explain

explain is a command for coding agents from bengous/claude-code-plugins. It costs 26 tokens per session (334 once invoked), scanned A, original, MIT.

A command that explains a concept, code pattern, or topic in as few words as needed. It can use a simple diagram when that makes a mechanism easier to understand.

In plain words
What is it for?
Use it to learn how code works, understand a programming concept, or clarify a topic in the current codebase.
Why use it?
It helps you understand unfamiliar ideas without receiving a long, repetitive tutorial or unexplained technical terms.

Command

Part of the understanding plugin — 2 commands shipped together

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 commands/bengous/claude-code-plugins/explain
Clone the repo
git clone --depth 1 https://github.com/bengous/claude-code-plugins

Or install understanding, the plugin that ships this one along with the rest of its 2 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 explain

README.md
[![agentmods](https://agentmods.dev/badge/commands/bengous/claude-code-plugins/explain.svg)](https://agentmods.dev/commands/bengous/claude-code-plugins/explain)
Your own site
<a href="https://agentmods.dev/commands/bengous/claude-code-plugins/explain"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/explain.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 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 $0.00026 $0.00334
Opus 5 $0.00013 $0.00167
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00003 $0.00033

Measured yesterday against content hash 53c4de1e0509, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explain 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.

understanding/commands/explain.md · 31 lines

What it actually says

Explain: $ARGUMENTS

Make the user genuinely understand the topic in the fewest words that do the job.

  • Answer the question asked, not a template. No fixed sections, no mandatory analogy, no restating an idea already stated. Stop when the concept is understood — if the answer runs past roughly a screen, you are answering questions that weren't asked.
  • If the topic touches this codebase, ground the explanation in the actual code and cite file:line. Otherwise explain from knowledge — but verify recent, contested, or precise factual claims (numbers, dates, attributions) with the research tools before asserting them. Name a verified source inline in the sentence that uses it; never append a sources section.
  • Default to no diagram. Add at most one ASCII diagram (under 80 columns) only when it shows something simultaneous or branching that linear prose can't hold — a fork, a feedback loop, concurrent state. A diagram that restates the prose is noise.
  • Define jargon inline the first time it appears, or don't use it.
  • End with a single line naming 2-3 adjacent angles worth digging into, and let follow-up questions drive the depth. Never pre-empt them with the full tour.
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 · 31 lines · 26 tokens per session scan A 53c4de1e0509

Subscribe to this mod's changes

explain is a command published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 334 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 2026-09-03.