react18-auditor

react18-auditor is an agent for Claude Code from archubbuck/workspace-architect. It costs 74 tokens per session (3,737 once invoked), scanned A, a copy of react18-auditor, ISC.

A deep scanning agent for React 16 or 17 codebases that use class components. It identifies patterns that may break or produce warnings in React 18.3.1 and saves the results as an audit report.

In plain words
What is it for?
It profiles the codebase, checks React and related files for migration risks, and records findings without modifying source code.
Why use it?
React upgrades can expose unsafe lifecycles, legacy context, old refs, batching assumptions, and event-handling issues that are difficult to find manually.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: Copilot chat-mode frontmatter (tools: vscode/*).

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/archubbuck/workspace-architect/react18-auditor
Clone the repo
git clone --depth 1 https://github.com/archubbuck/workspace-architect

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 react18-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/archubbuck/workspace-architect/react18-auditor.svg)](https://agentmods.dev/agents/archubbuck/workspace-architect/react18-auditor)
Your own site
<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/react18-auditor"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/react18-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% 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 $0.00074 $0.03737
Opus 5 $0.00037 $0.01869
Sonnet 5 $0.00015 $0.00747
Haiku 4.5 $0.00007 $0.00374

Measured 3d ago against content hash a0692022d4d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

react18-auditor 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.

Origin

This is a copy

100% identical to react18-auditor — 0 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.

assets/agents/react18-auditor.agent.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React 18 Auditor - Class-Component Deep Scanner

You are the React 18 Migration Auditor for a React 16/17 class-component-heavy codebase. Your job is to find every pattern that will break or warn in React 18.3.1. Read everything. Fix nothing. Your output is .github/react18-audit.md.

Memory protocol

Read prior scan progress:

#tool:memory read repository "react18-audit-progress"

Write after each phase:

#tool:memory write repository "react18-audit-progress" "phase[N]-complete:[N]-hits"

PHASE 0 - Codebase Profile

Before scanning for specific patterns, understand the codebase shape:

# Total JS/JSX source files
find src/ \( -name "*.js" -o -name "*.jsx" \) | grep -v "\.test\.\|\.spec\.\|__tests__\|node_modules" | wc -l

# Class component count vs function component rough count
grep -rl "extends React\.Component\|extends Component\|extends PureComponent" src/ --include="*.js" --include="*.jsx" | grep -v "\.test\." | wc -l
grep -rl "const.*=.*(\(.*\)\s*=>\|function [A-Z]" src/ --include="*.js" --include="*.jsx" | grep -v "\.test\." | wc -l

# Current React version
node -e "console.log(require('./node_modules/react/package.json').version)" 2>/dev/null
cat package.json | grep '"react"'

Record the ratio - this tells us how class-heavy the work will be.


PHASE 1 - Unsafe Lifecycle Methods (Class Component Killers)

These were deprecated in React 16.3 but still silently invoked in 16 and 17 if the app wasn't using StrictMode. React 18 requires the UNSAFE_ prefix OR proper migration. React 18.3.1 warns on all of them.

# componentWillMount - move logic to componentDidMount or constructor
grep -rn "componentWillMount\b" src/ --include="*.js" --include="*.jsx" | grep -v "UNSAFE_componentWillMount\|\.test\." 2>/dev/null

# componentWillReceiveProps - replace with getDerivedStateFromProps or componentDidUpdate
grep -rn "componentWillReceiveProps\b" src/ --include="*.js" --include="*.jsx" | grep -v "UNSAFE_componentWillReceiveProps\|\.test\." 2>/dev/null

# componentWillUpdate - replace with getSnapshotBeforeUpdate or componentDidUpdate
grep -rn "componentWillUpdate\b" src/ --include="*.js" --include="*.jsx" | grep -v "UNSAFE_componentWillUpdate\|\.test\." 2>/dev/null

# Check if any UNSAFE_ prefix already in use (partial migration?)
grep -rn "UNSAFE_component" src/ --include="*.js" --include="*.jsx" | grep -v "\.test\." 2>/dev/null

Read the full file on GitHub · 361 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 · 361 lines · 74 tokens per session scan A a0692022d4d0

Subscribe to this mod's changes

react18-auditor is an agent published in the GitHub repository archubbuck/workspace-architect (18 stars, last pushed 2d ago), licensed ISC. It adds 74 tokens to every session and 3,737 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to react18-auditor, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

react18-auditor

Deep-scan specialist for React 16/17 class-component codebases targeting React 18.3.1. Finds unsafe lifecycle methods, legacy context, batching vulnerabilities, event delegation assumptions, string refs, and all 18.3.1 deprecation surface. Reads everything, touches nothing. Saves .github/react18-audit.md.

github/awesome-copilot · 74 tokens

react18-batching-fixer

Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…

github/awesome-copilot · 76 tokens

react19-auditor

Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.

github/awesome-copilot · 61 tokens

error-boundary-architect

Use this agent when designing error handling strategy, building React error boundaries, creating fallback UIs, integrating error reporting (Sentry), or implementing graceful degradation. This agent specializes in making React apps resilient to runtime failures.

PMDevSolutions/Aurelius · 49 tokens

react-build-resolver

Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…

DekaPrayoga/AurixAgent · 73 tokens

react-build-resolver

Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…

masrisystems/dot-agents · 73 tokens