review

A project command that checks whether a feature specification is complete, follows EARS requirements language, and is ready for implementation. EARS is a format for writing precise software requirements.

In plain words
What is it for?
Use it to review a feature’s context, requirements, and task files, assess their structure and EARS compliance, and identify possible improvements.
Why use it?
It can reveal missing specification files, unclear requirements, and quality problems before development starts. This reduces ambiguity for the people or agents implementing the feature.

Command for Claude Code

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 commands/marcelsud/spec-driven-agentic-development/review
Clone the repo
git clone --depth 1 https://github.com/marcelsud/spec-driven-agentic-development

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,845 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 $0.00013 $0.01845
Opus 5 $0.00006 $0.00923
Sonnet 5 $0.00003 $0.00369
Haiku 4.5 $0.00001 $0.00185

Measured 2d ago against content hash e6e5d3995c03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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 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.

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/commands/spec/review.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Feature Specification

Review a feature specification for completeness, EARS format compliance, and identify areas for improvement.

Feature: $ARGUMENTS

Feature Selection

  1. IF a feature name is provided in $ARGUMENTS:

    • Find a directory in features/ that matches $ARGUMENTS
    • If no exact match, search for closest match and ask for confirmation
  2. IF no feature name is provided:

    • List all directories under features/
    • If only one exists, select it automatically
    • If multiple exist, ask user to specify using AskUserQuestion

Your Task

Analyze the feature specification files and produce a comprehensive quality review.

Process

Step 1: Load Feature Files

Read all specification files:

  • features/[feature-name]/context.md
  • features/[feature-name]/requirements.md
  • features/[feature-name]/tasks.md

If any file is missing, note it as a critical issue.

Step 2: Review context.md

Check for required sections:

  • Overview - Brief description of the feature
  • Goals - What the feature aims to achieve
  • Scope - In Scope / Out of Scope clearly defined
  • Technical Decisions - Stack, architecture, key decisions with rationale
  • Constraints & Considerations - Limitations and important factors
  • Dependencies - External dependencies and requirements

Flag as issues:

  • Missing sections (Critical)
  • Empty or placeholder content (Warning)
  • Technical decisions without rationale (Suggestion)

Step 3: Review requirements.md - EARS Compliance

Check EARS Format

Each requirement must use one of these patterns:

Type Pattern Example
Ubiquitous "The system SHALL [requirement]" The system SHALL encrypt all passwords
Event-Driven "WHEN [trigger] THEN the system SHALL [response]" WHEN user clicks submit THEN the system SHALL validate input
State-Driven "WHILE [state] the system SHALL [requirement]" WHILE processing payment the system SHALL display progress
Conditional "IF [condition] THEN the system SHALL [requirement]" IF cart is empty THEN the system SHALL show empty message
Optional "WHERE [feature] the system SHALL [requirement]" WHERE premium enabled the system SHALL allow exports

Read the full file on GitHub · 232 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 · 232 lines · 13 tokens per session scan A e6e5d3995c03

Subscribe to this mod's changes

review is a command published in the GitHub repository marcelsud/spec-driven-agentic-development (174 stars, last pushed 9mo ago), licensed MIT. It adds 13 tokens to every session and 1,845 once invoked, about $0.0001 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 2026-08-30.