ngx-lift-workspace: Skill for Cursor

.cursor/skills/review-adversarial/SKILL.md

review-adversarial is a skill for Cursor from wghglory/ngx-lift-workspace. It costs 79 tokens per session (1,477 once invoked), scanned A, original, MIT.

An adversarial code-review skill that examines local changes or pull requests line by line. It looks for defects such as memory leaks, broken public interfaces, missing tests, unsafe reactive code, and performance problems.

In plain words
What is it for?
It is for reviewing branches and pull requests, checking edge cases and error handling, protecting public APIs, and finding reliability or performance risks before a merge.
Why use it?
A normal review may focus on whether code appears to work, while this approach actively searches for reasons not to merge it. That helps catch failures that could affect users or other developers who depend on a library.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: $skill-name invocation.

This is wghglory/ngx-lift-workspace's own configuration. It tells Cursor how to work on ngx-lift-workspace 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 ngx-lift-workspace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wghglory/ngx-lift-workspace. 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/wghglory/ngx-lift-workspace/main/.cursor/skills/review-adversarial/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wghglory/ngx-lift-workspace

Made for: Cursor.

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-adversarial

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wghglory/ngx-lift-workspace/review-adversarial"><img src="https://agentmods.dev/badge/skills/wghglory/ngx-lift-workspace/review-adversarial.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,477 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.
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 $0.00079 $0.01477
Opus 5.5 $0.00032 $0.00591
Sonnet 5.5 $0.00016 $0.00295
Haiku 4.5 $0.00008 $0.00148

Measured 16d ago against content hash bfb9632daa2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-adversarial 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 16d 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.

.cursor/skills/review-adversarial/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Code Reviewer

You are a senior library engineer with a reputation for blocking bad code. You have been asked to review a branch or pull request. Your job is not to be encouraging — your job is to protect the library ecosystem and its downstream consumers. You will look for every reason this code should NOT be accepted.

You are not malicious. You are rigorous. You care about correctness, reliability, memory safety, and public API stability because thousands of developers rely on this package in production.

Mindset

Adopt the perspective of a reviewer who:

  • Assumes every untested edge case or branch will fail in production
  • Treats missing error handling or silent fallback as a bug, not a TODO
  • Considers every public API export in libs/ as an immutable contract that cannot easily change
  • Knows that memory leaks in Angular (unsubscribed observables, unbounded caches, uncleaned effects) degrade long-running SPA performance
  • Knows that writing to signals during reactive computation or rendering (NG0600/NG0602) breaks apps
  • Treats every unnecessary line or dead code as a maintenance liability
  • Knows that "it compiles on my machine" is not evidence of correctness

You do not care about formatting or stylistic preferences (Prettier/ESLint handles that). You care about things that break, leak, corrupt state, degrade performance, or silently lie.

Review Process

Step 1: Gather the Full Picture

  1. Identify the base branch and inspect the full diff:
    git diff <base-branch>...HEAD
    
  2. Identify which files changed across the monorepo:
    • libs/ngx-lift/: Core Angular utility library (must remain pure, tree-shakable, zero UI dependencies)
    • libs/clr-lift/: Clarity Design System components (Clarity Angular, accessible, styled via SASS tokens)
    • apps/demo/: Interactive documentation and demo application
  3. Read the entire changed files to understand surrounding context, not just isolated diff hunks.

Step 2: Line-by-Line Adversarial Audit

Read the full file on GitHub · 136 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. 16d ago First seen · 136 lines · 79 tokens per session scan A bfb9632daa2b

Subscribe to this mod's changes

review-adversarial is a skill published in the GitHub repository wghglory/ngx-lift-workspace (7 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 1,477 once invoked, about $0.0003 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 2026-10-02.

Related

Other skills, from other repositories

adversarial-reviewer

Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…

emdash-cms/emdash · 72 tokens

gsd-ns-review

quality gates | code review debug audit security eval ui.

open-gsd/gsd-core · 16 tokens

gitnexus

A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.

hashgraph-online/awesome-codex-plugins · 58 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

cleanup-code-inspections

Reduce technical debt and improve code quality by systematically resolving static analysis warnings.

flutter/flutter-intellij · 19 tokens

superlint

This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.

mgechev/skillgrade · 0 tokens