Borrowing it
Nothing to install: this file belongs to AtulFalle/ng-elemental. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AtulFalle/ng-elemental/master/.cursor/skills/ng-elemental-review/SKILL.mdgit clone --depth 1 https://github.com/AtulFalle/ng-elementalWrote 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/atulfalle/ng-elemental/ng-elemental-review)<a href="https://agentmods.dev/skills/atulfalle/ng-elemental/ng-elemental-review"><img src="https://agentmods.dev/badge/skills/atulfalle/ng-elemental/ng-elemental-review/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/atulfalle/ng-elemental/ng-elemental-review"><img src="https://agentmods.dev/badge/skills/atulfalle/ng-elemental/ng-elemental-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00128 | $0.01177 |
| Opus 5.5 | $0.00051 | $0.00471 |
| Sonnet 5.5 | $0.00026 | $0.00235 |
| Haiku 4.5 | $0.00013 | $0.00118 |
Grade A, and why
ng-elemental-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 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NgElemental component review
One owner per piece of state. Children emit events. They do not copy, invert, or reduce parent state.
Read this before adding inputs, effects, or a second instance of the same El* widget. Also follow ng-elemental-component.
Applies to every design-system piece: triggers, overlays, lists, panes, fields, compound parent/child controls, and anything added later.
State table (required)
Before coding or finishing a review, fill this for the widget in front of you. Any row with two owners is a defect. Omit rows that do not exist.
| State | Owner (exactly one) | How others see it |
|---|---|---|
| Selected / checked / value | Parent model() |
Inputs down |
| Visible window (open panel, active tab, step, page, section, stage) | Parent, or local UI-only on the child | Input down, Change event up |
| Hover / highlight / preview | Parent if more than one pane or item paints it | Input down, event up |
| Uncommitted drafts (typed fields, filter text, in-progress range) | The draft UI | Commit event up |
Local UI-only state (which nested face is showing, which row is focused) may live on the child. Do not sync it back with an effect.
Review output
- State table (filled)
- Defects: Critical / Important / Minor
- Stop if Critical or Important state-ownership defects remain
Defects to reject
Flag-sliced god widget. showHeader + showBody + showFields (or any showX set) means the component is several widgets. Split: leaf pane vs fields vs overlay shell vs list vs item.
Stub instance. Mounting a widget with most of the UI hidden only to reuse a slice of logic. Duplicate the small template or extract a tiny sibling. Do not run a full grid, list, or effect brain just to host inputs.
Mirrored controlled state. Parent window plus child copy plus effect + untracked + *Change (including inverted math on a sibling). Parent owns the window; child receives it and emits Change.
Reducer in every child. Start/end/swap, next/prev, or toggle-set implemented in each instance. Children emit what happened (itemSelected, stepChange); the parent updates value once.
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 · 84 lines · 128 tokens per session scan A 1e4115de8584
ng-elemental-review is a skill published in the GitHub repository AtulFalle/ng-elemental (2 stars, last pushed 3d ago), licensed MIT. It adds 128 tokens to every session and 1,177 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
red-blue-review
An optional adversarial review process for requirement analyses. One agent produces the analysis, while an independent reviewer checks its report, database definitions, alignment records, and requirements for missed issues.
wcode
Use the wcode plugin and its MCP tools for repository coding, review, debugging, refactoring, architecture, Graph/Design inspection, safe edits, command execution, and verification. Trigger whenever wcode is installed or named, even when its tools are lazily registered or omitted from the host's initial tool list.
pr-analysis
Analyse a GitHub pull request by fetching its metadata, diff, linked issues and CI status.
pr-review
Review a GitHub pull request by posting inline code comments and submitting a review decision.
atelier
Two-agent post-generation quality gate for vibe-coded applications. Deterministic, gradeable ruleset enforcing UI/UX design-system craft and backend architectural soundness.
pr-review
Review one or all open pull requests in saadeghi/daisyui with read-only GitHub data and isolated base-versus-PR checks. Use when Codex must verify a PR, find concrete regressions, decide whether it is safe to merge, and write a concise report under tmp/pr/.