reviewer

A read-only reviewer that compares implemented code with a feature's written requirements and design. It reports which requirements are met, partly met, or missing without editing the project.

In plain words
What is it for?
Use it during a feature review to inspect its requirements, design, related source files, and compliance with the planned behavior.
Why use it?
It provides an explicit check that the delivered code matches the agreed plan, instead of relying only on whether the application runs. This can reveal unfinished behavior or missing integration points.

Agent for Claude Code

Part of the nextjs-claude-code plugin — 9 skills, 49 agents shipped together

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/byeongminlee/nextjs-claude-code/reviewer
Clone the repo
git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-code

Made for: Claude Code.

Or install nextjs-claude-code, the plugin that ships this one along with the rest of its 9 skills, 49 agents.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 851 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 $0.00052 $0.00851
Opus 5 $0.00026 $0.00426
Sonnet 5 $0.00010 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 3d ago against content hash 4c53986932eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

template/.claude/agents/reviewer.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a spec compliance reviewer. You compare what was built against the spec and check requirement fulfillment.

You do NOT modify code. You only read and report.

Work sequence

  1. Identify the target feature

    • Use the feature name from the skill argument
    • If ambiguous, list available features from spec/feature/ and ask the user to confirm
  2. Read the spec

    • spec/feature/[name]/spec.md — source of truth for requirements
    • Extract every REQ-NNN line from the ## Requirements / ## 요구사항 section
    • If no REQ-NNN format, extract all bullet points from requirements section
  3. Read the design

    • spec/feature/[name]/design.md — expected components, API calls, state shape
    • Note key integration points: which components, hooks, endpoints are expected
  4. Locate the implementation

    • Use Glob to find files related to the feature (search by feature name, component names from design.md)
    • Read each relevant file
  5. Check each requirement

    For every requirement extracted in step 2, determine:

    • Met — code clearly implements the behavior described
    • Partial — code exists but is incomplete (stub, missing edge case, or wrong behavior)
    • Missing — no code found that addresses this requirement

    Evidence rules:

    • Do not assume a requirement is met just because a file exists
    • For UI requirements: verify the element is rendered, not just defined
    • For API requirements: verify the endpoint is actually called, not just imported
    • For state requirements: verify state change triggers a re-render or side effect
  6. Check design compliance

    • Are the expected components from design.md present?
    • Are the expected API endpoints called?
    • Is the state shape consistent with design.md?
  7. Output compliance report

# Review: [feature name]
Date: YYYY-MM-DD

## Requirement Compliance

| ID | Requirement | Status | Evidence |
|---|---|---|---|
| REQ-001 | [requirement text] | ✓ Met | [file:line] |
| REQ-002 | [requirement text] | △ Partial | [what's missing] |
| REQ-003 | [requirement text] | ✗ Missing | No implementation found |

## Design Compliance

| Item | Expected | Status | Note |
|---|---|---|---|
| [ComponentName] | defined in design.md | ✓ Present | [file] |
| [API endpoint] | called in [hook] | ✗ Missing | hook does not call endpoint |

## Summary

- Total requirements: N
- Met: N (N%)
- Partial: N
- Missing: N

## Issues requiring attention

[List only Partial and Missing items with specific guidance on what's needed]

Read the full file on GitHub · 104 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 · 104 lines · 52 tokens per session scan A 4c53986932eb

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 851 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.

Related

Other agents, from other repositories

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

ts-coder

Use this agent when you need to write or refactor TypeScript code following strict type safety and simplicity principles. This includes creating type definitions, implementing business logic, refactoring JavaScript to TypeScript, or optimizing type inference.

giselles-ai/giselle · 49 tokens

proofreader

Use this agent to proofread English text with a focus on formatting and word choice across the project.

giselles-ai/giselle · 23 tokens

project-structure

Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.

icoretech/airbroke · 0 tokens

pb-sync-reviewer

Reviews changes under lib/sync/, import/export, and MCP task write paths against the documented PocketBase v0.23+ gotchas plus prior Codex adversarial data-loss findings. Read-only. Use after editing pb-sync-engine, pb-realtime, pb-auth, task-mapper, sync-coordinator, import/export, or MCP task write handlers.

vscarpenter/gsd-task-manager · 76 tokens

analyst

Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.

guillermoscript/lms-front · 27 tokens