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 surendranb/writing-skills --skill plain-languagegit clone --depth 1 https://github.com/surendranb/writing-skillsWrote 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/surendranb/writing-skills/plain-language)<a href="https://agentmods.dev/skills/surendranb/writing-skills/plain-language"><img src="https://agentmods.dev/badge/skills/surendranb/writing-skills/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/surendranb/writing-skills/plain-language"><img src="https://agentmods.dev/badge/skills/surendranb/writing-skills/plain-language.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00710 |
| Opus 5 | $0.00032 | $0.00355 |
| Sonnet 5 | $0.00013 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plain Language
Clear, direct, useful. The reader gets it on one read.
The core rule
Write so your reader can find, understand, and use what they need on the first read. Plain language is not dumbing down — it is removing obstacles: wordiness, passive construction, jargon, and buried logic.
Workflow: decide who the reader is and what they must do → front-load the key point → cut every word that is not doing work → run the verification checklist.
Mechanics
- Front-load the point. First sentence states the purpose, conclusion, or action. No throat-clearing.
- Short sentences. Average 15–20 words; hard cap ~25. One idea per sentence.
- Active voice. Subject acts: "The team shipped the fix" not "The fix was shipped by the team." Reserve passive for when the actor is truly unknown or irrelevant.
- Common words. Plain terms over Latinates: "use" not "utilize", "end" not "terminate", "ask" not "request".
- Actionable verbs. Name the action: "we will refund you" not "a refund will be issued".
- You, not we/them. Address the reader directly where appropriate ("you must renew your license").
- Short paragraphs. One topic per paragraph; 3–5 sentences max.
- No jargon, no abbreviations without explanation. If a term is unavoidable, define it the first time in plain words.
- Headers that work. Headings answer questions or state outcomes ("How to apply", "What happens next").
Verify
- Every sentence ≤ 25 words (longest sentence check)
- First two sentences state the point and the action
- No passive-voice hits above ~10% of sentences (search "was/were + past participle")
- No words from the jargon list: utilize, leverage, facilitate, commence, pursuant to, aforementioned, henceforth, in the event that, with regard to
- Flesch Reading Ease ≥ 60 (aim 65–75)
- Read aloud: could the intended reader follow once?
Do not
- Sacrifice precision for brevity where a term is legally or technically load-bearing
- Leave definitions out — plain language defines, it never assumes
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.
- 9d ago First seen · 50 lines · 64 tokens per session scan A ae06cfcfa173
plain-language is a skill published in the GitHub repository surendranb/writing-skills (31 stars, last pushed 7d ago), licensed MIT. It adds 64 tokens to every session and 710 once invoked, about $0.0003 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.
Other skills, from other repositories
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
schema-markup-generator
Generate JSON-LD structured data markup for rich results in Google Search. Supports FAQ, HowTo, Article, Product, LocalBusiness, and multi-type schemas. Validates against Google requirements and provides implementation guidance. Use when asked to "add schema markup", "generate structured data", "JSON-LD", "rich…
google-ads-landing
Score and diagnose Google Ads landing pages. Use when asked to audit a landing page, check landing page quality, diagnose high-CTR but low-conversion-rate ad groups, improve Quality Score's Landing Page Experience component, or compare an ad group's messaging against its landing page. Trigger on "landing page audit"…
content-planner
GSC-driven content calendar. Pulls real Search Console data, finds the highest click-potential opportunities (striking-distance queries at positions 5-20, unanswered query intent, related-keyword expansions), and produces a dated, prioritized content calendar — ready to hand to /content-writer. Use when the user asks…
keyword-research
Discover, analyze, and prioritize keywords for SEO and GEO content strategies from a seed keyword or niche. Identifies high-value opportunities based on search volume, competition, intent, and business relevance. Generates topic clusters. For building a dated editorial calendar from your own Search Console data, use…
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…