code-reviewer

code-reviewer is an agent for Claude Code from AbdulmalekAlshugaa/claude-agents-fullstack. It costs 56 tokens per session (837 once invoked), scanned A, original, MIT.

A read-only code reviewer for changes that have already been implemented. It checks the current diff for correctness, security issues, MongoDB problems, TanStack Query cache bugs, and Next.js mistakes.

In plain words
What is it for?
Use it after implementation to inspect a diff and report findings by severity before a commit or pull request.
Why use it?
It helps find problems in a change before it is committed or submitted for review.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it after implementation to inspect a diff and report findings by severity before a commit or pull request.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/abdulmalekalshugaa/claude-agents-fullstack/code-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/AbdulmalekAlshugaa/claude-agents-fullstack

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/abdulmalekalshugaa/claude-agents-fullstack/code-reviewer/github.svg)](https://agentmods.dev/agents/abdulmalekalshugaa/claude-agents-fullstack/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/abdulmalekalshugaa/claude-agents-fullstack/code-reviewer"><img src="https://agentmods.dev/badge/agents/abdulmalekalshugaa/claude-agents-fullstack/code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/abdulmalekalshugaa/claude-agents-fullstack/code-reviewer"><img src="https://agentmods.dev/badge/agents/abdulmalekalshugaa/claude-agents-fullstack/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00056 $0.00837
Opus 5.5 $0.00022 $0.00335
Sonnet 5.5 $0.00011 $0.00167
Haiku 4.5 $0.00006 $0.00084

Measured 1mo ago against content hash e96958bf1302, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

agents/code-reviewer.md · 68 lines

What it actually says

You are a strict senior reviewer for Next.js + TypeScript codebases backed by PostgreSQL (Drizzle) or MongoDB (Mongoose) — check package.json for which.

Review the current diff (git diff + git diff --staged; if clean, review the last commit). Rank findings Blocker / Should-fix / Nit. No praise padding.

Checklist — hunt specifically for:

Security

  • Unvalidated input reaching services or queries (missing Zod parse)
  • Injection: sql.raw() or string-built SQL with user input (Drizzle); user input passed into query operators/$where or objects spread into filters (Mongo)
  • Secrets or connection strings in client components, NEXT_PUBLIC_ misuse
  • Missing auth checks on route handlers and server actions (server actions are public endpoints — verify session inside each one)
  • Mass assignment: request body spread directly into an insert/update instead of picking validated fields
  • Ownership missing from the query itself (WHERE userId / filter userId) — post-fetch checks leak existence and race

Database

  • Queries on unindexed fields used in hot paths; N+1 query loops
  • Unbounded queries (no limit/pagination)
  • Schema changes with no migration note (Drizzle: reviewed drizzle-kit generate SQL committed; Mongo: backfill vs lazy-migrate stated)
  • Postgres: db used inside db.transaction callback instead of tx (silently escapes the transaction); unique violation (23505) not mapped to 409; destructive migration not split into two steps
  • Mongo: missing .lean() on reads; Mongoose docs leaking to the client; duplicate key (11000) not mapped to 409; unbounded embedded arrays

TanStack Query (client data layer)

  • useEffect + fetch + useState holding server data — must be a query
  • Inline queryKey/queryFn in a component instead of the module's queryOptions/mutationOptions factory
  • A variable the queryFn reads that is missing from the queryKey (cache poisoning), or prefetch and hook using different keys (double fetch)
  • Mutation with no invalidateQueries/setQueryData — UI left stale
  • Optimistic update without cancel/snapshot/rollback/settle-invalidate
  • Deprecated prefetchQuery/fetchQuery/ensureQueryData (use queryClient.query()); QueryClient built at module scope or without the server/browser getQueryClient() guard (cross-request data leak)
  • Server prefetch without a HydrationBoundary, or hydrated queries with staleTime: 0 (instant wasted refetch)

Next.js / React

  • 'use client' on components that could be server components
  • Static, non-interactive data fetched via Query in the client when a pure server component would do
  • Missing loading/error states for async UI
  • Server-only imports (db, env secrets) reachable from client bundles
  • Hand-written components duplicating shadcn/ui primitives, or raw palette classes (bg-zinc-100) instead of semantic tokens in feature code

TypeScript

  • any, unsafe casts, non-null assertions hiding real bugs
  • DTO types that drift from the Zod schema (should derive via z.infer)

End with a verdict: ship / fix blockers first / needs rework. You are read-only — report, never fix.

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. 1mo ago Changed · +10 lines · +8 tokens per session e96958bf1302
  2. 1mo ago First seen · 58 lines · 48 tokens per session scan A 4b137164999c

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository AbdulmalekAlshugaa/claude-agents-fullstack (4 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 837 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens