---
title: "How to use Claude Code well: a first workflow | Bombos"
description: "Anthropic's advice: tell Claude what the repo cannot show, give it a check that passes or fails, enforce hard rules in config, and /clear between tasks."
image: "https://bombos.ai/assets/og-en-v2.png"
---

# How do I use Claude Code well? A first workflow that works

Short answer

Write a specific prompt, give Claude a check it can run (a test, a build, a linter) and ask for the output as evidence. Keep CLAUDE.md short and only for what the code cannot tell Claude. Put rules that may never be broken in deny rules or hooks, not in prose. Press Esc when it drifts, and after two failed corrections run /clear and write a better prompt.

*Piet Baudoin · published November 17, 2026 · November 17, 2026*

## A first workflow

Anthropic’s best-practices page, as of November 2026, comes down to four points: tell Claude what it cannot see, give it a check to run, enforce the rules that cannot have exceptions, and change a default only when a task costs too much. As a workflow for a real task:

1.  **Write a specific prompt.** Name the file, the symptom and what “fixed” means. Not “fix the login bug”, but “users report login fails after the session times out. Look at token refresh in src/auth/, write a failing test that reproduces it, then fix it.” Type `@` and a path to include a file, paste a screenshot, or pipe output in with `cat error.log | claude -p "what's going on here"`.
2.  **If you do not know exactly what you want yet, let Claude interview you.** “Interview me until you could write the spec, then write it to SPEC.md.” Then start a fresh session to build from that file, with a clean context and a written definition of done.
3.  **Give Claude a check.** A test file, a build, a linter, a script that compares output, a screenshot next to the mockup. In the prompt: “run the auth tests after, and keep going until they pass.”
4.  **Ask for evidence.** The command it ran and the output. “All tests pass” on its own tells you little.
5.  **Get a second pair of eyes.** `/code-review` reviews the diff in a fresh subagent that never saw your conversation. When you want a check against your plan, ask a subagent to compare the diff with SPEC.md and to skip style. More on the options in [Claude Code review](https://bombos.ai/en/questions/claude-code/claude-code-review/).
6.  **Commit, then `/clear`** before the next unrelated task.

If you want the fuller version of a feature, say “be ambitious”: Claude tends to build the smallest thing that satisfies a request, because it cannot see how much you hoped for.

## Steer in the first minute

Three controls are worth knowing by heart:

| Control | What it does |
| --- | --- |
| `Esc` | Stops Claude mid-action and keeps the work so far, so you can redirect |
| `/rewind` (or `Esc` twice on an empty prompt) | Rolls code, conversation or both back to an earlier prompt |
| `/clear` | Starts over; after two failed corrections, a fresh prompt that includes what you learned works better than a third correction |

`/btw` answers a quick side question without adding it to the history. `/rename oauth-migration` names a session so `claude --resume oauth-migration` picks it up days later.

## Where each instruction belongs

The page splits instructions in two. A prompt, `CLAUDE.md` or a skill is read by the model, which usually follows it but decides itself. A hook, a deny rule or a managed setting is applied by Claude Code every time.

-   **`CLAUDE.md`**: short, only what the repo does not show. Test and typecheck commands, code that misleads, decisions made outside the repo, things you had to correct twice. `/init` drafts one; then the work is mostly deleting lines. How it loads is on [Claude Code memory](https://bombos.ai/en/questions/claude-code/claude-code-memory/).
-   **`.claude/rules/`** with a `paths:` filter for rules that only matter in one part of the codebase.
-   **Skills** for team procedures such as a release. They only load fully when the task needs them. See [Claude Code skills](https://bombos.ai/en/questions/claude-code/claude-code-skills/).
-   **Hooks and deny rules** for what must always or never happen: never read `.env`, always run the formatter. See [Claude Code hooks](https://bombos.ai/en/questions/claude-code/claude-code-hooks/).

A sign from the docs: if you keep adding emphasis to a `CLAUDE.md` line and Claude still misses it, that line belongs in a hook.

## The misunderstanding: the old advice still applies

A lot of Claude Code advice online was written for older models. Anthropic’s page now has a table of things you can stop doing:

1.  **Managing the context window aggressively.** Most current models have a 1M-token window and compact on their own. `/clear` between tasks is still worth it, for focus and cost.
2.  **IMPORTANT or ALL CAPS.** Current models follow a plain line; emphasis makes Claude over-apply the rule.
3.  **“Think hard” in the prompt.** Effort is the control, through `/effort`.
4.  **Describing your architecture in `CLAUDE.md`.** Claude reads the repo itself.
5.  **Delegating to a subagent for a better answer.** Same model, same task. A fresh reviewer helps; plain delegation does not.

