write-concept

write-concept is a skill for Claude Code, Codex from leonardomso/33-js-concepts. It costs 27 tokens per session (12,405 once invoked), scanned A, original, MIT.

A writing guide for creating and reviewing pages that explain JavaScript concepts in the 33 JavaScript Concepts project. It is aimed at beginners as well as intermediate developers.

In plain words
What is it for?
Use it to create, rewrite, review, or expand JavaScript documentation in the project's docs/concepts/ folder.
Why use it?
It helps keep concept pages clear, consistent, practical, and easy to follow without assuming that readers already know how to code.

Skill for Claude CodeCodex

About the project

33 JavaScript Concepts is a learning guide that explains core JavaScript ideas through practical examples and selected resources. It helps developers understand topics such as primitive values, objects, coercion, equality, scope, closures, and the call stack. The catalogue add-ons provide skills related to studying or working with the guide.

leonardomso/33-js-concepts · 66,518 stars · on GitHub

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

Made for: Claude Code, Codex.

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 write-concept

README.md
[![agentmods](https://agentmods.dev/badge/skills/leonardomso/33-js-concepts/write-concept.svg)](https://agentmods.dev/skills/leonardomso/33-js-concepts/write-concept)
Your own site
<a href="https://agentmods.dev/skills/leonardomso/33-js-concepts/write-concept"><img src="https://agentmods.dev/badge/skills/leonardomso/33-js-concepts/write-concept.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,405 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 $0.00027 $0.12405
Opus 5 $0.00014 $0.06202
Sonnet 5 $0.00005 $0.02481
Haiku 4.5 $0.00003 $0.01240

Measured 5d ago against content hash 8ed8542de8c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-concept 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 5d 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/write-concept/SKILL.md · 1,445 lines

How it starts

The opening of the file, as written. The whole thing — 1,445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Write JavaScript Concept Documentation

Use this skill when writing or improving concept documentation pages for the 33 JavaScript Concepts project.

When to Use

  • Creating a new concept page in /docs/concepts/
  • Rewriting or significantly improving an existing concept page
  • Reviewing an existing concept page for quality and completeness
  • Adding explanatory content to a concept

Target Audience

Remember: the reader might be someone who has never coded before or is just learning JavaScript. Write with empathy for beginners while still providing depth for intermediate developers. Make complex topics feel approachable and never assume prior knowledge without linking to prerequisites.

Writing Guidelines

Voice and Tone

  • Conversational but authoritative: Write like you're explaining to a smart friend
  • Encouraging: Make complex topics feel approachable
  • Practical: Focus on real-world applications and use cases
  • Concise: Respect the reader's time; avoid unnecessary verbosity
  • Question-driven: Open sections with questions the reader might have

Avoiding AI-Generated Language

Your writing must sound human, not AI-generated. Here are specific patterns to avoid:

Words and Phrases to Avoid
❌ Avoid ✓ Use Instead
"Master [concept]" "Learn [concept]"
"dramatically easier/better" "much easier" or "cleaner"
"one fundamental thing" "one simple thing"
"one of the most important concepts" "This is a big one"
"essential points" "key things to remember"
"understanding X deeply improves" "knowing X well makes Y easier"
"To truly understand" "Let's look at" or "Here's how"
"This is crucial" "This trips people up"
"It's worth noting that" Just state the thing directly
"It's important to remember" "Don't forget:" or "Remember:"
"In order to" "To"
"Due to the fact that" "Because"
"At the end of the day" Remove entirely
"When it comes to" Remove or rephrase
"In this section, we will" Just start explaining
"As mentioned earlier" Remove or link to the section

Read the full file on GitHub · 1,445 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. 5d ago First seen · 1,445 lines · 27 tokens per session scan A 8ed8542de8c8

Subscribe to this mod's changes

write-concept is a skill published in the GitHub repository leonardomso/33-js-concepts (66,518 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 12,405 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.