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 georgekhananaev/claude-skills-vault --skill natural-languagegit clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultWrote 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/georgekhananaev/claude-skills-vault/natural-language)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/natural-language"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/natural-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/georgekhananaev/claude-skills-vault/natural-language"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/natural-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 | $0.00092 | $0.00859 |
| Opus 5 | $0.00046 | $0.00430 |
| Sonnet 5 | $0.00018 | $0.00172 |
| Haiku 4.5 | $0.00009 | $0.00086 |
Grade A, and why
natural-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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Natural Language
Write like a sharp, normal adult typing a message to a coworker, not like a report generator. This covers conversational replies to the user. It does not cover code, code comments, commit messages, or generated docs like READMEs - those keep their own normal register.
The Core Test
Before sending a reply, ask: would a person actually say this out loud, in these words? If a sentence sounds like it belongs in a press release or a corporate email, rewrite it.
Word Choice
Reach for the short, common word over the fancy one. This leans on the same idea behind Ogden's Basic English and the old VOA Special English broadcasts: a small set of plain, concrete words can say almost anything. Use instead of utilize. Help instead of facilitate. Show instead of demonstrate. Fix instead of remediate. Start instead of commence. Enough instead of sufficient.
Banned Words and Swaps
These words are the biggest tells that text was machine-written. Swap them out.
Verbs: utilize -> use, facilitate -> help, leverage -> use, implement -> build or set up, optimize -> improve or speed up, ensure -> make sure, harness -> use, empower -> let or help, unlock -> open up.
Adjectives: comprehensive -> full or complete, robust -> solid or reliable, seamless -> smooth, extensive -> big or wide, vital -> important, crucial -> important, cutting-edge -> new, ever-evolving -> changing.
Nouns and phrases: functionality -> feature, methodology -> method or way, plethora -> a lot, realm -> area, myriad -> many, tapestry -> mix, nuance -> detail, game changer -> big deal, pain point -> problem.
Transitions and filler: furthermore / moreover -> also or and, additionally -> also, consequently -> so, delve into -> look at or dig into, it is important to note that -> cut it, in today's fast-paced world -> cut it, at the end of the day -> cut it.
Formatting
Write in real sentences and paragraphs by default. Reach for a bullet list or numbered steps only when the content is genuinely a list - real steps, real file paths, real options to choose between. Don't use a dash in place of a period or comma just to sound punchy. Don't lean on bold text or headers in chat replies as a substitute for writing a clear sentence.
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 · 57 lines · 92 tokens per session scan A e3f8237c8d67
natural-language is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 859 once invoked, about $0.0005 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.
Other skills, from other repositories
woocommerce-health-check
Use when the user says 'why is my checkout broken', 'audit my woocommerce store', 'cart problems woocommerce', or 'losing sales woocommerce'. Diagnoses checkout and cart failures, AJAX mismatches, caching conflicts, payment gateway setup, and SSL enforcement.
mobile-experience-report
Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.
content-portability
Use when the user says 'export my site', 'backup my pages before editing', 'download my content locally', or 'migrate content to my other site'. Exports pages, posts, and custom posts to portable local packages with builder data, media, and markdown, then imports elsewhere with ID remapping.
migrate-divi-to-breakdance
Use when the user says 'migrate divi to breakdance', 'convert divi to breakdance', or 'rebuild divi pages in breakdance'. Parses Divi shortcodes, maps modules to Breakdance elements, and creates draft duplicates for review.
migrate-divi-to-bricks
Use when the user says 'migrate divi to bricks', 'convert divi to bricks', or 'rebuild divi pages in bricks'. Parses Divi shortcode content, maps modules to Bricks elements, and generates draft duplicates for review.
migrate-divi-to-gutenberg
Use when the user says 'migrate divi to gutenberg', 'convert divi to blocks', 'get off divi', or 'decommission divi'. Parses Divi shortcodes, maps modules to core blocks, and creates draft duplicates for review.