## What this means for a team

Most of what makes Claude Code work well is information only people have: decisions, procedures, the check that defines done. A short committed `CLAUDE.md`, shared skills and hooks in `.claude/settings.json` carry that to every developer. What they do not carry is what one developer’s session learned today, or what was decided in a thread outside the repo, until someone writes it down. For unattended runs, the same points apply more strictly: a definition of done, a check, limits on what it may touch, a cap on turns or spend, and a person who approves the result.

## Where Bombos fits

The best-practices page keeps returning to one gap: Claude cannot see what the team knows outside the code. Bombos is a plugin that gives Claude Code and the team’s other AI tools one shared memory with that knowledge, the rules the team learned, and what already lives in mail, documents and repos, each answer traceable to its source. One developer can try it on their own agents first.

## Related questions

Do I need to set anything up before my first prompt?

No. Anthropic's best-practices page says a plain first prompt in a fresh session usually does the right thing: sessions start in auto mode, Claude delegates to subagents on its own and compacts long conversations automatically. Setup pays off once the project has knowledge Claude cannot read from the code.

Should I write think hard or be thorough in my prompt?

It no longer raises how hard Claude thinks. Effort is the control: /effort high for tricky work, /effort low for quick back-and-forth. ultrathink in a single prompt asks for deeper reasoning on that one turn.

When should I use /clear and when /compact?

/clear between unrelated tasks, so the next task does not pay for the previous one's history. /compact with a focus, such as /compact keep the API changes, when you want to keep going but trim. /compact is itself a large request on a long session.

How do I undo what Claude just did?

/rewind, or Esc twice on an empty prompt, rolls back the code, the conversation or both to an earlier prompt. It covers files Claude edited with its own file tools, not changes made by Bash commands, so keep using git.

What should go in CLAUDE.md?

Only what Claude cannot find by reading the repo: the exact test and lint commands, misleading spots in the code, team decisions, and anything you corrected twice. /init writes a first version; the memory guide recommends staying under 200 lines.

## Sources

1.  [Claude Code docs: Best practices](https://code.claude.com/docs/en/best-practices)
2.  [Claude Code docs: Review locally with /code-review](https://code.claude.com/docs/en/code-review-local)
3.  [Claude Code docs: Run Claude Code programmatically](https://code.claude.com/docs/en/headless)

## What does your AI forget?

1.  01You tell us which AI you use and where it keeps starting over.
2.  02We show what a shared memory changes there, on your own examples.
3.  03You keep the plan, with or without Bombos.

![Piet Baudoin](https://bombos.ai/assets/team/piet-klein.jpg)

**Piet Baudoin**You talk to Piet, from the Bombos teamDutch team from Utrecht and Nijmegen · data in Europe

## More questions about Claude Code

-   [How do I use Claude Code in VS Code and JetBrains?](https://bombos.ai/en/questions/claude-code/claude-code-in-vs-code-and-jetbrains/)
-   [What is Claude Code Remote Control and how do I use it?](https://bombos.ai/en/questions/claude-code/claude-code-remote-control/)
-   [What is auto mode in Claude Code, and is it safe to use?](https://bombos.ai/en/questions/claude-code/claude-code-auto-mode/)
-   [How do I use Claude Code with GitHub, and @claude in pull requests?](https://bombos.ai/en/questions/claude-code/claude-code-github-actions/)
-   [What is Claude Code Router and should a team use it?](https://bombos.ai/en/questions/claude-code/claude-code-router/)
-   [Is Claude Code safe to use on company code?](https://bombos.ai/en/questions/claude-code/is-claude-code-safe-for-company-code/)
-   [OpenCode vs Claude Code: which coding agent should I use?](https://bombos.ai/en/questions/claude-code/opencode-vs-claude-code/)
-   [What are agent teams in Claude Code and how do you turn them on?](https://bombos.ai/en/questions/claude-code/claude-code-agent-teams/)

[All questions about Claude Code →](https://bombos.ai/en/questions/claude-code/)


