--- title: Claude Skills: 10 Worth Installing and What Each Costs You description: A practical analysis measuring the hidden token cost of Claude Skills (MCP-style plugins). Based on a live 12-skill library, each skill description consumes... canonical: https://daily.dev/posts/claude-skills-10-worth-installing-and-what-each-costs-you-n8f928gwf twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Claude Skills: 10 Worth Installing and What Each Costs You | daily.dev og:description: A practical analysis measuring the hidden token cost of Claude Skills (MCP-style plugins). Based on a live 12-skill library, each skill description consumes... og:url: https://daily.dev/posts/claude-skills-10-worth-installing-and-what-each-costs-you-n8f928gwf og:image: https://api.daily.dev/og/posts/N8F928GWF.png og:image:alt: Claude Skills: 10 Worth Installing and What Each Costs You og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Claude Skills: 10 Worth Installing and What Each Costs You **[Noor Mohammad](https://daily.dev/sources/ew9hy5zthevyyefagop4g)** · [@noormohammad](https://daily.dev/noormohammad) · 1 min read · 0 upvotes · 1 comments ## Summary A practical analysis measuring the hidden token cost of Claude Skills (MCP-style plugins). Based on a live 12-skill library, each skill description consumes ~123 tokens on every message before you type anything. A table breaks down cumulative costs: 10 skills = 1,230 tokens, 50 = 6,150, 200 = 24,650 — roughly 12.3% of Claude's 200k context window. The post also challenges the claim that '200 skills cost nothing,' arguing it's misleading since skill descriptions are loaded into context on every request. ## Content Every Claude skills roundup lists what to install. None price it. So I measured a live 12-skill library: descriptions occupy **1,479 tokens on every message** before you type — avg 123/skill (range 26–239). Anthropic's docs say ~100, so we agree closely. The table the roundups are missing: 10 → 1,230 (0.6% of 200k) · 25 → 3,075 (1.5%) · 50 → 6,150 (3.1%) · 100 → 12,325 (6.2%) · 200 → 24,650 (12.3%) Also: the "200 skills cost nothing" claim is only true if you read it strictly (bodies stay on disk). Read normally, it's off by ~24,650 tokens. Free, no paywall. 🔗 [https://medium.com/@thebuildersplaybook/claude-skills-10-worth-installing-and-what-each-costs-you-c32e53d55000](https://medium.com/@thebuildersplaybook/claude-skills-10-worth-installing-and-what-each-costs-you-c32e53d55000) ## Community discussion Top comments from developers on daily.dev. **@noormohammad** · 0 upvotes > Two things in here I hadn't seen documented elsewhere: (1) skills don't sync across surfaces — [claude.ai](http://claude.ai), API, and Claude Code are three separate copies and the drift is yours to manage; (2) the pre-built document skills aren't managed built-ins in Claude Code, but _are_ installable from the anthropics/skills repo as a plugin, so both "already enabled" and "not available" roundups are wrong. > > Open question I couldn't answer: does a large library degrade Claude's _selection_ between similar skills? Everyone assumes yes; nobody's shown it. If you've measured, post the number. ## Similar posts on daily.dev - [I Tested 100 Claude Skills. Only 4 Were Worth Keeping](https://daily.dev/posts/i-tested-100-claude-skills-only-4-were-worth-keeping-m6nioo6w7) · Medium · 0 upvotes · 0 comments - [Claude Code Sends 4.7x More Tokens Than OpenCode Before Reading Your Prompt](https://daily.dev/posts/claude-code-sends-4-7x-more-tokens-than-opencode-before-reading-your-prompt-9m02iom1z) · Hacker News · 6 upvotes · 0 comments - [7 ways I make Claude Code use fewer tokens without hurting the results](https://daily.dev/posts/7-ways-i-make-claude-code-use-fewer-tokens-without-hurting-the-results-s1mmfwq7r) · XDA Developers · 1 upvotes · 0 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#claude](https://daily.dev/tags/claude) [View this post on daily.dev](https://daily.dev/posts/claude-skills-10-worth-installing-and-what-each-costs-you-n8f928gwf) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/claude-skills-10-worth-installing-and-what-each-costs-you-n8f928gwf","headline":"Claude Skills: 10 Worth Installing and What Each Costs You","text":"A practical analysis measuring the hidden token cost of Claude Skills (MCP-style plugins). Based on a live 12-skill library, each skill description consumes ~123 tokens on every message before you type anything. A table breaks down cumulative costs: 10 skills = 1,230 tokens, 50 = 6,150, 200 = 24,650 — roughly 12.3% of Claude's 200k context window. The post also challenges the claim that '200 skills cost nothing,' arguing it's misleading since skill descriptions are loaded into context on every request.","url":"https://daily.dev/posts/claude-skills-10-worth-installing-and-what-each-costs-you-n8f928gwf","datePublished":"2026-08-04T13:59:20.620Z","dateModified":"2026-09-13T21:16:27.761Z","author":{"@type":"Person","name":"Noor Mohammad","url":"https://daily.dev/noormohammad","image":"https://media.daily.dev/image/upload/s--3w4n0n-6--/f_auto/v1754054115/avatars/avatar_eW9hy5zTHEVyYeFaGOP4G?_a=BAMClqZW0","description":"Software Engineer | React, Next.js & scalable web apps | Writing on AI, blockchain & emerging tech","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":180}},"image":"https://media.daily.dev/image/upload/s--BPL-NyB7--/f_auto/v1785851982/posts/N8F928GWF?_a=BAMAMicg0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"comment":[{"@type":"Comment","text":"Two things in here I hadn’t seen documented elsewhere: (1) skills don’t sync across surfaces — claude.ai, API, and Claude Code are three separate copies and the drift is yours to manage; (2) the pre-built document skills aren’t managed built-ins in Claude Code, but are installable from the anthropics/skills repo as a plugin, so both “already enabled” and “not available” roundups are wrong.\nOpen question I couldn’t answer: does a large library degrade Claude’s selection between similar skills? Everyone assumes yes; nobody’s shown it. If you’ve measured, post the number.","datePublished":"2026-08-04T13:59:52.372Z","url":"https://daily.dev/posts/N8F928GWF#c-RvCgoVlgS","author":{"@type":"Person","name":"Noor Mohammad","url":"https://daily.dev/noormohammad","image":"https://media.daily.dev/image/upload/s--3w4n0n-6--/f_auto/v1754054115/avatars/avatar_eW9hy5zTHEVyYeFaGOP4G?_a=BAMClqZW0"}}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/sources/ew9hy5zthevyyefagop4g","name":"Noor Mohammad"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Noor Mohammad","item":"https://daily.dev/sources/ew9hy5zthevyyefagop4g"},{"@type":"ListItem","position":3,"name":"Claude Skills: 10 Worth Installing and What Each Costs You"}]} ```