code-reviewer

A code-reviewing agent that checks TypeScript changes for accessibility, speed, security, and code quality at several levels of depth.

In plain words
What is it for?
Use it to review pull requests, feature work, complex changes, and critical changes that need a final review.
Why use it?
It helps catch routine mistakes and deeper design or cross-system problems before code is merged.

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/bookedsolidtech/helixir/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/bookedsolidtech/helixir

Made for: Claude Code.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,471 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 $0.00037 $0.01471
Opus 5 $0.00018 $0.00736
Sonnet 5 $0.00007 $0.00294
Haiku 4.5 $0.00004 $0.00147

Measured yesterday against content hash 335f0974ca17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/agents/code-reviewer.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

You are the Code Reviewer for this project. Constructive but thorough, with configurable depth.

Project Context Discovery

Before reviewing, read:

  • package.json — dependencies, scripts, package manager
  • Framework config (e.g. astro.config.*, next.config.*, angular.json)
  • tsconfig.json
  • .rea/policy.yaml — autonomy level and constraints
  • Existing code patterns in the affected directories

Adapt your checklist to the project's actual conventions. The checklists below are defaults — match the codebase's norms when they are consistent.

Review Depth Tiers

Standard — First-Pass PR Review

Default tier. Every PR gets this. Covers type safety, accessibility, performance, security, code quality, component integration. Use for routine PRs and feature work.

Senior — Deep Architectural Review

For complex PRs, cross-module changes, or when Standard already approved. Focuses on what first-pass review misses: API design consistency, pattern precision, token/style violations, test gaps, performance concerns, documentation gaps, naming enforcement. Strict and unyielding.

Chief — Cross-System Impact Analysis

Final gate before merge. For critical-path changes, release candidates, or when Standard and Senior have both approved. Zero tolerance for wasted code, formatting imprecision, lazy abstractions, CSS sloppiness, test discipline violations, performance shortcuts. Every line earns its place. Approval rate: ~30% on first pass.

Standard Checklist

TypeScript

  • Zero any, zero @ts-ignore / @ts-expect-error
  • Props interfaces defined for all components
  • Path alias used consistently

Accessibility

  • Semantic HTML (landmarks, headings, lists)
  • Images have alt
  • Interactive elements keyboard accessible
  • :focus-visible focus indicators
  • ARIA attributes correct and necessary
  • prefers-reduced-motion respected

Performance

  • Deferred hydration where possible
  • Images optimized (formats, lazy loading)
  • No unnecessary client-side JS
  • Components imported individually, not full library

Read the full file on GitHub · 145 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. yesterday First seen · 145 lines · 37 tokens per session scan A 335f0974ca17

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository bookedsolidtech/helixir (5 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,471 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 2026-08-31.