spec-review

spec-review is a command for Claude Code from ThibautBaissac/rails_ai_agents. It costs 28 tokens per session (2,471 once invoked), scanned A, original, MIT.

A read-only adversarial review of a feature specification, which is a written description of what a feature should do. It examines security, performance, edge cases, scaling, and regulatory concerns before implementation planning.

In plain words
What is it for?
Use it after writing a specification and before planning the implementation. Each finding must point to a specific section or to something the specification does not address.
Why use it?
It helps reveal missing requirements and risks before a specification is turned into architecture or code.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it after writing a specification and before planning the implementation. Each finding must point to a specific section or to something the specification does not address.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/spec-review"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/spec-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,471 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 $0.00028 $0.02471
Opus 5 $0.00014 $0.01236
Sonnet 5 $0.00006 $0.00494
Haiku 4.5 $0.00003 $0.00247

Measured 11d ago against content hash c89b4795bb1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 11d 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/sdd/spec-review.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Goal

Act as a devil's advocate — challenge the current feature specification from multiple adversarial perspectives to find gaps, risks, and blind spots that the spec author may have missed. This is a read-only analysis that produces a structured critique. No files are modified.

This command is designed to run AFTER /sdd:specify (and optionally after /sdd:clarify) but BEFORE /sdd:plan. It adds the most value when the spec is considered "ready" but has not yet been translated into architecture.

Operating Constraints

STRICTLY READ-ONLY: Do not modify any files. Output a structured review report. The user decides which findings to address (via /sdd:clarify, /sdd:specify, or manual edits).

Adversarial Mindset: Your job is to find problems, not to praise. A spec with zero findings is suspicious — push harder. However, do not fabricate issues. Every finding must cite a specific spec section or absence.

Constitution Authority: If .specify/memory/constitution.md exists, all findings must be evaluated against its principles. Constitution violations are automatically CRITICAL.

Execution Steps

1. Initialize Review Context

Run .specify/scripts/bash/check-prerequisites.sh --json --paths-only from repo root once. Parse JSON for:

  • FEATURE_DIR
  • FEATURE_SPEC

If FEATURE_SPEC does not exist, abort and instruct user to run /sdd:specify first. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").

2. Load Review Context

  • REQUIRED: Read the feature spec at FEATURE_SPEC
  • IF EXISTS: Read .specify/memory/constitution.md for principle validation
  • IF EXISTS: Read .specify/memory/lessons-learned.md — filter to entries tagged [phase:specify] or [phase:all] for known specification pitfalls from past features

3. Adversarial Analysis Passes

Read the full file on GitHub · 223 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. 11d ago First seen · 223 lines · 28 tokens per session scan A c89b4795bb1b

Subscribe to this mod's changes

spec-review is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (661 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,471 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.