youth-safety-review

youth-safety-review is a skill for Claude Code from ncssm-robotics/ftc-claude. It costs 58 tokens per session (1,118 once invoked), scanned A, original, MIT.

A review guide for checking whether FTC student-facing code contains inappropriate language. FIRST Tech Challenge is a student robotics competition, and the guide focuses on names, comments, strings, and file names.

In plain words
What is it for?
Use it to review variable and class names, comments, messages, and filenames in code intended for students aged roughly 12–18.
Why use it?
It helps mentors and maintainers spot profanity or questionable wording before code is shared with students. Flagged items still require human judgment because game terms can have harmless technical meanings.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to review variable and class names, comments, messages, and filenames in code intended for students aged roughly 12–18.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ncssm-robotics/ftc-claude/youth-safety-review
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.

Any agent
npx skills add ncssm-robotics/ftc-claude --skill youth-safety-review
Clone the repo
git clone --depth 1 https://github.com/ncssm-robotics/ftc-claude

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 youth-safety-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ncssm-robotics/ftc-claude/youth-safety-review/github.svg)](https://agentmods.dev/skills/ncssm-robotics/ftc-claude/youth-safety-review)
Your own site
<a href="https://agentmods.dev/skills/ncssm-robotics/ftc-claude/youth-safety-review"><img src="https://agentmods.dev/badge/skills/ncssm-robotics/ftc-claude/youth-safety-review/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 youth-safety-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ncssm-robotics/ftc-claude/youth-safety-review"><img src="https://agentmods.dev/badge/skills/ncssm-robotics/ftc-claude/youth-safety-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,118 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 $0.00058 $0.01118
Opus 5 $0.00029 $0.00559
Sonnet 5 $0.00012 $0.00224
Haiku 4.5 $0.00006 $0.00112

Measured 12d ago against content hash c8b458e66ee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

youth-safety-review 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 12d 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/skills/youth-safety-review/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FTC Youth Safety Review Checks

This skill defines content appropriateness checks for FTC marketplace skills. FTC participants are students ages 12-18, so all content should be appropriate for that audience.

Important: These checks flag items for human review. They do not auto-reject content because context matters. A mentor or maintainer should review flagged items.

Acceptable FTC Terms

These terms are ALLOWED despite potentially triggering filters:

Term Context
kill, killer Game mechanic (kill shot, killing it)
attack, defense Game strategy terms
destroy Game context (destroy opponent's stack)
target Vision targeting, game elements
shoot, shooter Game mechanisms
score, scoring Points and objectives
dead Battery dead, dead reckoning

Language Checks (Warnings)

Flag for human review if detected in:

  • Variable names
  • Function/method names
  • Class names
  • Comments
  • String literals
  • File names

Profanity Detection

  • No profanity in variable names
  • No profanity in comments
  • No profanity in string literals
  • No l33tspeak variations of profanity

Inappropriate Naming

  • Variable names don't contain inappropriate content
  • Function names are professional
  • Class names are appropriate

Insensitive Language

  • No racial or ethnic slurs
  • No gender-based insults
  • No disability-related slurs
  • No religious insults

Comment Review (Warnings)

Tone and Content

  • Comments don't contain personal attacks
  • Comments don't contain exclusionary language
  • Comments don't reference inappropriate content
  • TODO comments don't contain frustration venting

Humor

  • Jokes are appropriate for all ages
  • Sarcasm doesn't cross into inappropriate territory
  • Pop culture references are age-appropriate

Personal Information (Errors)

These must be fixed - privacy is important.

Student Information

  • No real student names in examples
  • No student photos or identifying information
  • No birth dates or ages

Read the full file on GitHub · 167 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. 12d ago First seen · 167 lines · 58 tokens per session scan A c8b458e66ee7

Subscribe to this mod's changes

youth-safety-review is a skill published in the GitHub repository ncssm-robotics/ftc-claude (4 stars, last pushed 7mo ago), licensed MIT. It adds 58 tokens to every session and 1,118 once invoked, about $0.0003 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 2026-08-31.