fundamental-ngx: Skill for Claude Code

.claude/skills/review-pr/SKILL.md

review-pr is a skill for Claude Code from SAP/fundamental-ngx. It costs 17 tokens per session (1,304 once invoked), scanned A, original, Apache-2.0.

A pull-request review command for Angular 22 and newer projects. A pull request is a proposed code change waiting for review.

In plain words
What is it for?
Use it to review a numbered GitHub pull request and group findings as blocking issues, suggestions, or optional cleanups.
Why use it?
It checks the changed code against project rules and current Angular practices, so reviewers do not have to inspect every detail manually.

Skill for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; positional $N argument.

This is SAP/fundamental-ngx's own configuration. It tells Claude Code how to work on fundamental-ngx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fundamental-ngx configures →

About the project

Fundamental Library for Angular is an SAP-maintained Angular component library implementing SAP's design system and wrapping UI5 Web Components. Angular developers use its typed UI components and higher-level composites to build SAP-style web interfaces. Catalogue entries provide skills, agents, instructions, and a rule for working with the library.

SAP/fundamental-ngx · 294 stars · on GitHub · sap.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to SAP/fundamental-ngx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SAP/fundamental-ngx/main/.claude/skills/review-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SAP/fundamental-ngx

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 review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/sap/fundamental-ngx/review-pr/github.svg)](https://agentmods.dev/skills/sap/fundamental-ngx/review-pr)
Your own site
<a href="https://agentmods.dev/skills/sap/fundamental-ngx/review-pr"><img src="https://agentmods.dev/badge/skills/sap/fundamental-ngx/review-pr/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 review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/sap/fundamental-ngx/review-pr"><img src="https://agentmods.dev/badge/skills/sap/fundamental-ngx/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00017 $0.01304
Opus 5 $0.00009 $0.00652
Sonnet 5 $0.00003 $0.00261
Haiku 4.5 $0.00002 $0.00130

Measured 11d ago against content hash d74633ee0931, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-pr 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 11d 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.

.claude/skills/review-pr/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review: #$0

If $0 is empty or not a number, ask the user for a PR number before proceeding.

Context

Fetch the PR details:

  • Diff: !gh pr diff $0
  • PR info: !gh pr view $0
  • Changed files: !gh pr diff $0 --name-only

Review Checklist

For each changed file, check the applicable sections below. Report findings grouped by severity: Blocking (must fix), Suggestion (should fix), Nit (optional).

1. Angular 22+ Patterns

  • New code uses input() / output() / model() / linkedSignal(). Existing @Input() / @Output() decorators being modified should prefer migration to signal functions, but it's not blocking.
  • host: {} in decorator — no @HostBinding() / @HostListener()
  • @if / @for / @switch — no *ngIf / *ngFor / *ngSwitch
  • No standalone: true in @Component (default since Angular 19)
  • No allowSignalWrites option in effect() (the option no longer exists)
  • DestroyRef + takeUntilDestroyed() — no custom DestroyedService
  • computed() + host: { '[class]': } — no CssClassBuilder / @applyCssClass
  • Member ordering: decorated props → signal inputs/outputs → public → protected → private → constructor → methods

2. State Management

  • signal() only used when a reactive consumer exists (template, computed, effect, host binding)
  • Plain properties for internal bookkeeping, one-time flags, cached values
  • No redundant markForCheck() after signal updates
  • BehaviorSubjectsignal() where there are no async consumers
  • effect() for signal reactions; RxJS only for async operations (HTTP, WebSocket, timers)
  • No effect() used for state derivation — use computed() or linkedSignal instead
  • linkedSignal used where mutable derived state is needed (not effect() + signal.set())
  • No object/array mutation in place then signal.set() with same reference — always new references
  • No conditional signal reads creating invisible dependency gaps in effect() / computed()

Read the full file on GitHub · 115 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. 11d ago First seen · 115 lines · 17 tokens per session scan A d74633ee0931

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository SAP/fundamental-ngx (294 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 1,304 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 2026-08-30.

Related

Other skills, from other repositories

angular-best-practices

Official Angular v22 coding best practices — signals, standalone, native control flow, zoneless, host bindings, Signal Forms, inject(), and accessibility (WCAG AA / AXE). Use whenever writing, generating, or reviewing Angular/TypeScript code in this repo.

anousss007/ng-blatui · 60 tokens

igniteui-angular-linting

Quick-reference for linting the core Ignite UI for Angular library. Covers the combined lint command (lint:lib), ESLint for TypeScript and templates, and Stylelint for Sass/SCSS styles. Use when an agent needs to run the main linters, fix lint errors, or understand the primary lint configuration. Do NOT use for…

IgniteUI/igniteui-angular · 99 tokens

logic-component-shape

Decision tree for single component versus container/presenter, which componentStructure to generate, and which componentType to declare. Invoked by logic-placement and logic-review, not directly.

AmadeusITGroup/otter · 43 tokens

logic-placement

Decide where new logic belongs — component shape, logic layer, and store variant — when designing a component, service, or store in an Angular/Otter workspace. Use logic-review to assess existing code.

AmadeusITGroup/otter · 46 tokens

logic-review

Review existing components, services, or stores for misplaced logic — presenter leaks, componentType mismatches, wrong store variants. Use logic-placement when designing something new.

AmadeusITGroup/otter · 37 tokens

logic-state-layer

Decision tree for whether logic belongs in the component class, a service, or an NgRx store, including service scope and where API calls go. Invoked by logic-placement and logic-review, not directly.

AmadeusITGroup/otter · 48 tokens