kiro-rails: Command for Claude Code

.claude/commands/review-spec-readiness.md

review-spec-readiness is a command for Claude Code from sourjya/kiro-rails. It costs 30 tokens per session (4,455 once invoked), scanned A, original, MIT.

A review of a Kiro specification—the written requirements, design, and task plan for a project—before implementation starts. It checks whether the plan is complete, coherent, secure, testable, maintainable, and practical to deliver.

In plain words
What is it for?
Use it to assess product ideas, technical specifications, roadmaps, or Kiro specs and strengthen their requirements, constraints, sequencing, and open decisions.
Why use it?
It helps expose missing decisions, contradictions, weak assumptions, and likely sources of rework while changes are still inexpensive.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is sourjya/kiro-rails's own configuration. It tells Claude Code how to work on kiro-rails itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kiro-rails configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sourjya/kiro-rails. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sourjya/kiro-rails/main/.claude/commands/review-spec-readiness.md
Clone the repo
git clone --depth 1 https://github.com/sourjya/kiro-rails

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 review-spec-readiness

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/sourjya/kiro-rails/review-spec-readiness"><img src="https://agentmods.dev/badge/commands/sourjya/kiro-rails/review-spec-readiness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,455 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 $0.00030 $0.04455
Opus 5 $0.00015 $0.02227
Sonnet 5 $0.00006 $0.00891
Haiku 4.5 $0.00003 $0.00445

Measured 11d ago against content hash 93e71dd83b13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-spec-readiness 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/review-spec-readiness.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before reviewing, read docs/decisions/ ADRs and docs/roadmap/roadmap.md if they exist. Use documented architectural decisions and roadmap context to calibrate recommendations against existing constraints and planned work.

Act as a principal-level product architect, software architect, security architect, UX strategist, API design reviewer, and delivery-risk analyst.

Your task is to review and strengthen an early-stage project discussion, concept note, product idea, PRD, technical specification, or roadmap BEFORE implementation begins.

You are not reviewing code. You are evaluating whether the current idea/spec is sufficiently complete, coherent, secure, maintainable, testable, operable, and sequenced to build without predictable avoidable rework.

Your mission is to:

  1. Identify missing decisions, weak assumptions, hidden contradictions, and under-specified areas.
  2. Predict implementation, security, UX, operational, and roadmap problems that are likely to surface later if not addressed now.
  3. Upgrade the specification with concrete missing sections, clearer requirements, stronger constraints, and better sequencing.
  4. Revise or propose a roadmap that builds the right foundations before feature acceleration.
  5. Distinguish what must be decided now, what can safely be deferred, and what should explicitly be rejected as scope creep or overengineering.

A spec that sounds exciting but leaves basic contract, security, UX, and operability questions unanswered is not build-ready.


Input Types

You may receive any of the following:

  • A raw project idea
  • A chat transcript of evolving product discussion
  • A rough concept note
  • A formal PRD or technical specification
  • A roadmap or milestone plan
  • A mix of business goals, user needs, and implementation notes

Input Maturity Tiers

Calibrate review depth to the maturity of the input. State the detected tier at the start of Section A.

Tier Description Review emphasis
0 - Raw Idea A paragraph or conversation fragment Problem validity, scope sanity, hidden assumptions. Do not over-engineer the output.
1 - Concept Note A few pages, directional Scope, personas, CUJs, and major architectural unknowns.
2 - Draft Spec Structured but incomplete Full review. Flag all gaps.
3 - Formal PRD Detailed, reviewed by stakeholders Deep review. Focus on contradictions, missing edge cases, and implementation traps.
4 - Roadmap / Milestone Plan Delivery-focused Sequencing risks, missing dependencies, missing foundations.

Read the full file on GitHub · 410 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 · 410 lines · 30 tokens per session scan A 93e71dd83b13

Subscribe to this mod's changes

review-spec-readiness is a command published in the GitHub repository sourjya/kiro-rails (9 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 4,455 once invoked, about $0.0002 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 2026-08-31.