react-doctor

react-doctor is a skill for Claude Code, Codex from New1Direction/korgex. It costs 23 tokens per session (375 once invoked), scanned A, original, MIT.

A deterministic scanner for React code, which is JavaScript code used to build user interfaces. It checks components, hooks, state, effects, performance, architecture, security, and accessibility.

In plain words
What is it for?
Use it after changing React or JSX to find issues such as stale closures, incorrect effect dependencies, avoidable re-renders, unstable props, and accessibility problems, then rerun it after fixes.
Why use it?
It catches common React mistakes that a quick code review or ordinary testing may miss.

Skill for Claude CodeCodex

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 skills/new1direction/korgex/react-doctor
Any agent
npx skills add New1Direction/korgex --skill react-doctor
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

Made for: Claude Code, Codex.

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 react-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/new1direction/korgex/react-doctor.svg)](https://agentmods.dev/skills/new1direction/korgex/react-doctor)
Your own site
<a href="https://agentmods.dev/skills/new1direction/korgex/react-doctor"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/react-doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 375 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 $0.00023 $0.00375
Opus 5 $0.00012 $0.00187
Sonnet 5 $0.00005 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured 4d ago against content hash a469eea4efb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-doctor 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 4d 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.

src/skills_builtin/react-doctor/SKILL.md · 30 lines

What it actually says

When you've written or changed React/JSX (components, hooks, state, effects), run react-doctor — a deterministic linter that catches the mistakes agents commonly make in React — before calling the work done.

  1. Run it (no install needed — it's an npx CLI; requires Node): npx react-doctor@latest On a large repo, scope to the files you touched.
  2. Read the report. It flags issues across: state & effects (stale closures, missing/incorrect effect deps, unnecessary effects), performance (avoidable re-renders, missing memoization, unstable props/children), architecture, security, and accessibility.
  3. Fix what it flags, judging each in context. react-doctor is deterministic (rule-based), so treat findings as real — but verify each fix preserves intent. Address the cause; don't blindly silence a rule.
  4. Re-run to confirm the issues you touched are gone and you didn't add new ones.
  5. If the project has a doctor.config.{ts,js,json}, respect it — it tunes which rules run.

This is the "your agent writes bad React → this catches it" check: cheap, fast, and it catches the bug classes that slip past a quick read. (react-doctor also ships an install command that drops editor skills/rules, and an experimental LSP server — but for an agent loop, running the CLI on your diff is the direct path.)

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. 4d ago First seen · 30 lines · 23 tokens per session scan A a469eea4efb3

Subscribe to this mod's changes

react-doctor is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 375 once invoked, about $0.0001 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.