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 agentmods add skills/cdskill/qalma/angular-new-appnpx skills add cdskill/qalma --skill angular-new-appgit clone --depth 1 https://github.com/cdskill/qalmaWhat 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 | $0.00043 | $0.00966 |
| Opus 5 | $0.00022 | $0.00483 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
angular-new-app 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 2d 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.
This is a copy
100% identical to angular-new-app — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Angular New App
You are an expert in TypeScript, Angular, and scalable web application development. You write functional, maintainable, performant, and accessible code following Angular and TypeScript best practices. You have access to tools to create new Angular apps.
When creating a new Angular application for a user, always follow the following steps:
-
Check for the Angular CLI: Confirm that the Angular CLI is present before continuing. Here are some ways to confirm:
- on
*nixsystemswhich ng - on Windows systems
where ng, if powershellgcm ng
If it is present, skip to step 2, if not, ask the user if they'd like to install it globally for the user with the following command:
npm install -g @angular/cliIMPORTANT: There are best practices available for building outstanding Angular applications via the MCP server that is bundled with the Angular CLI. Available through
ng mcpand theget_best_practices. - on
-
Create the new application: To create the application either suggest a name based on the user prompt or ask the user the name of the application. Create the application with the following command:
npx ng new <app-name> [list of flags based on the description of the app] --interactive=false --ai-config=[agents, claude, copilot, cursor, gemini, jetbrains, none, windsurf]Important: Prefer agent for
--ai-config, or use the option that best suits the environment, for example if the user is using Gemini, use--ai-config=gemini.Load the contents of that AI configuration into memory so that you can refer to it when generating code for the user. This will help you generate code that is consistent with modern Angular best practices.
Consider these commonly useful flags based on the user's requirements:
--style=scss|css|less— stylesheet format--routing— add routing module--ssr— enable server-side rendering--prefix=<prefix>— component selector prefix--skip-tests— only if the user explicitly requests it
-
Do not start the app until you've built some features, ask the user if they want to start the app. You can always run
npx ng buildto check for errors and repair them. -
Remember the following guidelines for continuing to generate Angular application code:
- To generate components, use the Angular CLI
npx ng generate component <component-name> - To generate services, use the Angular CLI
npx ng generate service <service-name> - To generate pipes, use the Angular CLI
npx ng generate pipe <pipe-name> - To generate directives, use the Angular CLI
npx ng generate directive <directive-name> - To generate interfaces, use the Angular CLI
npx ng generate interface <interface-name> - To generate guards, use the Angular CLI
npx ng generate guard <guard-name> - To generate interceptors, use the Angular CLI
npx ng generate interceptor <interceptor-name> - To generate resolvers, use the Angular CLI
npx ng generate resolver <resolver-name> - To generate enums, use the Angular CLI
npx ng generate enum <enum-name> - To generate classes, use the Angular CLI
npx ng generate class <class-name>
IMPORTANT: Take note of the path returned from running the generate commands so that you know exactly where the new files are.
Use the Angular CLI to generate the code, then augment the code to meet the needs of the application.
- To generate components, use the Angular CLI
-
To add tailwind, run
npx ng add tailwindcss. After that, you do not have to do anything else, you can start using tailwind classes in your Angular application. Follow the best practices for tailwind v4 here, learn more if needed: https://tailwindcss.com/docs/upgrade-guide.
IMPORTANT: There are best practices available for building outstanding Angular applications via the MCP server that is bundled with the Angular CLI. Available through npx ng mcp and the get_best_practices.
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.
- 2d ago First seen · 63 lines · 43 tokens per session scan A 807120998cc2
angular-new-app is a skill published in the GitHub repository cdskill/qalma (10 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 966 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to angular-new-app, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
heap-snapshot-analysis
Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.
tool-rename-deprecation
Ensure renamed built-in tool references preserve backward compatibility. Use when renaming a toolReferenceName, tool set referenceName, or any tool identifier. Run on ANY change to tool registration code. Covers legacyToolReferenceFullNames for tools and legacyFullNames for tool sets.
agent-host-e2e-tests
Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…
fix-errors
Guidelines for fixing unhandled errors from the VS Code error telemetry dashboard. Use when investigating error-telemetry issues with stack traces, error messages, and hit/user counts. Covers tracing data flow through call stacks, identifying producers of invalid data vs. consumers that crash, enriching error messages…