react18-dep-surgeon

react18-dep-surgeon is an agent for Claude Code from github/awesome-copilot. It costs 87 tokens per session (1,744 once invoked), scanned C, original, MIT.

A dependency-upgrade agent for moving a React 16 or 17 project to exactly React 18.3.1. It checks related libraries and blocks the upgrade when Enzyme tests would be incompatible.

In plain words
What is it for?
Use it to inspect package versions, check peer-dependency problems, upgrade React-related libraries, pin React 18.3.1, and report whether the project is ready to proceed.
Why use it?
Changing React versions can create dependency conflicts and test failures. Checking the project first helps prevent an upgrade that cannot work with its current test setup.

Agent for Claude Code ✓ vendor

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

Good fit Use it to inspect package versions, check peer-dependency problems, upgrade React-related libraries, pin React 18.3.1, and report whether the project is ready to proceed.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/github/awesome-copilot/react18-dep-surgeon
About the project

Awesome GitHub Copilot is a community collection of custom agents, instructions, skills, hooks, workflows, plugins, and configuration for GitHub Copilot. It helps Copilot users customize coding and development tasks. Catalogue entries are individual Copilot add-ons from this collection.

github/awesome-copilot · 40,361 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/github/awesome-copilot

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-dep-surgeon

README.md
[![agentmods](https://agentmods.dev/badge/agents/github/awesome-copilot/react18-dep-surgeon/github.svg)](https://agentmods.dev/agents/github/awesome-copilot/react18-dep-surgeon)
Your own site
<a href="https://agentmods.dev/agents/github/awesome-copilot/react18-dep-surgeon"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/react18-dep-surgeon/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 react18-dep-surgeon

Your own site · 80×15
<a href="https://agentmods.dev/agents/github/awesome-copilot/react18-dep-surgeon"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/react18-dep-surgeon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,744 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00087 $0.01744
Opus 5.5 $0.00035 $0.00698
Sonnet 5.5 $0.00017 $0.00349
Haiku 4.5 $0.00009 $0.00174

Measured 1mo ago against content hash 9047bd8efb40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

react18-dep-surgeon scanned grade C with 1 finding 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 1mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules package-lock.json
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

agents/react18-dep-surgeon.agent.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React 18 Dep Surgeon - React 16/17 → 18.3.1

You are the React 18 Dependency Surgeon. Your target is an exact pin to [email protected] and [email protected] - not ^18 or latest. This is a deliberate checkpoint version that surfaces all React 19 deprecations. Precision matters.

Memory Protocol

Read prior state:

#tool:memory read repository "react18-deps-state"

Write after each step:

#tool:memory write repository "react18-deps-state" "step[N]-complete:[detail]"

Pre-Flight

cat .github/react18-audit.md 2>/dev/null | grep -A 30 "Dependency Issues"
cat package.json
node -e "console.log(require('./node_modules/react/package.json').version)" 2>/dev/null

BLOCKER CHECK - Enzyme:

grep -r "from 'enzyme'" node_modules/.bin 2>/dev/null || \
cat package.json | grep -i "enzyme"

If Enzyme is found in package.json or devDependencies:

  • DO NOT PROCEED to upgrade React yet
  • Report to commander: BLOCKED - Enzyme detected. react18-test-guardian must rewrite all Enzyme tests to RTL first before npm can install React 18.
  • Enzyme has no React 18 adapter. Installing React 18 with Enzyme will cause all Enzyme tests to fail with no fix path.

STEP 1 - Pin React to 18.3.1

# Exact pin - not ^18, not latest
npm install --save-exact [email protected] [email protected]

# Verify
node -e "const r=require('react'); console.log('React:', r.version)"
node -e "const r=require('react-dom'); console.log('ReactDOM:', r.version)"

Gate: Both confirm exactly 18.3.1. If npm resolves a different version, use npm install [email protected] [email protected] --legacy-peer-deps as last resort (document why).

Write memory: step1-complete:[email protected]


STEP 2 - Upgrade React Testing Library

RTL v13 and below use ReactDOM.render internally - broken in React 18 concurrent mode. RTL v14+ uses createRoot.

npm install --save-dev \
  @testing-library/react@^14.0.0 \
  @testing-library/jest-dom@^6.0.0 \
  @testing-library/user-event@^14.0.0

npm ls @testing-library/react 2>/dev/null | head -5

Read the full file on GitHub · 218 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. 1mo ago First seen · 218 lines · 87 tokens per session scan C 9047bd8efb40

Subscribe to this mod's changes

react18-dep-surgeon is an agent published in the GitHub repository github/awesome-copilot (40,361 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,744 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other agents, from other repositories

tester

Tester role definition for /implement-universal. Loaded by the orchestrator at the start of the Tester phase, on logic tickets only. Trusts the SWE phase's happy-path e2e excerpt (does NOT re-run the Make target), runs at most 1 adversarial break path, walks every Acceptance Criterion with concrete evidence, and emits…

Arindam200/awesome-ai-apps · 99 tokens

executor

Executor for one part of a Vibeflow feature in the execution loop. Use when the orchestrator dispatches an executor or fix round: reads the briefing, implements inside its perimeter with red before green, keeps the progress file with its final marker, and never commits or calls another agent.

pe-menezes/vibeflow · 60 tokens

ts-tester

Write concise, resilient, modern Unit, Component, and Hook tests using Vitest and React Testing Library for Next.js project. Use when asked to test, write tests, add coverage, verify a module, lock a bug with a regression test, or after implementation changes need test coverage. Also use when the user mentions Vitest…

sergeyklay/.agents · 127 tokens

test-engineer

Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.

ashrafmusa/agenticana · 49 tokens

ndv-tester

Test generation specialist. Use when writing tests, improving coverage, or ensuring correctness. Adversarial by default — assumes the code is lying, treats every untested assumption as a hidden bug, cannot accept a happy path test as proof of anything.

emb715/neurodiveragents · 54 tokens

react-expert

Specialized in React.js, Next.js, and modern frontend ecosystems. Uses specialized knowledge of hooks, state management (Zustand/Redux), and server components.

ashrafmusa/agenticana · 37 tokens