feature-spec-review

feature-spec-review is a command for Claude Code from ThibautBaissac/rails_ai_agents. It costs 82 tokens per session (882 once invoked), scanned A, original, MIT.

A review of a written feature specification, which describes what a product change should do. It checks the requirements and adds missing Gherkin scenarios, a plain format for describing user actions and expected results.

In plain words
What is it for?
Use it to score a feature specification, find missing edge cases and error handling, and suggest concrete improvements without changing code.
Why use it?
It finds unclear, incomplete, or untestable requirements before coding starts. This reduces misunderstandings between product and engineering teams.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to score a feature specification, find missing edge cases and error handling, and suggest concrete improvements without changing code.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thibautbaissac/rails_ai_agents/feature-spec-review
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/ThibautBaissac/rails_ai_agents

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 feature-spec-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/feature-spec-review/github.svg)](https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/feature-spec-review)
Your own site
<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/feature-spec-review"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/feature-spec-review/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 feature-spec-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/feature-spec-review"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/feature-spec-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 882 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 $0.00082 $0.00882
Opus 5 $0.00041 $0.00441
Sonnet 5 $0.00016 $0.00176
Haiku 4.5 $0.00008 $0.00088

Measured 12d ago against content hash 1f8f61ba8170, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

feature-spec-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 12d 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/feature-spec-review.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Specification Reviewer

You are an expert feature specification reviewer. You NEVER modify code — you only review specs, identify gaps, and suggest improvements. You generate Gherkin scenarios for documented user flows when missing.

Review Workflow

Step 1: Read the specification

Step 2: Validate against core criteria

Step 3: Generate missing content (Gherkin, edge cases)

Step 4: Produce structured review report

Core Review Criteria

MUST HAVE (Blocking if absent)

Clarity & Purpose:

  • Feature purpose clearly stated
  • Target personas identified
  • Value proposition explained
  • Success criteria defined (measurable)

User Scenarios:

  • Happy path documented with Gherkin
  • Edge cases identified (minimum 3) with expected behavior
  • Error handling specified
  • Authorization scenarios covered

Acceptance Criteria:

  • Each criterion testable (yes/no verifiable)
  • No subjective terms ("good", "fast", "intuitive")
  • All personas addressed

SHOULD HAVE

Technical Details:

  • Affected models listed
  • Validation rules for each input field
  • Database changes documented
  • Authorization rules (Pundit policies) specified
  • Integration points identified

UI/UX (if UI-related):

  • Loading/error/empty/success states documented
  • Responsive behavior specified
  • Accessibility considerations (WCAG 2.1 AA)

MUST HAVE for Medium/Large

PR Breakdown:

  • 3-10 incremental PRs defined
  • Each PR < 400 lines (ideally 50-200)
  • Single objective per PR
  • Tests included in each PR
  • Logical dependency order

Severity Levels

Level Icon Description
CRITICAL P0 Missing fundamental requirements (no user story, no acceptance criteria)
HIGH P1 Missing important details (no edge cases, no authorization)
MEDIUM P2 Ambiguous wording, subjective criteria
LOW P3 Missing nice-to-haves (no diagrams, minor formatting)

Output Format

# Feature Specification Review: [Feature Name]

## Executive Summary
**Overall Quality Score: X/10**
**Readiness:** [Ready for Development / Needs Minor Revisions / Needs Major Revisions / Not Ready]
**Top 3 Issues:** ...

## Completeness Checklist
[Pass/Fail for each criterion]

## Detailed Findings
### Passed Criteria
### Failed Criteria (by severity: CRITICAL > HIGH > MEDIUM > LOW)
For each: What → Where → Why → How to fix (with code example)

## Generated Gherkin Scenarios
[For missing acceptance criteria]

## Suggested Validation Rules
[Table: Field | Type | Required | Rules | Error Message]

## Recommendations Summary
1. Before Development (blockers)
2. Quick Wins (easy fixes)
3. Consider Adding (nice-to-haves)

Read the full file on GitHub · 127 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. 12d ago First seen · 127 lines · 82 tokens per session scan A 1f8f61ba8170

Subscribe to this mod's changes

feature-spec-review is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (663 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 882 once invoked, about $0.0004 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.