validate-impl

A command that checks the link from a feature’s requirements to its design, implementation tasks, and code files.

In plain words
What is it for?
Use it to review a named feature by checking its specification files, referenced code, error handling, data checks, and tests.
Why use it?
It helps find missing documents, broken links, and code that does not meet the planned requirements or acceptance checks.

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

Made for: Claude Code.

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 558 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 $0.00558
Opus 5 $0.00000 $0.00279
Sonnet 5 $0.00000 $0.00112
Haiku 4.5 $0.00000 $0.00056

Measured yesterday against content hash 747f882936e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-impl 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 yesterday.

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-impl.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate Implementation

Perform full traceability validation from requirements through design to implementation.

Usage

/kiro:validate-impl <feature-name>

Instructions

  1. Read all spec documents:

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

    If any are missing, report which files are absent.

  2. Build the traceability chain:

    • Requirements -> Design components (from design traceability section)
    • Design components -> Tasks (from task traceability section)
    • Tasks -> Files (from task file lists)
  3. For each requirement, trace the full chain:

    • Which design component addresses it?
    • Which task(s) implement that component?
    • Which files were created/modified?
    • Does the implementation actually satisfy the requirement?
  4. Validate implementation correctness:

    • Read each implemented file referenced in tasks
    • Check that the code matches the design's API contracts
    • Verify error handling matches specified error cases
    • Verify data validation matches model specifications
    • Check that tests exist and cover the requirement
  5. Check acceptance criteria:

    • For each task, verify all acceptance criteria are met
    • Run tests if possible to confirm passing state
  6. Generate full traceability report:

# Implementation Validation: <feature-name>

## Traceability Matrix

| Requirement | Design Component | Task(s) | Files | Status |
|------------|-----------------|---------|-------|--------|
| FR-001 | ComponentA | T-001 | src/a.ts | PASS |
| FR-002 | ComponentB | T-002, T-003 | src/b.ts | FAIL: missing validation |

## Passing Requirements: X / Y

## Failing Requirements
### FR-002: <requirement text>
- **Expected**: <what should happen>
- **Actual**: <what the code does>
- **Fix**: <suggested fix>

## Test Coverage
- Requirements with tests: X / Y
- Tests passing: Z / X

## Overall Verdict: PASS / FAIL
<Summary of validation results>

## Recommended Actions
1. <action>
2. <action>

Read the full file on GitHub · 85 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. yesterday First seen · 85 lines · 0 tokens per session scan A 747f882936e4

Subscribe to this mod's changes

validate-impl 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 558 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.