fact-check

A review guide for checking whether JavaScript documentation is technically correct, including its code examples, browser behavior, and links to outside references.

In plain words
What is it for?
Use it before publishing or after editing JavaScript concept pages, when reviewing contributions, or during accuracy audits.
Why use it?
It helps prevent documentation from teaching incorrect, outdated, or misleading JavaScript information.

Skill for Claude CodeCodex

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 skills/leonardomso/33-js-concepts/fact-check
Any agent
npx skills add leonardomso/33-js-concepts --skill fact-check
Clone the repo
git clone --depth 1 https://github.com/leonardomso/33-js-concepts

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,786 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 $0.00030 $0.04786
Opus 5 $0.00015 $0.02393
Sonnet 5 $0.00006 $0.00957
Haiku 4.5 $0.00003 $0.00479

Measured yesterday against content hash 600e55b2749b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fact-check 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/skills/fact-check/SKILL.md · 650 lines

How it starts

The opening of the file, as written. The whole thing — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: JavaScript Fact Checker

Use this skill to verify the technical accuracy of concept documentation pages for the 33 JavaScript Concepts project. This ensures we're not spreading misinformation about JavaScript.

When to Use

  • Before publishing a new concept page
  • After significant edits to existing content
  • When reviewing community contributions
  • When updating pages with new JavaScript features
  • Periodic accuracy audits of existing content

What We're Protecting Against

  • Incorrect JavaScript behavior claims
  • Outdated information (pre-ES6 patterns presented as current)
  • Code examples that don't produce stated outputs
  • Broken or misleading external resource links
  • Common misconceptions stated as fact
  • Browser-specific behavior presented as universal
  • Inaccurate API descriptions

Fact-Checking Methodology

Follow these five phases in order for a complete fact check.

Phase 1: Code Example Verification

Every code example in the concept page must be verified for accuracy.

Step-by-Step Process
  1. Identify all code blocks in the document

  2. For each code block:

    • Read the code and any output comments (e.g., // "string")
    • Mentally execute the code or test in a JavaScript environment
    • Verify the output matches what's stated in comments
    • Check that variable names and logic are correct
  3. For "wrong" examples (marked with ❌):

    • Verify they actually produce the wrong/unexpected behavior
    • Confirm the explanation of why it's wrong is accurate
  4. For "correct" examples (marked with ✓):

    • Verify they work as stated
    • Confirm they follow current best practices
  5. Run project tests:

    # Run all tests
    npm test
    
    # Run tests for a specific concept
    npm test -- tests/fundamentals/call-stack/
    npm test -- tests/fundamentals/primitive-types/
    
  6. Check test coverage:

    • Look in /tests/{category}/{concept-name}/
    • Verify tests exist for major code examples
    • Flag examples without test coverage

Read the full file on GitHub · 650 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 · 650 lines · 30 tokens per session scan A 600e55b2749b

Subscribe to this mod's changes

fact-check is a skill published in the GitHub repository leonardomso/33-js-concepts (66,520 stars, last pushed 29d ago), licensed MIT. It adds 30 tokens to every session and 4,786 once invoked, about $0.0002 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.