validate-design

validate-design is a command for Claude Code from kaze-jp/kusa. It costs 0 tokens per session (520 once invoked), scanned A, original, MIT.

A checker for design documents that tests whether they fully and consistently address the stated software requirements.

In plain words
What is it for?
Use it to validate a Kiro feature's requirements and design documents before implementation.
Why use it?
It finds requirements missing from the design, unsupported design parts, and gaps in areas such as errors, security, performance, and accessibility.

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/kaze-jp/kusa/validate-design
Clone the repo
git clone --depth 1 https://github.com/kaze-jp/kusa

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 validate-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaze-jp/kusa/validate-design.svg)](https://agentmods.dev/commands/kaze-jp/kusa/validate-design)
Your own site
<a href="https://agentmods.dev/commands/kaze-jp/kusa/validate-design"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/validate-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 520 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 $0.00000 $0.00520
Opus 5 $0.00000 $0.00260
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 4d ago against content hash 2939e0f24fe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-design 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 4d 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/kiro/validate-design.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate Design

Validate a design document against its requirements for completeness, consistency, and correctness.

Usage

/kiro:validate-design <feature-name>

Instructions

  1. Read both documents:

    • .kiro/specs/$FEATURE_NAME/requirements.md
    • .kiro/specs/$FEATURE_NAME/design.md

    If either is missing, report which file is absent and what command to run.

  2. Perform traceability check:

    • For EVERY requirement ID in requirements.md, verify it appears in the design's traceability section
    • Flag any requirement that has no corresponding design component
    • Flag any design component that does not trace back to a requirement
  3. Check for gaps:

    • Error handling: Does every API contract specify error cases?
    • Edge cases: Are boundary conditions from requirements addressed?
    • Security: Are authentication/authorization requirements covered?
    • Performance: Are performance requirements reflected in design choices?
    • Accessibility: Are accessibility requirements addressed?
  4. Check for inconsistencies:

    • Data model fields must match what API contracts reference
    • Component interfaces must be compatible with their consumers
    • State management must account for all state transitions in requirements
    • Naming must be consistent across all design sections
  5. Check design quality:

    • Architecture decisions have rationale documented
    • Component boundaries are clear and explicit
    • No circular dependencies between components
    • Testing strategy covers all components
    • No premature optimization
  6. Generate validation report:

# Design Validation: <feature-name>

## Traceability
- Requirements covered: X / Y
- Uncovered requirements: [list]
- Orphan design components: [list]

## Gaps Found
- [ ] <gap description with severity: Critical/Major/Minor>

## Inconsistencies Found
- [ ] <inconsistency description>

## Design Quality
- [ ] All decisions have rationale: Pass/Fail
- [ ] Component boundaries clear: Pass/Fail
- [ ] No circular dependencies: Pass/Fail
- [ ] Error handling complete: Pass/Fail

## Verdict: PASS / NEEDS REVISION
<Summary and recommended fixes>

Read the full file on GitHub · 80 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. 4d ago First seen · 80 lines · 0 tokens per session scan A 2939e0f24fe5

Subscribe to this mod's changes

validate-design is a command published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 520 tokens. 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.