实用技巧

CLAUDE.md is the first thing loaded into context and guides all of Claude's behavior. Put it at the repo root. Every rule, convention, or piece of context you write there is applied automatically on every session.

Claude saves things between sessions in ~/.claude/projects/<slug>/memory/. You can ask it to remember facts, preferences, or decisions and it will retrieve them in future conversations automatically.

The Explore agent uses the cheaper and faster Haiku model (not your main model). For simple codebase searches, asking Claude to use the Explore agent saves tokens and money compared to the main model doing the same search.

When ~13,000 tokens remain before your context limit, Claude automatically forks an agent to summarize the conversation. You can run /compact manually before hitting the limit to get a cleaner, more controlled compression.

In auto permission mode, a 2-stage AI classifier blocks certain commands considered high-risk: curl, wget, ssh, git, kubectl, aws, and more. If you need these in auto mode, you must approve them manually or configure explicit allow rules.

Custom agents are defined in .md files with YAML frontmatter specifying tools, model, and permission mode. Claude loads them automatically. You can build specialized agents with restricted tool sets for safer, more focused tasks.

The built-in Verification Agent runs after implementations and always emits a structured verdict: PASS, FAIL, or PARTIAL. It appears in red in the terminal to stand out. This makes it useful as an automated quality gate in CI/CD workflows.