Claude Code skills: how they load, what a big catalog costs, and which ones to keep A developer tested how Claude Code and Codex CLI load skills, finding that the cost of a large skill catalog comes from every installed skill occupying a slot in the always-loaded list on every turn, with least-used skills losing their descriptions once the list exceeds its budget. The tests, run by a Claude Opus 5.5 agent session on Claude Code 2.1.312 and Codex CLI 0.160.1, also surfaced that Codex loads skills from an undocumented ~/.codex/skills folder. The author recommends keeping a few short, self-written skills and reviewing third-party skills like code before installing them. A skill is a folder with a SKILL.md file that Claude Code or Codex loads when your task matches its description. Write one when you catch yourself pasting the same procedure into the chat a third time, and keep it short. The cost sits in the catalog, not in the single skill: every installed skill takes a place in the list on every turn, many never run, and once the list outgrows its budget the least-used ones lose their descriptions. Keep a few short skills of your own, and read anyone else's like code before it goes on your machine. Who ran the tests. An agent procedure ran everything measured below, not me. On 2026-11-02 a Claude Code session Claude Opus 5.5 drove the shell on my Mac, with my own skill catalog installed, using Claude Code 2.1.312 and Codex CLI 0.160.1 model gpt-6.1-sol , reasoning effort medium . Each prompt ran once per condition in a fresh headless session through my subscriptions, so the counts show what happened, not a rate. Documented behavior is marked as documented. Claude Code's docs and changelog were rechecked on 2026-11-18 against release 2.1.327, the latest at the time of writing; the tests were not rerun. The prompts, scripts and results are in our evidence archive. My rule: a skill is for a procedure you repeat. A fact belongs in the instruction file, so CLAUDE.md and AGENTS.md https://actuallyshipped.com/en/articles/claude-md-agents-md/ is the place for what the project is. Once a section there has grown into numbered steps that only matter on some tasks, it is a skill, because a skill's body is read only when it is used. | You want | Use | Why | |---|---|---| | A procedure Claude should follow when the task matches | Skill | Only its name and description are always loaded; the body loads on use | | A fact about the project, true on every task | CLAUDE.md or AGENTS.md | Read at the start of every session | | A rule that must hold every time | Hook | Runs on the event whether or not Claude remembers documented | | Work in a separate context, with a report back | Subagent | Keeps the noise out of your main conversation | The hook row matters more than it looks. The docs say it directly: if Claude skips a rule that must hold every time, move the rule into a hook, which a skill can define in its own frontmatter. Our hook recipes https://actuallyshipped.com/en/articles/claude-code-hooks/ show what a hook does and does not block. Custom slash commands no longer compete with skills. Per the docs they are merged: .claude/commands/deploy.md and .claude/skills/deploy/SKILL.md both give you /deploy . The format is the same in both because it is an open standard. Anthropic handed it to the Agentic AI Foundation https://actuallyshipped.com/en/news/agent-skills-moves-to-the-agentic-ai-foundation/ on 2026-10-22, so one SKILL.md can serve both tools. The portable core, a name, a description and a body, works in both; the folders, the way you call a skill and some fields differ. | | Claude Code | Codex | |---|---|---| | Personal | ~/.claude/skills/