validate-impl

validate-impl is a command for Claude Code from growilabs/growi-mcp-server. It costs 9 tokens per session (449 once invoked), scanned A, a copy of validate-impl, MIT.

A command that checks whether an implemented feature matches its requirements, design, and task list. It can find the relevant feature and completed tasks automatically or accept them as arguments.

In plain words
What is it for?
Use it to validate completed Kiro specification tasks and implementation files for a chosen feature or an automatically detected one.
Why use it?
It catches differences between what was planned and what was built before the work is treated as complete. The check also considers the project's steering documents.

Command for Claude Code

Part of the mcp-client-skills plugin — 2 skills, 12 commands shipped together

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/growilabs/growi-mcp-server/validate-impl
Clone the repo
git clone --depth 1 https://github.com/growilabs/growi-mcp-server

Made for: Claude Code.

Or install mcp-client-skills, the plugin that ships this one along with the rest of its 2 skills, 12 commands.

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-impl

README.md
[![agentmods](https://agentmods.dev/badge/commands/growilabs/growi-mcp-server/validate-impl.svg)](https://agentmods.dev/commands/growilabs/growi-mcp-server/validate-impl)
Your own site
<a href="https://agentmods.dev/commands/growilabs/growi-mcp-server/validate-impl"><img src="https://agentmods.dev/badge/commands/growilabs/growi-mcp-server/validate-impl.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00009 $0.00449
Opus 5 $0.00005 $0.00225
Sonnet 5 $0.00002 $0.00090
Haiku 4.5 $0.00001 $0.00045

Measured 4d ago against content hash a1decbb56b75, 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 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.

Origin

This is a copy

94% identical to validate-impl — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/kiro/validate-impl.md · 69 lines

What it actually says

Implementation Validation

Parse Arguments

  • Feature name: $1 (optional)
  • Task numbers: $2 (optional)

Auto-Detection Logic

Perform detection before invoking Subagent:

If no arguments ($1 empty):

  • Parse conversation history for /kiro:spec-impl <feature> [tasks] patterns
  • OR scan .kiro/specs/*/tasks.md for [x] checkboxes
  • Pass detected features and tasks to Subagent

If feature only ($1 present, $2 empty):

  • Read .kiro/specs/$1/tasks.md and find all [x] checkboxes
  • Pass feature and detected tasks to Subagent

If both provided ($1 and $2 present):

  • Pass directly to Subagent without detection

Invoke Subagent

Delegate validation to validate-impl-agent:

Use the Task tool to invoke the Subagent with file path patterns:

Task(
  subagent_type="validate-impl-agent",
  description="Validate implementation",
  prompt="""
Feature: {$1 or auto-detected}
Target tasks: {$2 or auto-detected}
Mode: {auto-detect, feature-all, or explicit}

File patterns to read:
- .kiro/specs/{feature}/*.{json,md}
- .kiro/steering/*.md

Validation scope: {based on detection results}
"""
)

Display Result

Show Subagent summary to user, then provide next step guidance:

Next Steps Guidance

If GO Decision:

  • Implementation validated and ready
  • Proceed to deployment or next feature

If NO-GO Decision:

  • Address critical issues listed
  • Re-run /kiro:spec-impl <feature> [tasks] for fixes
  • Re-validate with /kiro:validate-impl [feature] [tasks]

Note: Validation is recommended after implementation to ensure spec alignment and quality.

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 · 69 lines · 0 tokens per session scan A a1decbb56b75

Subscribe to this mod's changes

validate-impl is a command published in the GitHub repository growilabs/growi-mcp-server (19 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 449 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to validate-impl, differing in 8 lines, and is treated as a copy.