Everything the course teaches, in one place to look up rather than re-read.
| Command | What it does |
|---|
/clear | Start a new conversation in the same process; the previous session remains resumable |
/compact | Summarize the thread to reclaim tokens without losing the plot |
/context | Show what’s currently filling the context window |
/usage | Show token spend for this session |
/rewind | Restore or summarize an eligible checkpoint; it is not a Git replacement |
/init | Generate a starter CLAUDE.md by scanning the project |
/memory | View or edit the persistent memory file |
/model | Inspect or switch the active model by alias/full name |
/permissions | View and manage allow/deny rules for this session |
/btw | Ask a side-question in an overlay that never enters context |
/resume | Pick a previous session to continue |
/branch | Create a new conversation branch from the current session |
/effort | Set supported reasoning effort levels |
/fast | Toggle fast mode where supported |
/recap | Summarize the current session without compacting it |
/keybindings | Configure interactive keybindings |
| Flag | What it does |
|---|
--continue | Resume the most recent session in this directory |
--resume | Pick a past session to resume from a list |
-p | Run a single prompt headlessly and exit (no REPL) |
--output-format | Control headless output: text, json, stream-json |
--max-turns | Cap how many agentic turns a headless run may take |
--bare | Skip project auto-discovery such as CLAUDE.md, hooks, skills, plugins, and MCP |
--model | Set the model for this invocation without /model |
| Shortcut | What it does |
|---|
Shift+Tab | Cycle the modes available in the current configuration, normally default → acceptEdits → plan |
Escape | Interrupt the agent mid-response |
Ctrl+C | Cancel the current input or action |
| Mode | Behaviour |
|---|
default | Reads are free; every write or shell command asks for approval |
acceptEdits | File edits auto-approve; shell commands still ask |
auto | All actions auto-approve within configured allow rules |
dontAsk | Deny calls that would otherwise prompt; useful for unattended runs |
bypassPermissions | Skips normal permission checks; use only inside strong isolation |
| File | Purpose |
|---|
CLAUDE.md | Project instructions loaded at session start (rules, conventions, context) |
.claude/settings.json | Per-project permission rules, allowed/denied tools and paths |
.claude/skills/ | Reusable skill definitions the agent invokes by description match |
.claude/agents/ | Custom subagent definitions with their own model and permissions |
