reviewer

reviewer is a skill for Claude Code from MountainUnicorn/add. It costs 18 tokens per session (4,505 once invoked), scanned A, original, MIT.

A read-only code inspection tool that compares an implementation with its specification and reports problems in behavior, quality, tests, structure, errors, and documentation.

In plain words
What is it for?
Use it to check whether acceptance criteria have passing tests, inspect backend or frontend implementations, and review compliance with the project's development practices.
Why use it?
It provides a structured review without changing the code. It helps reveal missing requirements, weak test coverage, unfinished work, and maintainability issues.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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/skills/mountainunicorn/add/reviewer.svg)](https://agentmods.dev/skills/mountainunicorn/add/reviewer)
Your own site
<a href="https://agentmods.dev/skills/mountainunicorn/add/reviewer"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,505 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00018 $0.04505
Opus 5 $0.00009 $0.02253
Sonnet 5 $0.00004 $0.00901
Haiku 4.5 $0.00002 $0.00451

Measured 6d ago against content hash 5fff83b70470, 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 1 finding 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 6d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Search for synchronous I/O in async contexts (`readFileSync`, `execSync`, blocking HTTP calls)
core/skills/reviewer/SKILL.md · 631 lines

How it starts

The opening of the file, as written. The whole thing — 631 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Reviewer Skill v{{VERSION}}

Conduct a comprehensive code review focused on specification compliance, code quality, and ADD methodology adherence. This is a READ-ONLY skill that produces a detailed structured review report.

Overview

The Reviewer analyzes implementation against the spec and quality standards without modifying code. It checks:

  • Spec Compliance: Every acceptance criterion has a corresponding passing test
  • Code Quality: Readability, maintainability, style adherence
  • Test Coverage: Edge cases, error conditions, user scenarios
  • Architecture: Separation of concerns, dependency management
  • Error Handling: Validation, exception handling, error messages
  • Documentation: Comments, docstrings, API clarity
  • ADD Adherence: Test coverage, traceability, naming conventions

Pre-Flight Checks

  1. Verify spec file exists

    • Read spec at provided path
    • Extract feature name, acceptance criteria, user test cases
    • Identify scope (backend, frontend, or full system)
  2. Verify implementation exists

    • Locate implementation files from spec or config
    • Verify code files are readable
    • Check for completeness (no placeholder files)
  3. Verify tests exist and pass

    • Locate test files (tests/ or tests/)
    • Read test mapping file if available
    • Run tests to confirm all passing: npm test or python -m pytest
    • Halt if tests not passing (code not GREEN)
  4. Load configuration

    • Read .add/config.json for:
      • Code style rules
      • Test coverage thresholds
      • Quality standards
      • Naming conventions
  5. Determine review scope

    • Use --scope flag or infer from config
    • backend: Server, API, database code
    • frontend: UI, components, client code
    • full: Everything

Read the full file on GitHub · 631 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. 6d ago First seen · 631 lines · 18 tokens per session scan A 5fff83b70470

Subscribe to this mod's changes

reviewer is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 4,505 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.