Skip to content
Mia Automation
NLEN Sign in Put Mia to workGet started

Claude Skills vs. MCP vs. Plugins vs. Subagents: Which One for Which Job

Use a skill for know-how Claude Code needs now and then, and CLAUDE.md for the few facts it needs every time. Add an MCP server when it has to reach another system, a subagent when work should happen in a separate context, and a plugin to package any of those for others. The numbers behind the first choice: we gave Claude Code the same 4,500-word style guide as a skill and as CLAUDE.md. As a skill it cost 60 tokens in a session that didn't need it; in CLAUDE.md it cost 8,825 tokens every time. Both produced the right result when the guide mattered.

Claude in practiceUpdated 7 min read

Tested by us on 11 November 2026.

The short answer

SkillCLAUDE.mdMCP serverSubagentPlugin
What it isA SKILL.md with instructions, loaded when relevant or with /nameA file Claude Code reads at the start of every sessionA connection that gives Claude Code tools for another systemA helper with its own context window and instructionsA package of skills, subagents, hooks and MCP servers
Costs contextIts description, until usedAll of it, every sessionTool names; tool search is on by defaultOnly its summary in your sessionThe descriptions of everything inside it
Use it forProcedures and reference you need sometimesShort rules that always applyReading or changing data elsewhere: GitHub, a database, DriveSide work whose output you don't want in your sessionSharing a setup with a team or across projects
Not forRules that must hold every timeLong reference materialKnow-how without an outside systemQuick tasks, or work that needs back-and-forthA single file you could copy

Pick a skill for know-how Claude Code needs some of the time, and CLAUDE.md for short rules that always apply. Pick MCP to reach another system, a subagent to keep side work out of your session, and a plugin to hand all of it to someone else.

Animated bar chart of context for an unrelated task: 18,712 tokens with nothing added, 18,772 with the guide as a skill, 18,917 with a 14-tool MCP server and tool search on, 27,537 with the guide in CLAUDE.md and 37,707 with the MCP server and tool search off; the related task with the skill loaded reached 28,135
Context cost of each building block. The skill and the MCP server only take real space when they're used, or when tool search is off.

How we tested it

We wrote a 4,500-word invoice style guide: 120 general wording rules and one exact rule for the due-date line, "Please pay by <date>, quoting invoice <number>." We put it in three empty Python projects. One had it as CLAUDE.md, one as a skill in .claude/skills/invoice-style/SKILL.md with a two-sentence description, and one had no guide. Each project got two tasks in a fresh Claude Code 2.1.321 session: an unrelated one ("How many lines does tools.py have?") and a related one ("Add a function due_line(number, date)"). We read the token counts from the session logs and ran the function ourselves. We repeated the related task with the skill two more times, and added a fourth project with an MCP server. All tests ran on Ubuntu; the screenshots were rendered on a Windows PC.

November 11, 2026. Cost as reported by Claude Code at API rates. One run per cell, except the skill on the related task: three runs.
SetupUnrelated task: context, costRelated task: guide used?Due-date line produced
No guide18,712 tokens, $0.028No"Invoice 2026-0042 is due on 14 December 2026." (wrong wording)
Guide as a skill18,772 tokens, $0.028Yes, loaded by Claude Code itself in 3 of 3 runs"Please pay by 14 December 2026, quoting invoice 2026-0042." (3 of 3)
Guide in CLAUDE.md27,537 tokens, $0.064Yes, it was already loaded"Please pay by 14 December 2026, quoting invoice 2026-0042."
MCP filesystem server (14 tools), tool search on18,917 tokens, $0.029Not applicableNot applicable
Same MCP server, tool search off37,707 tokens, $0.157Not applicableNot applicable
Three terminal panels: without the guide the function prints Invoice 2026-0042 is due on 14 December 2026; with the skill, whose tool list starts with Skill invoice-style, and with CLAUDE.md, it prints Please pay by 14 December 2026, quoting invoice 2026-0042 (opens at full size)
The related task in all three projects: which tools Claude Code used, and what the function it wrote returns.

What the numbers mean

Context. A skill's description was all that sat in context until the task called for it: 60 extra tokens. The same text in CLAUDE.md added 8,825 tokens to every session, related or not, and more than doubled the cost of the unrelated task, from $0.028 to $0.064. At 50 short sessions a day, that is about 440,000 tokens spent on a guide most of those sessions never needed.

Reliability. Here both worked. Claude Code matched the request to the skill's description and loaded it on its own. That depends on the description: Anthropic's docs say descriptions are cut at 1,536 characters in the skill list, so put the trigger words first. A rule that must hold in every session, like how money is rounded, belongs in CLAUDE.md, where Claude Code can't skip loading it.

Commands. Custom commands in .claude/commands/ and skills now create the same /name, according to the docs, and existing command files keep working. A skill adds a folder for supporting files and lets Claude Code load it without being asked. For anything new, we write a skill.

Where MCP, subagents and plugins fit

MCP is about reach, not knowledge. An MCP server adds tools: read issues on GitHub, query a database, open a file in Drive. You add one with claude mcp add, at local, project or user scope. We connected the official filesystem server, which brings 14 tools. With tool search on, the default, it added 205 tokens to an unrelated task. With ENABLE_TOOL_SEARCH=false it added 18,995 and the task cost $0.157 instead of $0.028. A skill can tell Claude Code how to use such tools well, so the two often go together.

Subagents are about where work happens. In our subagent tests a separate context shrank the main conversation by 8% at best on two small tasks, while sessions cost 1.6 to 2.4 times as much. A reviewer subagent with a fresh context did find two planted bugs. A skill can also run in its own subagent context with context: fork in its frontmatter.

Plugins are about distribution. Skills, subagents, hooks and MCP servers all work without a plugin. A plugin bundles them so a team can install one unit from a marketplace and get updates. The docs warn that every enabled plugin adds its skill and agent descriptions to every session, so turn off plugins you don't use.

What we use ourselves

Our main instruction file holds about twenty hard rules, each with a date and a reason. Everything else lives in 96 skills, from code review to writing checks. The instruction file only names the kinds of skills in a few lines, and the skills load themselves on their descriptions. The weak spot is the description. Some third-party skills come with long descriptions that crowd the list, so a small script shortens them back to two sentences, trigger words first, after every update. For the rules side, see our CLAUDE.md guide.

Questions

What is the difference between Claude skills and MCP?

A skill is know-how: instructions Claude Code loads when a task needs them. MCP is reach: a server that gives Claude Code tools for another system. Use a skill to teach how, MCP to give access.

Should I use a skill or CLAUDE.md?

CLAUDE.md for short rules that apply every time; a skill for longer procedures or reference that only some tasks need. In our test the same guide cost 8,825 tokens per session in CLAUDE.md and 60 as a skill.

Are slash commands the same as skills now?

According to Claude Code's docs, custom commands have been merged into skills: a file in .claude/commands/ and a skill in .claude/skills/ both create the same /name. Skills can also be loaded by Claude Code on its own.

Do I need a plugin to use skills?

No. Save a skill in .claude/skills/ in your project or ~/.claude/skills/ for all projects. Plugins are for packaging and sharing. We have no paid relationship with any of the tool makers mentioned here.

Sources