Glossary · Phase 10 · Agent harnesses
CLAUDE.md
A project instructions file a coding agent loads at the start of every session: build commands, conventions and things to avoid.
Try it now
The list makes the model plan, survives compaction, and lets you spot a bad plan early.
Learn it properly
Memory, plans and long tasks · To-do lists, progress notes, memory files and checkpoints. About 40 minutes.
Other terms from the same lesson
- memory poisoning: An injected instruction saved into an agent's memory, where it comes back in later sessions.
- memory tool: A Claude API tool the model uses to view and edit files under /memories. Your harness carries out each command.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.