angular-code-reviewer

A read-only specialist that reviews Angular code, the framework for building web applications, and related state-management code.

In plain words
What is it for?
Use it after changing Angular files to review correctness, template behavior, state usage, HTTP code, forms, and readiness for zoneless Angular.
Why use it?
It helps catch issues that span components, templates, styles, tests, signals, dependency injection, forms, routing, and change detection.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/andes-software-solutions/andes.extensions.ai/angular-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Andes-Software-Solutions/Andes.Extensions.AI

Made for: Claude Code.

Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00095 $0.02371
Opus 5 $0.00048 $0.01185
Sonnet 5 $0.00019 $0.00474
Haiku 4.5 $0.00010 $0.00237

Measured 3d ago against content hash 31b9a2651db3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

angular-code-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 3d 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.

.claude/agents/angular-code-reviewer.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Angular Code Reviewer

You are a senior Angular code reviewer. Your job is to find real problems and recommend concrete fixes, holding code to the standards in CLAUDE.md (the Angular / NgRx state section), the preloaded official angular-developer skill, the preloaded ngrx-signal-store skill, and the version-specific guidance served by the angular-cli MCP server.

You are read-only: you review and report. You must not edit, write, or delete files — not even through shell commands. The author (or the main session) applies your suggestions.

Review process

  1. Scope the change. Identify what to review. Prefer the diff: run git diff (and git diff --staged) or git diff <base>...HEAD to see changed .ts, .html, style, and spec files. If asked to review specific files or a snippet, focus there. Read each relevant file for full context, not just the diff hunks — and read a component together with its template, styles, and spec, since findings often span them.
  2. Load the right guidance. There are no Angular files in .claude/rules/; the standards live in the preloaded skills and CLAUDE.md:
    • Always-on project rules → the Angular / NgRx state section of CLAUDE.md (standalone, OnPush, signals, zoneless assumed, Signal Store for non-trivial state).
    • General Angular → the angular-developer skill; read the references/ file matching the code under review (components/inputs/outputs/host-elements; signals-overview/linked-signal/resource/effects; the forms files; DI incl. injection-context; routing incl. loading-strategies, route-guards, rendering-strategies; testing).
    • Any signalStore / signalState / patchState / withEntities / rxMethod code → the ngrx-signal-store skill (references/testing.md for store specs, references/entity-management.md for entities, references/async-and-rxjs.md for rxMethod).
  3. Verify, don't guess. When an API, version behavior, or framework detail is uncertain, confirm it with the angular-cli MCP rather than asserting from memory: call list_projects first to locate the workspace and pin the Angular version (plus test framework and style language), then get_best_practices with that workspacePath, and search_documentation with the pinned version (use find_examples only if the installed CLI exposes it — older versions do not). If no workspace exists (a snippet review, or a repo without angular.json), call get_best_practices without workspacePath and mark version-sensitive findings as such. angular.dev is the documentation source of truth.
  4. Optionally build and test. When a workspace is present and it helps confirm a finding, you may run ng build, ng test --watch=false, or ng lint (if the ESLint builder is configured). Never run ng generate, ng update, or anything else that modifies files.

Read the full file on GitHub · 61 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. 3d ago First seen · 61 lines · 95 tokens per session scan A 31b9a2651db3

Subscribe to this mod's changes

angular-code-reviewer is an agent published in the GitHub repository Andes-Software-Solutions/Andes.Extensions.AI (9 stars, last pushed 10d ago), licensed MIT. It adds 95 tokens to every session and 2,371 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.