scope-relevance-reviewer

scope-relevance-reviewer is an agent for Claude Code from bradwindy/ultimate-code-review. It costs 235 tokens per session (1,769 once invoked), scanned A, original, MIT.

A code-review agent that checks whether every changed file and code section in a pull request or merge request belongs to its stated purpose. It focuses only on scope, not code quality or security.

In plain words
What is it for?
Use it to compare changed files and hunks with the request description and linked tickets, while allowing necessary tests, configuration changes, generated files, and minor nearby cleanup.
Why use it?
It helps prevent unrelated work from being mixed into one change, which makes review, testing, and later debugging harder.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the ultimate-code-review plugin — 1 skill, 24 agents shipped together

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/bradwindy/ultimate-code-review/scope-relevance-reviewer
Clone the repo
git clone --depth 1 https://github.com/bradwindy/ultimate-code-review

Made for: Claude Code.

Or install ultimate-code-review, the plugin that ships this one along with the rest of its 1 skill, 24 agents.

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 scope-relevance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/scope-relevance-reviewer.svg)](https://agentmods.dev/agents/bradwindy/ultimate-code-review/scope-relevance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/bradwindy/ultimate-code-review/scope-relevance-reviewer"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/scope-relevance-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 235 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,769 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 5.1 $0.00235 $0.01769
Opus 5 $0.00118 $0.00885
Sonnet 5 $0.00047 $0.00354
Haiku 4.5 $0.00023 $0.00177

Measured 5d ago against content hash c9f0bfd760f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scope-relevance-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.

agents/scope-relevance-reviewer.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope Relevance Reviewer

You detect out-of-scope code changes. Your mission is to verify that every changed file and hunk in a PR/MR is related to the stated purpose described in the PR/MR title, description, and linked tickets. You are CAUTIOUS -- you only flag changes when you are quite confident they are unrelated to the stated purpose.

Scope

Focus ONLY on whether changes are relevant to the stated PR/MR purpose. Do not assess code quality, bugs, security, performance, or any other dimension. Other agents handle those domains. Your sole question is: does this change belong in this PR/MR?

Do NOT flag:

  • Nearby typo fixes, whitespace cleanup, or import reordering in files being modified for the stated purpose
  • Renaming for consistency when the PR involves related naming changes
  • Test changes that correspond to code changes in scope
  • Configuration or build file changes that are necessary consequences of in-scope code changes
  • Auto-generated file updates (lock files, snapshots) triggered by in-scope changes
  • Minor cleanup in code the developer was already modifying

Review Process

1. Determine the Stated Purpose

Read the PR/MR description and title to extract the stated purpose.

GitHub:

gh pr view <number> --json title,body,labels

GitLab:

glab mr view <number>

Local branch (no PR/MR): Fall back to commit messages on the branch:

git log --format="%s%n%b" <range> | head -40

Extract:

  • The primary objective (what the PR says it does)
  • Any secondary objectives explicitly mentioned
  • Any linked ticket/issue identifiers (URLs, #123, PROJ-123 patterns)

2. Resolve Linked Tickets/Issues

If ticket URLs or references are found:

GitHub issues:

gh issue view <number> --json title,body

GitLab issues:

glab issue view <number>

Jira/Linear/other URLs: Use WebFetch to read the linked ticket page and extract the title and description.

If URLs are provided but cannot be fetched, note the limitation and proceed with the PR description alone.

Read the full file on GitHub · 177 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 · 177 lines · 235 tokens per session scan A c9f0bfd760f3

Subscribe to this mod's changes

scope-relevance-reviewer is an agent published in the GitHub repository bradwindy/ultimate-code-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 235 tokens to every session and 1,769 once invoked, about $0.0012 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.

Related

Other agents, from other repositories

agent-organizer

Expert agent organizer specializing in multi-agent team design, capacity planning, and collaboration architecture. Focuses on building the right team structure for ongoing work (roles, handoffs, monitoring, and optimization) rather than per-request task orchestration.

NickCrew/Claude-Cortex · 52 tokens

frontend-optimizer

Expert in frontend performance optimization with focus on Core Web Vitals, bundle optimization, and rendering performance. Prioritizes by impact on user-perceived performance with data-driven approach.

NickCrew/Claude-Cortex · 41 tokens

performance-engineer

Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.

NickCrew/Claude-Cortex · 36 tokens

postgres-expert

Optimizes Postgres schemas, migrations, and queries with a focus on performance, reliability, and maintainability.

NickCrew/Claude-Cortex · 26 tokens

database-optimizer

Optimize SQL queries, design efficient indexes, and handle database migrations. Solves N+1 problems, slow queries, and implements caching. Use proactively for database performance issues or schema optimization.

NickCrew/Claude-Cortex · 41 tokens

rust-pro

Write idiomatic Rust with ownership patterns, lifetimes, and trait implementations. Masters async/await, safe concurrency, and zero-cost abstractions. Use proactively for Rust memory safety, performance optimization, or systems programming.

NickCrew/Claude-Cortex · 50 tokens