Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
Practice needs JavaScript. The reading works without it.Back to the reading
Slash commands control Claude Code from inside a session: switching models, managing permissions, clearing context, running a workflow. Type / to open the list and a few letters to filter it.
Three small rules people often trip over:
- A command only counts at the start of a message.
/compactin the middle of a sentence is just text. - Whatever follows the command name is its arguments, as in
/code-review high 1234. - If you send a command while Claude is replying, it is queued and runs when the current turn ends. A few, such as
/status,/tasksand/usage, run immediately without interrupting.
The list holds two kinds. Built-in commands such as /clear and /context run fixed logic inside the CLI. Bundled skills such as /code-review, /doctor and /debug are different: they are a detailed prompt handed to Claude, which then uses its tools to do the work. The docs' commands table marks the second kind as Skill. The distinction matters in lesson 3.2, when you write your own commands: those are skills too.
The first time you work in a repo, four commands set things up for every later session:
/initwrites a startingCLAUDE.md, as in lesson 2.2./memoryopens the memory files so you can trim them./mcpsets up and manages the MCP servers the project needs (level 5)./permissionssets rules for which tools are allowed or ask first.
For todo-api, you did the first two in level 2. The other two come back in later levels.
These are the commands you'll use most:
/planswitches into plan mode before a big change: Claude researches and proposes, and changes nothing until you approve (lesson 1.3)./modeland/effortchange the model and how much reasoning Claude puts in. This is the real control for "think harder", not typing those words into a prompt (lesson 1.2)./contextshows what's filling the context window. When a session has run long and answers slow down, look at/contextbefore guessing./compactsummarises the conversation to free space. The project-rootCLAUDE.mdis re-read after compaction (lesson 2.2)./btwasks a side question without adding it to the conversation history. Fixing an endpoint and suddenly want to check some JavaScript syntax? Ask with/btwso the main task stays focused.
When Claude says it's done, don't commit straight away. Three commands help you check:
/diffshows what changed. This is where the three diff-reading questions from lesson 1.3 come in./code-reviewchecks the current diff for correctness bugs. Add--fixto have Claude apply the findings. Pass a PR number, such as/code-review high 1234, to review a pull request instead of the local diff./reviewis another name for the same command./code-review ultraruns a multi-agent review in the cloud for large changes./security-reviewchecks the diff for security vulnerabilities.
Remember from lesson 1.2: /code-review runs in a fresh subagent that hasn't seen your conversation, so it isn't swayed by the reasoning that produced the code. That independent look catches mistakes the author tends to miss.
A normal day strings several tasks together. Four commands keep the hand-offs clean:
/clearstarts a new task with a clean context while keeping project memory. A good habit is/clearwhenever you move to something unrelated.Why bother, when current models have large context windows and compaction happens on its own? Because running out of space isn't the point. A focused context gets you better answers and costs less: Claude isn't rereading a morning's worth of unrelated work on every turn, and nothing from the previous task leaks into the next one.
/resumereturns to an earlier conversation./branchbranches the current conversation so you can try another direction without losing this one./forkcopies the conversation into a new background session, leaving this one free for something else.
And /tasks lists the session's background work, including subagents that have finished. Level 4 uses it a lot.
/rewindrolls code and conversation back to a checkpoint, or summarises part of a conversation that has gone stale (lessons 1.2 and 1.3)./doctorchecks your installation and configuration, diagnoses problems and can fix them. In level 2 you saw it suggest cuts toCLAUDE.md./debugdiagnoses problems that happen at runtime./feedbackreports a bug to Anthropic with the session's context attached.
A day on todo-api touches nearly every group: /plan in the morning for the restore endpoint, /btw for a side question and /context as the session grows, /diff and /code-review in the afternoon before committing, and /clear before the next task.
Next lesson: when you keep typing the same instructions, it's time to turn them into a slash command of your own.