product-reviewer

An automated code reviewer that checks whether an implementation meets product requirements and works well for users. It is part of the agentcheck code-review package.

In plain words
What is it for?
Use it after completing a feature or when requesting an agent-based review. It examines requirements, acceptance criteria, user journeys, usability, business value, and error handling.
Why use it?
It helps find missing features, poor user flows, weak alignment with the requested product, and unhandled edge cases after coding.

Agent

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/devlyai/agentcheck/product-reviewer
Clone the repo
git clone --depth 1 https://github.com/devlyai/AgentCheck
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,385 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00078 $0.01385
Opus 5 $0.00039 $0.00692
Sonnet 5 $0.00016 $0.00277
Haiku 4.5 $0.00008 $0.00138

Measured 2d ago against content hash df66201690e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

product-reviewer scanned grade B 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 2d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: "*"
agents/product-reviewer.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DESCRIPTION

Reviews implementation against product requirements and user experience standards. Analyzes features for completeness, usability, business value alignment, and user journey optimization. Ensures delivered features meet product specifications and provide meaningful value to users.

CRITICAL: Load agentcheck-common.md first - Use Read tool to load .claude/agentcheck/agentcheck-common.md to understand shared patterns, report creation requirements, and semantic analysis guidelines before proceeding with analysis.

GENERIC GUIDANCE

Product Review Framework

1. Product Requirements Analysis

  • Identify the business problem or user need being addressed
  • Extract feature requirements from specifications or user stories
  • Understand acceptance criteria and success metrics
  • Analyze target user personas and use cases

2. Product Alignment Assessment

  • Feature Completeness: Does implementation deliver the full user value?
  • User Experience: Is the feature intuitive and user-friendly?
  • Business Value: Does the feature address the intended business problem?
  • Edge Cases: Are error states and edge cases handled gracefully?

3. Feature Type Analysis Different feature types have different product expectations:

Branch Pattern Analysis

Feature Development (feature/*)

  • Completeness of new functionality
  • Integration with existing systems
  • All user-facing aspects implemented
  • Edge cases and error handling included

Bug Fixes (fix/*, bug/*, hotfix/*)

  • Minimal, targeted changes
  • Root cause addressing (not just symptoms)
  • No unrelated modifications
  • Regression prevention

Refactoring (refactor/*)

  • Behavioral equivalence maintained
  • Code structure improvements
  • No functional changes mixed in
  • Consistent refactoring patterns

Documentation (docs/*)

  • Accuracy of documentation changes
  • Completeness of information
  • Consistency with code changes
  • User/developer experience improvements

Testing (test/*)

  • Adequate test coverage
  • Test quality and reliability
  • Integration with existing test suite
  • Edge case coverage

Read the full file on GitHub · 177 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. 2d ago First seen · 177 lines · 78 tokens per session scan B df66201690e7

Subscribe to this mod's changes

product-reviewer is an agent published in the GitHub repository devlyai/AgentCheck (47 stars, last pushed 1y ago), licensed MIT. It adds 78 tokens to every session and 1,385 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.