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 skills add d-padmanabhan/agent-engineering-handbook --skill frontend-engineeringgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/frontend-engineering)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/frontend-engineering"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/frontend-engineering.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 | $0.00105 | $0.02625 |
| Opus 5 | $0.00053 | $0.01313 |
| Sonnet 5 | $0.00021 | $0.00525 |
| Haiku 4.5 | $0.00011 | $0.00263 |
Grade A, and why
frontend-engineering 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Engineering Playbook
Framework-agnostic. React, Vue, Svelte, Solid, Astro, Next, Nuxt, Gatsby, Hugo, SvelteKit, Remix - the architecture decisions and CI discipline are the same; the framework is the implementation.
Companion rule: 260-frontend.mdc. The rule is what auto-loads when an agent edits .tsx / .vue / vite.config.* / etc.; this skill is the depth.
When to invoke
- Designing a new frontend project (greenfield)
- Auditing an existing frontend project (perf, a11y, security)
- Choosing between SPA / SSG / SSR / ISR / hybrid rendering
- Setting up Core Web Vitals tracking (lab + RUM)
- Picking state management (and unbreaking a Redux/Zustand-stuffed-with-server-data mess)
- Hitting an INP / LCP / CLS regression
- Wiring CI gates: bundle budget, axe-core, Lighthouse
Do not use for:
- Framework-specific syntax help (defer to framework docs)
- CSS architecture (BEM vs Tailwind vs CSS-in-JS - taste + team conventions)
- Design system decisions (out of scope; that is a design org problem)
Five Golden Rules
- Rendering choice is upstream of everything else. SSG vs SSR vs SPA vs ISR shapes hosting, perf budget, SEO, hydration cost. Decide first; document in ADR.
- The bundle is a budget, not a metric. Set the budget; enforce in CI; raise it explicitly with justification - never silently.
- Three buckets for state, no overlap. Local UI / server / global client. Stuffing server data into Redux is the most common frontend refactor.
- Real-user metrics beat lab metrics. Lighthouse in CI is a floor; RUM (
web-vitals+ analytics) is the truth. - Accessibility is a CI gate, not a sprint. axe-core in CI on every PR; manual SR pass before release; no a11y debt accrual.
Workflow 1 - Design a new frontend project
Steps
- Pick the rendering model. Use the matrix in
references/rendering-choice-matrix.md. Document in an ADR. - Pick the framework. Constraints first: team familiarity > marketing claims. React, Vue, and Svelte are all production-grade in 2026; the framework is rarely the bottleneck.
- Pick the meta-framework if SSR/SSG/hybrid. Next.js / Nuxt / SvelteKit / Astro / Remix - match to the rendering model and team familiarity.
- Set bundle budgets per route type (NN2 in the rule). Wire
bundlewatch/size-limit/@next/bundle-analyzer+ CI gate from day one. - Set state-management strategy. Server-state library (TanStack Query / SWR / Pinia query) chosen on day one. Global client store (Zustand / Pinia / Redux Toolkit) added only when actual cross-route state appears - not preemptively.
- Set Core Web Vitals SLOs. Targets in the rule. Pick a RUM vendor (Cloudflare Web Analytics free; Vercel Analytics if on Vercel; Datadog / Sentry / SpeedCurve if you have budget).
- Wire CI gates in this order: TypeScript strict, ESLint (including
jsx-a11yorvuejs-accessibility), test suite, axe-core E2E pass, Lighthouse CI with perf + a11y thresholds, bundle budget, dependency scan. - Pick the analytics + RUM split. RUM (perf metrics) vs product analytics (user behavior) - usually different tools, and that is fine.
- Pick the error tracker. Sentry / Datadog / Rollbar / self-hosted - source-map upload from CI, release tagging from the deploy commit SHA.
- Document in
README.md+ ADR: rendering model, framework + version, state libraries, perf budgets, RUM / error vendors, CI gates.
What ships with it
1 file 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.
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.
- 3d ago First seen · 205 lines · 105 tokens per session scan A 3d94a25c96aa
frontend-engineering is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 7d ago), licensed MIT. It adds 105 tokens to every session and 2,625 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.
tailwindcss
Tailwind CSS v4 conventions — semantic design tokens for theme-safe styling, mobile-first responsive layouts, and v4-first utilities. Use when styling components or writing className utilities with Tailwind. Don't use for plain CSS, CSS-in-JS (styled-components, emotion), or other utility frameworks.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.