code-explanation

code-explanation is a skill for Claude Code, Codex from jamestorrevillas/dev-skills. It costs 67 tokens per session (685 once invoked), scanned A, original, MIT.

A guide for explaining code and the reasons behind implementation choices. It covers useful comments, function documentation, module notes, and architecture documents.

In plain words
What is it for?
Use it to write comments about tricky logic, document inputs and side effects, explain module responsibilities, and record why one design was chosen over alternatives.
Why use it?
It helps future readers understand non-obvious decisions without filling the code with comments that merely repeat what it does. Clear explanations also make reviews and maintenance easier.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write comments about tricky logic, document inputs and side effects, explain module responsibilities, and record why one design was chosen over alternatives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamestorrevillas/dev-skills/code-explanation
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 jamestorrevillas/dev-skills --skill code-explanation
Clone the repo
git clone --depth 1 https://github.com/jamestorrevillas/dev-skills

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 code-explanation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/code-explanation"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/code-explanation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 685 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 $0.00067 $0.00685
Opus 5.5 $0.00027 $0.00274
Sonnet 5.5 $0.00013 $0.00137
Haiku 4.5 $0.00007 $0.00068

Measured 1mo ago against content hash 7c49eedd25e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-explanation 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 1mo 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.

.github/skills/code-explanation/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Explanation

Core Principle

Comments explain WHY. Code explains WHAT.

If you need a comment to explain what the code does, the code should be cleaner. If you need a comment to explain why it's done this way — write that comment.


The Four Levels of Code Explanation

Level Where Explains
Inline comment Next to specific line Non-obvious logic or gotcha
Function docstring Top of function What it does, parameters, returns, side effects
Module header Top of file What this module is responsible for
Architecture note README / ADR Why this approach was chosen over alternatives

What to Comment (and What Not To)

Comment This

// Using exponential backoff here because the payment API 
// has a 429 rate limit that triggers on burst traffic
await retryWithBackoff(() => paymentAPI.charge(amount))

// Intentionally not validating here — validation happens 
// upstream in the middleware layer (see auth.middleware.ts)
const user = req.user

// This looks backwards but the API returns results 
// in reverse chronological order — newest = index 0
const latest = results[0]

Don't Comment This

// Increment counter by 1
count++

// Check if user is authenticated
if (user.isAuthenticated) {

Docstring Template

/**
 * Calculates the discount amount for a given order.
 * 
 * @param order - The order to calculate discount for
 * @param promoCode - Optional promo code to apply
 * @returns The discount amount in cents, or 0 if no discount applies
 * @throws InvalidPromoCodeError if the promo code format is invalid
 * 
 * Note: Does NOT check if the promo code is active — 
 * call validatePromoCode() first.
 */

PR Description: Explaining Your Decisions

When your PR makes non-obvious decisions, explain them:

## Technical Decisions

**Why I chose X over Y:**
[reasoning — constraints, trade-offs, what you considered]

**Known limitations:**
[what this doesn't handle and why that's acceptable for now]

**What I'd do differently with more time:**
[honest reflection — shows growth mindset]

Read the full file on GitHub · 119 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. 1mo ago First seen · 119 lines · 0 tokens per session scan A 7c49eedd25e8

Subscribe to this mod's changes

code-explanation is a skill published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 67 tokens to every session and 685 once invoked, about $0.0003 per session on Opus 5.5. 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.