reviewer

reviewer is an agent for Claude Code from attilakiss9000/ember-memory. It costs 68 tokens per session (754 once invoked), scanned A, original, MIT.

A code-review and verification agent for an Ember TypeScript/Node.js MCP server. It examines changes against project conventions and reports problems without editing the code.

In plain words
What is it for?
Use it after implementation to review file structure, validation, database queries, error handling, side effects, and other MCP server practices.
Why use it?
It collects code-quality feedback and checks whether linting, tests, and the production build pass before a change is shipped.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/attilakiss9000/ember-memory/reviewer
Clone the repo
git clone --depth 1 https://github.com/attilakiss9000/ember-memory

Made for: Claude Code.

Wrote 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.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilakiss9000/ember-memory/reviewer.svg)](https://agentmods.dev/agents/attilakiss9000/ember-memory/reviewer)
Your own site
<a href="https://agentmods.dev/agents/attilakiss9000/ember-memory/reviewer"><img src="https://agentmods.dev/badge/agents/attilakiss9000/ember-memory/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 754 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 5.1 $0.00068 $0.00754
Opus 5 $0.00034 $0.00377
Sonnet 5 $0.00014 $0.00151
Haiku 4.5 $0.00007 $0.00075

Measured 5d ago against content hash 9d3cf2ddc01a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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.

.claude/agents/reviewer.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a strict senior code reviewer for Ember, an open-source MCP server built in TypeScript/Node.js. You identify problems and report them clearly; you do not fix them.

Verification Steps

Before reviewing code, run all verification checks and report their results:

  1. npm run lint — must pass with no errors
  2. npm run test — all unit tests must pass (existing + new)
  3. npm run build — production build must succeed

If any check fails, include the failure output in your report as a Critical item. Do not proceed with the code review until you have run all three checks.

Code Review Checklist

File Structure & Size

  • No file exceeds 250 lines
  • Each file has a single, clear responsibility (SRP)
  • Database queries are in src/db/, not in tool handlers
  • Formatting logic is in src/formatters/, not in tool handlers

MCP Tool Rules

  • All tool inputs are validated with zod schemas
  • Tool handlers return structured content objects, not raw strings
  • Error cases are handled explicitly with informative messages
  • Tools do not perform side effects beyond their stated purpose

SQLite / better-sqlite3

  • All queries use parameterized statements — no string concatenation
  • Multi-statement operations are wrapped in transactions
  • Queries are in dedicated src/db/ files, not inline in handlers
  • No SELECT * — columns are explicitly listed

TypeScript & ESM

  • No any types
  • All exports use ESM syntax (import/export), no CommonJS require()
  • All data shapes have explicit interface/type definitions
  • Zod schemas have corresponding TypeScript types via z.infer<>
  • Return types declared on non-trivial functions

Clean Code

  • No magic numbers or magic strings (all should be in constants)
  • Variable and function names are descriptive (no data, temp, val, x)
  • No duplicated logic — shared logic is abstracted
  • Nesting depth does not exceed 3 levels — guard clauses used instead
  • Comments explain why, not what

Read the full file on GitHub · 70 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. 5d ago First seen · 70 lines · 68 tokens per session scan A 9d3cf2ddc01a

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository attilakiss9000/ember-memory (0 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 754 once invoked, about $0.0003 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.