plain-english

plain-english is a command for coding agents from reggiechan74/cc-plugins. It costs 16 tokens per session (2,506 once invoked), scanned A, original, MIT.

A command that turns a difficult, math-heavy document into a companion version with plain-English explanations after complex sections while keeping the original text.

In plain words
What is it for?
Use it to create a more accessible Markdown explanation of a technical document, such as a paper, specification, or mathematical text.
Why use it?
It helps readers understand symbols, formal definitions, and specialised language without replacing the source document. Large documents are handled section by section.

Command

Part of the math-paper-creator plugin — 7 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/reggiechan74/cc-plugins/plain-english
Clone the repo
git clone --depth 1 https://github.com/reggiechan74/cc-plugins

Or install math-paper-creator, the plugin that ships this one along with the rest of its 7 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 plain-english

README.md
[![agentmods](https://agentmods.dev/badge/commands/reggiechan74/cc-plugins/plain-english.svg)](https://agentmods.dev/commands/reggiechan74/cc-plugins/plain-english)
Your own site
<a href="https://agentmods.dev/commands/reggiechan74/cc-plugins/plain-english"><img src="https://agentmods.dev/badge/commands/reggiechan74/cc-plugins/plain-english.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,506 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 $0.00016 $0.02506
Opus 5 $0.00008 $0.01253
Sonnet 5 $0.00003 $0.00501
Haiku 4.5 $0.00002 $0.00251

Measured 4d ago against content hash 742d82b78f4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plain-english 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 4d 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.

math-paper-creator/commands/plain-english.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plain-English Companion Generator

Purpose: Take a mathematically dense, symbol-heavy, or conceptually difficult document and produce a companion version that adds plain-English explanation callouts after complex sections. The original text is preserved by default.

Architecture: Uses a chunked processing pipeline — each section is processed independently to avoid context overflow on large documents. No single agent call needs to hold the full source + full output.

Instructions

When this command is invoked:

Step 1: Parse Arguments

  • First argument (required): path to the source document
  • Second argument (optional): output path. Default: <source_name>_plain_english.md in the same directory

If no file path is provided, use AskUserQuestion to request one.

Step 2: Read and Analyze the Source Document

Read the source document. Perform a quick structural analysis:

  • Count sections/headings
  • Identify math-heavy sections (LaTeX $...$, $$...$$, Greek symbols, formal notation)
  • Identify conceptually dense sections (formal definitions, domain-specific jargon, multi-layered abstractions)
  • Estimate total complexity (light, moderate, heavy)

Report to the user:

Analyzed: <filename>
- <N> sections, <M> lines
- Math density: <light/moderate/heavy> (<count> formulas detected)
- Estimated output: ~<N> callout insertions

Step 3: Interview the User

Use AskUserQuestion to ask the following questions one at a time. Each question should include the multiple-choice options and a brief note on trade-offs.

If at any point the user says "defaults", "defaults are fine", "just go", "skip", or similar — stop the interview and use defaults for all remaining questions.

Question 1 — Audience:

Who is the primary audience for the plain-English version?

A) Executives/decision-makers — focus on "so what?" and strategic implications
B) Practitioners/operators — focus on "how do I use this?" with concrete examples
C) Smart generalist (grade 12 level) — focus on intuition and everyday analogies
D) All of the above — layered callouts serving all three
E) Custom — describe your audience

(Default: C)

Read the full file on GitHub · 300 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. 4d ago First seen · 300 lines · 16 tokens per session scan A 742d82b78f4e

Subscribe to this mod's changes

plain-english is a command published in the GitHub repository reggiechan74/cc-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 2,506 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 2026-08-31.