Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frognpx agentmods add skills/nguyenthienthanh/aura-frog/framework-expertWrote 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/nguyenthienthanh/aura-frog/framework-expert)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/framework-expert"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/framework-expert/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.
<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/framework-expert"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/framework-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00660 |
| Opus 5.5 | $0.00019 | $0.00264 |
| Sonnet 5.5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
framework-expert 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 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.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Framework Expert (Bundle)
Lazy-loads detected framework patterns. Per-framework depth (gotchas, decision
criteria, code examples) lives in refs/<framework>.md — this bundle no longer
delegates to separate <name>-expert skills; Read the matching ref file on
demand once you detect the stack. Use Context7 for full library docs.
Detection
bundles[4]{bundle,frameworks,detect_by}:
web-frontend,"react vue angular nextjs","package.json deps"
web-backend,"nodejs python laravel go","package.json/requirements.txt/composer.json/go.mod"
mobile,"react-native flutter","app.json (expo) or pubspec.yaml"
typescript,typescript,"tsconfig.json or .ts files"
Svelte and Godot used to be listed here and had no reference of their own, so detecting either sent the model looking for depth that does not exist — reach for Context7 for those instead.
Framework References (Read on demand)
Once a framework is detected, Read its ref file for the gotchas and decision tables:
refs[11]{framework,ref}:
React,refs/react.md
Vue,refs/vue.md
Angular,refs/angular.md
Next.js,refs/nextjs.md
Node.js,refs/nodejs.md
Python,refs/python.md
Laravel,refs/laravel.md
Go,refs/go.md
Flutter,refs/flutter.md
React Native,refs/react-native.md
TypeScript,refs/typescript.md
Core Patterns (All Frameworks)
core[8]{pattern,rule}:
File organization,Group by feature not type
Naming,PascalCase components camelCase functions
Error handling,Graceful degradation + user feedback
State,Minimize global state
API design,RESTful or GraphQL conventions
Testing,Unit + integration + e2e
Performance,Lazy loading + code splitting
Security,Input validation + sanitization
What ships with it
11 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.
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.
- 1mo ago First seen · 82 lines · 48 tokens per session scan A ca74441c672d
framework-expert is a skill published in the GitHub repository nguyenthienthanh/aura-frog (25 stars, last pushed 19d ago), licensed MIT. It adds 48 tokens to every session and 660 once invoked, about $0.0002 per session on Opus 5.5. 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
laravel-inertia-react
Laravel + Inertia.js + React integration patterns. Use when building Inertia page components, handling forms with useForm, managing shared data, or implementing persistent layouts. Triggers on tasks involving Inertia.js, page props, form handling, or Laravel React integration.
inertia-rails-setup
One-time project initializer for Inertia Rails skills. Detects stack and frontend framework (React/Vue/Svelte) from Gemfile and package.json, offers to install recommended deps (alba-inertia, js-routes, pagy, shadcn), and generates a CLAUDE.md section that configures which skill patterns apply. Use when first…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
nifra-web
Use when building the full-stack side of a Nifra app - file routes, layouts, loaders and actions, forms, server functions, streaming SSR, islands, SSG and ISR, the query cache, and the React, Vue, Solid, Svelte, or Preact render adapters. Covers the client/server boundary rules and the hydration errors that boundary…
graphql-client
Build Apollo Client or urql queries and mutations, manage cache behavior, and handle authentication and errors.
next-cache-components
Next.js 16 Cache Components guidance. Use when refactoring React Server Components for performance, debugging Partial Prerendering (PPR) issues, or applying the use cache directive, cacheLife, cacheTag, updateTag, and revalidateTag. Also use when deciding whether data should be static, cached, or dynamic, or when…