Watch the video with chapters & transcript →
AI TOOLS
In short: Anthropic's newly published Claude Code best-practices documentation surfaced at least five mistakes even a working consultant was making daily.
Claude Code ships with safe defaults, and most people never change them — which means they work slower than necessary. After reading Anthropic's new best-practices documentation end to end, Ani Björkström, a tech consultant based in Stockholm, found at least five things she had been doing wrong and distilled them into these five fixes.
Either bypass all prompts with the dangerously-skip-permissions option, or — the safer route — explicitly allow the actions you trust: edits to files, git commands, and running tests. By default Claude asks before writing files, committing to git, running bash commands, or using MCP tools — deliberate for safety, but it slows you down massively across a session.
Skills extend Claude's knowledge with information specific to your project; subagents offload tasks into separate context windows. A skill is a named file holding domain knowledge — for example API conventions like "kebab-case for URL paths, camelCase for JSON properties, always include pagination for list endpoints" — applied automatically when relevant or invoked with a forward slash and the skill name.
Subagents matter because the main agent's context window is limited. A subagent runs with its own context and tools — the documentation's example defines a "security reviewer" on the Opus model, instructed as a senior security engineer to check injection vulnerabilities, authentication and authorization flows, secrets in code, and insecure data handling — so delegated tasks stop cluttering the main conversation.
Because Claude asks about things you have not considered yet: technical implementation, UI/UX, edge cases, and trade-offs. Instead of writing a long specification, start with a minimal prompt — "I want to build a LinkedIn scraping tool, interview me in detail using the AskUserQuestion tool" — and answer its questions.
The interview often surfaces features you had not considered, forcing real product planning before any code exists. That is cheaper than discovering the missing requirement after the build.
Press ESC to stop Claude mid-action while keeping your context — useful when you return and find it has been grinding on the same task for hours. Dedicated controls then let you rewind, undo, or reset.
| Situation | Action in Claude Code |
|---|---|
| Claude is stuck mid-task | Press ESC once to stop the action and keep your context |
| You want to go a few steps back | Press the ESC key twice to rewind |
| Claude made a change you dislike | Run /undo to reverse the last change |
| Starting an unrelated task | Run /clear to reset the context window |
The skip-permissions flag is explicitly labeled dangerous, so the better default is targeted allowances: file edits, git commands, and test runs. You keep most of the speed while Claude still asks before anything else.
For small, well-defined tasks like a security review, since each subagent runs in its own context window with its own tools and model. That keeps the main agent's limited context available longer.
Use /undo to reverse the last change, or press ESC twice to rewind a few steps. For a fresh start between tasks, /clear resets the context window entirely.
Read the full video transcript, with chapters, on the video page →
Want this working inside your finance team?