validate-skills

validate-skills is a command for Claude Code from athola/skrills. It costs 16 tokens per session (326 once invoked), scanned A, original, MIT.

A checker for skills written for Claude Code, Codex, or GitHub Copilot CLI. It reports errors, warnings, compatibility issues, and optionally missing dependencies.

In plain words
What is it for?
Use it to check skills for one or more supported assistants, inspect only errors, check dependencies, or apply available automatic fixes.
Why use it?
A skill may look correct but fail in a particular assistant because of formatting, unsupported details, or missing files. Validation finds these problems before use.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Part of the skrills plugin — 17 commands shipped together

Good fit Use it to check skills for one or more supported assistants, inspect only errors, check dependencies, or apply available automatic fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/athola/skrills/validate-skills
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.

Clone the repo
git clone --depth 1 https://github.com/athola/skrills

Made for: Claude Code.

Or install skrills, the plugin that ships this one along with the rest of its 17 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-skills

README.md
[![agentmods](https://agentmods.dev/badge/commands/athola/skrills/validate-skills/github.svg)](https://agentmods.dev/commands/athola/skrills/validate-skills)
Your own site
<a href="https://agentmods.dev/commands/athola/skrills/validate-skills"><img src="https://agentmods.dev/badge/commands/athola/skrills/validate-skills/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 validate-skills

Your own site · 80×15
<a href="https://agentmods.dev/commands/athola/skrills/validate-skills"><img src="https://agentmods.dev/badge/commands/athola/skrills/validate-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 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 $0.00016 $0.00326
Opus 5 $0.00008 $0.00163
Sonnet 5 $0.00003 $0.00065
Haiku 4.5 $0.00002 $0.00033

Measured 9d ago against content hash fc67c411d62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

validate-skills 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 9d 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.

plugins/skrills/commands/validate-skills.md · 34 lines

What it actually says

Validate Skills

Validate installed skills using the skrills MCP server.

Use the mcp__plugin_skrills_skrills__validate-skills tool with:

  • target: Validation target (claude, codex, copilot, both, or all). Default: both
  • autofix: Automatically fix issues when possible
  • errors_only: Only show skills with errors
  • check_dependencies: Validate skill dependencies exist

Parse $ARGUMENTS for:

  • --target <target> or -t <target>: Which CLI(s) to validate against
  • --autofix or -a: Enable automatic fixes
  • --errors-only or -e: Filter to errors only
  • --deps or -d: Check dependencies

Report validation results including:

  • Total skills validated
  • Skills with errors (must fix)
  • Skills with warnings (should fix)
  • Valid skills
  • Specific issues and how to fix them

Handle errors:

  • If target invalid: List valid options (claude, codex, copilot, both, all)
  • If no skills found: Report empty state with setup suggestions
  • If autofix fails: Report which fixes failed and why
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. 9d ago First seen · 34 lines · 16 tokens per session scan A fc67c411d62f

Subscribe to this mod's changes

validate-skills is a command published in the GitHub repository athola/skrills (69 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 326 once invoked, about $0.0001 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 2026-08-30.