validate-skill

validate-skill is a command for Claude Code from VoDaiLocz/kilo-kit-mcp. It costs 0 tokens per session (318 once invoked), scanned A, original, Apache-2.0.

A command-line checker for skill files, which are instruction files used by coding agents to follow repeatable workflows.

In plain words
What is it for?
Use it to validate one skill or all skills, inspect detailed warnings, return machine-readable JSON, and review file structure and workflow quality.
Why use it?
It finds missing required sections, incomplete metadata, weak descriptions, and other quality issues before a skill is used.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python src/tools/validate-skill.py skills/kilo-kit/debugging/systematic/.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/vodailocz/kilo-kit-mcp/validate-skill.svg)](https://agentmods.dev/commands/vodailocz/kilo-kit-mcp/validate-skill)
Your own site
<a href="https://agentmods.dev/commands/vodailocz/kilo-kit-mcp/validate-skill"><img src="https://agentmods.dev/badge/commands/vodailocz/kilo-kit-mcp/validate-skill.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 318 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 5.1 $0.00000 $0.00318
Opus 5 $0.00000 $0.00159
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 6d ago against content hash da0c40c8bcc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

validate-skill 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 6d 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.

commands/validate-skill.md · 46 lines

What it actually says

🔍 Validate Skill Command

Usage: Validate skill files for correctness, completeness, and quality.

Quick Start

# Python
python src/tools/validate-skill.py skills/kilo-kit/debugging/systematic/
python src/tools/validate-skill.py skills/kilo-kit/ --all --verbose

# Node.js
node src/tools/validate-skill.js skills/kilo-kit/debugging/systematic
node src/tools/validate-skill.js --all skills/kilo-kit --verbose

What It Checks

Required (Error if missing)

  • SKILL.md file exists
  • YAML frontmatter with name, description, version
  • Sections: "When to Use", "Process", "Guidelines"

Recommended (Warning if missing)

  • Frontmatter: behaviors, token_estimate, dependencies
  • Sections: "Prerequisites", "Success Criteria", "Related Skills"
  • At least 3 keywords in description

Quality (Info)

  • File size (not too short or too long)
  • Process has multiple phases
  • Guidelines has DO and DON'T subsections

Options

Flag Description
--all, -a Validate all skills under path
--verbose, -v Show all issues including info
--json Output as JSON (Python only)
--fix Attempt auto-fix (planned)

Validate Skill Command v1.0.0

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. 6d ago First seen · 46 lines · 0 tokens per session scan A da0c40c8bcc3

Subscribe to this mod's changes

validate-skill is a command published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 318 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 2026-08-30.