---

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","url":"https://bombos.ai/","logo":"https://bombos.ai/assets/bombos-bee.png","description":"Bombos is the memory layer under every AI your team uses. One shared memory for Claude, ChatGPT, Copilot, Cursor and your own agents, that learns how you work.","sameAs":["https://www.linkedin.com/company/bombos-ai","https://www.youtube.com/@truebombos","https://www.instagram.com/truebombos/","https://bsky.app/profile/bombostrue.bsky.social","https://www.threads.com/@truebombos","https://mastodon.social/@Bombos","https://www.tiktok.com/@truebombos","https://t.me/truebombos","https://www.pinterest.com/truebombos/","https://github.com/bombos-ai","https://linktr.ee/bombos.ai","https://bombosai.substack.com","https://hashnode.com/@bombosai","https://hackernoon.com/u/bombos","https://dev.to/bombos"],"email":"info@bombos.ai","areaServed":["NL","Europe"],"knowsLanguage":["nl","en"],"contactPoint":{"@type":"ContactPoint","email":"info@bombos.ai","contactType":"sales","url":"https://bombos.ai/en/contact/","availableLanguage":["nl","en"]}},{"@type":"WebSite","@id":"https://bombos.ai/#website","name":"Bombos","url":"https://bombos.ai/","inLanguage":["nl-NL","en"],"publisher":{"@id":"https://bombos.ai/#organization"}}]}

{"@context":"https://schema.org","@type":"Article","headline":"How do I use Claude Code well? A first workflow that works","description":"Anthropic's advice: tell Claude what the repo cannot show, give it a check that passes or fails, enforce hard rules in config, and /clear between tasks.","abstract":"Write a specific prompt, give Claude a check it can run (a test, a build, a linter) and ask for the output as evidence. Keep CLAUDE.md short and only for what the code cannot tell Claude. Put rules that may never be broken in deny rules or hooks, not in prose. Press Esc when it drifts, and after two failed corrections run /clear and write a better prompt.","datePublished":"2026-11-17T00:00:00.000Z","dateModified":"2026-11-17T00:00:00.000Z","author":{"@type":"Person","name":"Piet Baudoin"},"publisher":{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","logo":{"@type":"ImageObject","url":"https://bombos.ai/assets/bombos-bee.png"}},"image":"https://bombos.ai/assets/og-en-v2.png","mainEntityOfPage":"https://bombos.ai/en/questions/claude-code/how-to-use-claude-code-well/","inLanguage":"en-US","isPartOf":{"@type":"CollectionPage","name":"Claude Code","url":"https://bombos.ai/en/questions/claude-code/"},"citation":[{"@type":"CreativeWork","name":"Claude Code docs: Best practices","url":"https://code.claude.com/docs/en/best-practices"},{"@type":"CreativeWork","name":"Claude Code docs: Review locally with /code-review","url":"https://code.claude.com/docs/en/code-review-local"},{"@type":"CreativeWork","name":"Claude Code docs: Run Claude Code programmatically","url":"https://code.claude.com/docs/en/headless"}]}

{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Bombos","item":"https://bombos.ai/en/"},{"@type":"ListItem","position":2,"name":"Questions","item":"https://bombos.ai/en/questions/"},{"@type":"ListItem","position":3,"name":"Claude Code","item":"https://bombos.ai/en/questions/claude-code/"},{"@type":"ListItem","position":4,"name":"How do I use Claude Code well? A first workflow that works","item":"https://bombos.ai/en/questions/claude-code/how-to-use-claude-code-well/"}]}

{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Do I need to set anything up before my first prompt?","acceptedAnswer":{"@type":"Answer","text":"No. Anthropic's best-practices page says a plain first prompt in a fresh session usually does the right thing: sessions start in auto mode, Claude delegates to subagents on its own and compacts long conversations automatically. Setup pays off once the project has knowledge Claude cannot read from the code."}},{"@type":"Question","name":"Should I write think hard or be thorough in my prompt?","acceptedAnswer":{"@type":"Answer","text":"It no longer raises how hard Claude thinks. Effort is the control: /effort high for tricky work, /effort low for quick back-and-forth. ultrathink in a single prompt asks for deeper reasoning on that one turn."}},{"@type":"Question","name":"When should I use /clear and when /compact?","acceptedAnswer":{"@type":"Answer","text":"/clear between unrelated tasks, so the next task does not pay for the previous one's history. /compact with a focus, such as /compact keep the API changes, when you want to keep going but trim. /compact is itself a large request on a long session."}},{"@type":"Question","name":"How do I undo what Claude just did?","acceptedAnswer":{"@type":"Answer","text":"/rewind, or Esc twice on an empty prompt, rolls back the code, the conversation or both to an earlier prompt. It covers files Claude edited with its own file tools, not changes made by Bash commands, so keep using git."}},{"@type":"Question","name":"What should go in CLAUDE.md?","acceptedAnswer":{"@type":"Answer","text":"Only what Claude cannot find by reading the repo: the exact test and lint commands, misleading spots in the code, team decisions, and anything you corrected twice. /init writes a first version; the memory guide recommends staying under 200 lines."}}]}
```
