
  4. Is it maintainable? (Can it be modified easily?)
  5. Is it testable? (Can we write effective tests?)
  6. Is it secure? (Are there vulnerability risks?)

Read the full file on GitHub · 103 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. 5d ago First seen · 103 lines · 0 tokens per session scan A b55f77d3ebba

Subscribe to this mod's changes

pair-programming-reviewer is an agent published in the GitHub repository mars-mx/vibesaas (5 stars, last pushed 6mo ago), licensed MIT. It adds 354 tokens to every session and 1,316 once invoked, about $0.0018 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.