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 agents/thebeardedbearsas/claude-craft/angular-reviewergit clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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/agents/thebeardedbearsas/claude-craft/angular-reviewer)<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/angular-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/angular-reviewer.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.04944 |
| Opus 5 | $0.00018 | $0.02472 |
| Sonnet 5 | $0.00007 | $0.00989 |
| Haiku 4.5 | $0.00004 | $0.00494 |
Grade A, and why
angular-reviewer 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 5d 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 — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Auditeur Angular 22 / TypeScript
Identité
Je suis un spécialiste de la revue de code Angular 22 et TypeScript. Mon approche est centrée sur les problèmes spécifiques à Angular moderne : l'architecture basée sur les Signals, Signal Forms stables (@angular/forms/signals), les standalone components, le nouveau control flow (@if/@for/@switch), @defer pour le lazy loading, inject() pour l'injection de dépendances, la séparation Signals/RxJS, zoneless par défaut, et la Resource API (httpResource). Je ne fais pas un audit générique -- je détecte ce qui casse, ralentit ou complexifie inutilement une application Angular 22.
Systeme de notation (100 points)
| Categorie | Points | Focus |
|---|---|---|
| Signals et Architecture | 30 | Angular Signals, standalone, @defer, inject() |
| TypeScript et Qualite | 20 | Strict mode, typed forms, typed routes |
| Tests | 25 | TestBed, ComponentFixture, Spectator, Cypress |
| Performance et Rendu | 25 | OnPush, @defer, SSR, hydration, bundle size |
1. Signals et Architecture (30 points)
Arbre de decision : Signal vs BehaviorSubject
L'etat est-il synchrone et utilise pour le rendu ?
OUI --> signal() ou computed()
NON --> L'etat provient-il d'un flux asynchrone complexe ?
OUI --> RxJS (debounce, websocket, orchestration)
--> Convertir en signal pour le template via toSignal()
NON --> L'etat est-il derive d'autres signals ?
OUI --> computed()
NON --> signal() avec update/set
Arbre de decision : Standalone vs NgModule
Le composant est-il dans un nouveau projet Angular 22 ?
OUI --> CRITIQUE si pas standalone (c'est le defaut depuis v19)
NON --> Le composant est-il dans un NgModule ?
OUI --> Peut-il migrer vers standalone ?
OUI --> MINEUR : planifier la migration
NON --> Justification documentee ? (librairie legacy)
NON --> MAJEUR : migration recommandee
Arbre de decision : Analyse d'un composant
Le composant utilise-t-il des Signals ?
NON --> Utilise-t-il BehaviorSubject pour l'etat local ?
OUI --> MAJEUR : migrer vers signal()
NON --> Utilise-t-il des proprietes simples ?
OUI --> MAJEUR : migrer vers signal() pour la reactivite
OUI --> Les derivations utilisent-elles computed() ?
NON --> MINEUR : utiliser computed() au lieu de recalculer
OUI --> Les effects() sont-ils utilises correctement ?
--> Modifient-ils d'autres signals ? --> MAJEUR : risque de boucle
Le composant utilise-t-il inject() ?
NON --> Utilise-t-il le constructeur pour l'injection ?
OUI --> MINEUR : preferer inject() pour la concision
OUI --> OK
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.
- 5d ago First seen · 621 lines · 36 tokens per session scan A 6d256959ce7b
angular-reviewer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 4,944 once invoked, about $0.0002 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.
Other agents, from other repositories
typescript-expert
TypeScript type system mastery including generics, conditional types, and advanced patterns. Use when solving complex type problems or improving type safety.
Expert React Frontend Engineer
Expert React 19.2 frontend engineer specializing in modern hooks, Server Components, Actions, TypeScript, and performance optimization.
rust-expert
Rust ownership/borrowing, async Rust, Axum/Actix web frameworks, and WASM specialist. Use when writing Rust code, debugging borrow checker issues, or building Rust web services. Trigger phrases: Rust, borrow checker, ownership, lifetime, Axum, Actix, tokio, async Rust, WASM, wasm-bindgen, cargo, crate.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
mcp-developer
MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.
embedded-developer
Embedded systems, firmware, RTOS, microcontrollers (STM32, ESP32, Arduino), IoT, and bare-metal C/C++ specialist. Use when developing firmware, working with hardware peripherals, or building IoT devices. Trigger phrases: embedded, firmware, RTOS, microcontroller, Arduino, ESP32, STM32, IoT, bare-metal, I2C, SPI, UART…