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.
npx skills add pandysp/claude-plugins --skill plain-languagegit clone --depth 1 https://github.com/pandysp/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/pandysp/claude-plugins/plain-language)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/plain-language"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/plain-language/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.
<a href="https://agentmods.dev/skills/pandysp/claude-plugins/plain-language"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/plain-language.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00131 | $0.01389 |
| Opus 5.5 | $0.00052 | $0.00556 |
| Sonnet 5.5 | $0.00026 | $0.00278 |
| Haiku 4.5 | $0.00013 | $0.00139 |
Grade A, and why
plain-language 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plain language: explain the problem behind the problem
Write as if the reader has no idea what you are talking about, but is smart. They follow any reasoning you give, but they share none of your context: the names you made up, what you found, what you tried. This holds for every reader, even an expert or someone who was there the whole time. An expert still knows their field. They don't know your task.
The bar: a smart reader who missed the whole conversation would understand it on first read and could explain it to someone else.
1. Find the problem behind the problem
When you write about a problem or a decision, the symptom you can see is rarely what the reader needs. Before you write, dig in two directions:
- Up: so what? Keep asking until you reach something the reader notices, loses or pays for. This is why it matters.
- Down: why does it happen? Keep asking until you reach the cause. The cause tells the reader where to act.
How it works step by step is the part you know best and the reader needs least. Explain it only as far as the reader needs to believe the consequence or act on it.
Stop digging when the next answer would not change what the reader understands or does. If you have not found the consequence or the cause, say so instead of presenting the symptom as the explanation.
- Symptom only: "The login test fails sometimes."
- So what: "The team now reruns failing tests until they pass, so a real login bug would get through unnoticed."
- Why: "Two tests share one test account. When they run at the same time, one logs the other out."
Explain it out loud first. Before you write a document, explain the matter as if you were answering the reader in a chat: what happens, and why that matters Then write the document with those words. Text written straight from your working notes tends to retell what you did instead of what goes wrong.
2. Write for what this reader cares about
- Work out what the reader is responsible for and what they care about, and use that to decide what to say. Your own situation is evidence, not the argument: a maintainer cares what breaks in their project, not what breaks in yours.
- Open with what the reader needs first: what this is about and, if you want something, the request and what it is for. Then what it means for the reader, then the cause. Then the details. If what you ask for can be done in several ways, leave how to the reader and offer yours as an example, unless they asked you to choose.
- For a decision, give every option worth considering, with what it costs and what it gets, so the reader can choose without asking back.
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.
- 22d ago Changed · +2 lines a5b3e93d38de
- 23d ago Changed · +2 lines d08316afb248
- 25d ago First seen · 74 lines · 131 tokens per session scan A 4aa98dea1278
plain-language is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 131 tokens to every session and 1,389 once invoked, about $0.0005 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 2026-10-03.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.