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/agenticpawan/fullstack-pilot/angular-dynamic-formsnpx skills add AgenticPawan/FullStack-Pilot --skill angular-dynamic-formsgit clone --depth 1 https://github.com/AgenticPawan/FullStack-PilotWhat 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 | $0.00091 | $0.02115 |
| Opus 5 | $0.00046 | $0.01058 |
| Sonnet 5 | $0.00018 | $0.00423 |
| Haiku 4.5 | $0.00009 | $0.00212 |
Grade A, and why
angular-dynamic-forms 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 yesterday.
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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standard IDs
| ID | Severity | What it checks |
|---|---|---|
| ADF-001 | P1 | Reactive form fields hand-coded per component instead of driven by a shared field-descriptor |
| ADF-002 | P1 | Validation rules duplicated between the JSON descriptor and ad-hoc Validators.* calls |
| ADF-003 | P2 | No generic DynamicFormField/renderer component — each feature hand-rolls its own template switch |
| ADF-004 | P2 | Field enabled/disabled toggled directly on the FormControl instead of driven from the descriptor |
| ADF-005 | P2 | Tooltip/label text hardcoded in the template instead of resolved from the descriptor's localization key |
This skill covers the descriptor-driven layer specifically. For the underlying shared
form-factory/ControlValueAccessor/validator-library patterns each descriptor field ultimately
uses, see angular-shared-libraries (ASL-001/ASL-002) — this skill doesn't re-explain those.
The field-descriptor shape
export interface FieldValidationRules {
required?: boolean;
pattern?: string; // regex source, e.g. '^[0-9]{5}$'
minLength?: number;
maxLength?: number;
min?: number;
max?: number;
}
export interface FormFieldDescriptor {
id: string; // stable field key, used as the FormControl name
name: string; // display label (or a localization key — see ADF-005)
type: 'text' | 'number' | 'select' | 'checkbox' | 'date';
validations?: FieldValidationRules;
enabled: boolean;
localizationKey?: string; // resolves name/tooltip/options through the i18n pipe
tooltip?: string;
}
A form is a FormFieldDescriptor[] (typically fetched from an API or defined as a constant
per feature), translated into a FormGroup and rendered generically — see Checks A–C.
Check A — Form fields hand-coded instead of descriptor-driven (ADF-001)
Detection
- Look for a feature component that constructs a
FormGroupwith an inline field list (name, validators, template markup) that could instead be data — especially where the same shape of form (varying only which fields appear, their labels, or validation rules) repeats across features or changes based on tenant/user-role configuration. - Flag when adding/removing/reordering a field requires a code change and redeploy instead of updating the descriptor data.
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.
- yesterday First seen · 240 lines · 91 tokens per session scan A 2eeb81d1e165
angular-dynamic-forms is a skill published in the GitHub repository AgenticPawan/FullStack-Pilot (2 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 2,115 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
translate-a-sample
Translate the Azure SDK sample from python to C# and generate markdownn file for the sample. Parameters: C# SDK repository root; python SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; The name of sample file in Python SDK repository.
azure-kusto-irql
Compose IRQL (Incident Response Query Language) queries for Kusto cybersecurity investigations. Translates natural language hunting questions into composable IRQL pipelines using Get, Extract, and Enrich functions. WHEN: IRQL query, security hunt, threat hunting KQL, incident response query, compose hunting pipeline…
i18n-manage
Add, rename, or remove i18n translation keys in fundamental-ngx (updates FdLanguage interface, .properties files, and generated types).
lingui-best-practices
Implement internationalization with Lingui in React and JavaScript applications. Use when adding i18n, translating UI, working with Trans/useLingui/Plural, extracting messages, compiling catalogs, or when the user mentions Lingui, internationalization, i18n, translations, locales, message extraction, ICU…
enhanced-message-context
Provide additional context for messages based on the codebase and the context of the message to improve the quality of the translations.
devexpress-office-file-api-ai-powered-extensions
Build .NET applications with the DevExpress AI-Powered Extensions for Office File API to add NLP-powered document processing capabilities — proofreading, translation, and text transformation for Word documents, PDF files, and PowerPoint presentations. Use when integrating AI language models (Azure OpenAI, OpenAI…