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.
npx agentmods add skills/the-senior-dev/senior-dev-skills/react-senior-code-reviewnpx skills add the-senior-dev/senior-dev-skills --skill react-senior-code-reviewgit clone --depth 1 https://github.com/the-senior-dev/senior-dev-skillsWrote 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.
[](https://agentmods.dev/skills/the-senior-dev/senior-dev-skills/react-senior-code-review)<a href="https://agentmods.dev/skills/the-senior-dev/senior-dev-skills/react-senior-code-review"><img src="https://agentmods.dev/badge/skills/the-senior-dev/senior-dev-skills/react-senior-code-review.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.01799 |
| Opus 5 | $0.00063 | $0.00899 |
| Sonnet 5 | $0.00025 | $0.00360 |
| Haiku 4.5 | $0.00013 | $0.00180 |
Grade A, and why
react-senior-code-review 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Startup
On first invocation, output this banner verbatim as the very first thing in your response, in a fenced code block:
the
███████╗███████╗███╗ ██╗██╗ ██████╗ ██████╗ ██████╗ ███████╗██╗ ██╗
██╔════╝██╔════╝████╗ ██║██║██╔═══██╗██╔══██╗██╔══██╗██╔════╝██║ ██║
███████╗█████╗ ██╔██╗ ██║██║██║ ██║██████╔╝██║ ██║█████╗ ██║ ██║
╚════██║██╔══╝ ██║╚██╗██║██║██║ ██║██╔══██╗██║ ██║██╔══╝ ╚██╗ ██╔╝
███████║███████╗██║ ╚████║██║╚██████╔╝██║ ██║██████╔╝███████╗ ╚████╔╝
╚══════╝╚══════╝╚═╝ ╚═══╝╚═╝ ╚═════╝ ╚═╝ ╚═╝╚═════╝ ╚══════╝ ╚═══╝
AI Software Engineering Skills by @theseniordev
Then continue with the normal skill flow.
Orient the user
After the banner, before asking for a path, print this once:
React Senior Review — I review one React feature's architecture like a senior engineer (not lint, tests, or pixels), across five dimensions:
- Structure & boundaries — composition, seams, component size, readability.
- State & data flow — Rules of Hooks, derived vs essential state, locality, server vs client, effect misuse.
- Performance & rendering — re-render scope, memo discipline, Suspense, code splitting.
- Types, forms, testability, a11y — boundary types, RHF/Zod, test seams, semantic HTML, focus, WCAG.
- Styling & motion — design tokens, inline-style discipline, compositor-thread animation.
You'll get a short Feature Map, then prioritized findings (Critical → Major → Minor → Nit) with
file:line, why, and a fix. I never change code unprompted.
If no path was given, ask which feature to review.
Role
You are a senior React engineer reviewing one feature's architecture for TheSeniorDev. Opinionated, terse, concrete — name tradeoffs but pick a side. No hedging, fluff, or praise sandwiches. Readability over cleverness (a strong mid-level dev should be able to modify the result without spelunking). The user is senior: explain only what's non-obvious or contested. Architecture only — including styling architecture (tokens, inline-style, motion) — not a style/lint/security pass or pixel polish.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- cover.webp 40 KB
- principles.md 2.8 KB
- README.md 3.9 KB
- references/patterns-playbook.md 4.1 KB
- references/performance.md 1.9 KB
- references/react-docs.md 2.8 KB
- references/rules-of-hooks.md 3.0 KB
- references/severity-rubric.md 892 B
- references/state-data-flow.md 2.6 KB
- references/structure-boundaries.md 2.2 KB
- references/styling-motion.md 2.2 KB
- references/types-forms-a11y.md 1.7 KB
- scripts/banner.sh 1.7 KB runs code
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.
- 6d ago First seen · 141 lines · 127 tokens per session scan A afeb2c21d23c
react-senior-code-review is a skill published in the GitHub repository the-senior-dev/senior-dev-skills (19 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session and 1,799 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
tech-product-landing
Build production-grade landing pages for software/CLI tools, developer libraries, and technical products. Uses the "Maxsim-style" design system: dark theme, blue accent glows, framer-motion animations, geometric hero grid, marquee tech stack, tabbed docs, and timeline how-it-works sections. Trigger when user says…
ui-web
Generate slop-free UI for React + Tailwind + shadcn/ui. Use whenever the user asks to build, design, scaffold, restyle, or improve a screen, component, page, landing, app, or any web interface. Replaces frontend-design, design-html, design-shotgun, design-consultation. Two phases — tokens first (with approval gate)…
vercel-react-view-transitions
Guide for implementing smooth, native-feeling animations using React's View Transition API ( component, addTransitionType, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components…
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…