Claude Code

Entwicklungsaufgaben, Projektkontext und überprüfbare Ergebnisse mit Claude Code.

Claude Code

Hier anfangen: A CLAUDE.md that actually gets followed Englisch

API- und Coding-Agent-Schritte in einer geprüften Pipeline ausführen Benötigt: Gemini API + Claude Code + Codex + OpenAI API
Direkte Modellaufrufe mit CLI-Schritten verbinden, Anfragegrenzen prüfen und unklare Ergebnisse vor weiteren Aufrufen abgleichen.
CLI-Schritte zwischen menschlichen Entscheidungen ausführen Benötigt: Claude Code + Codex + Gemini CLI
Claude Code, Codex und Gemini CLI konfigurieren, das Ausführungsprofil prüfen und freigegebene Schritte vom lokalen Koordinator starten und überwachen lassen.
A CLAUDE.md that actually gets followed Englisch Claude Code
It is read every session, so every line is a recurring cost. Facts belong here; procedures belong in a skill.
Why context management is most of the skill Englisch Claude Code
Anthropic says most of their own best practices descend from one constraint. Knowing what each action costs turns that from advice into arithmetic.
The first hour with Claude Code Englisch Claude Code
What to do, in order, so the first session teaches you something useful rather than either disappointing you or impressing you into overconfidence.
Git hygiene with an agent in the loop Englisch Claude Code
Checkpoints look like undo and have five documented holes, including anything done by a bash command. Git is what covers them.
Hooks: the part of the loop the model cannot skip Englisch Claude Code
Instructions are requests a model probably honours. A hook is code that runs at a lifecycle point whether the model would have chosen to or not.
Large refactors: scoping work an agent can hold Englisch Claude Code
The unit of work is however much fits in one window with room to think. Size for that, and the refactor becomes a series of small verified changes.
MCP servers: when they are worth it Englisch Claude Code
Connect one when you keep pasting from the same tool. Reach for a CLI first, because Anthropic calls that the most context-efficient option there is.
Plugins and marketplaces: what installing actually adds Englisch Claude Code
One install can add skills, agents, hooks and MCP servers at once. Know what arrived, what it costs at startup, and how to walk it back.
Use Claude Code in a repeatable pipeline Englisch Claude Code
Separate JSON transport, permissions, authentication, and human decisions when automating a Claude Code task.
Reviewing what the agent wrote Englisch Claude Code
You are reviewing a diff whose author cannot tell you what it was unsure of. Read for the things it never flagged, and let a fresh context do the first pass.
Secrets, credentials, and what never enters context Englisch Claude Code
Four routes get a secret into the transcript, and a Read deny rule closes two of them. Only the sandbox stops a script that opens the file itself.
Skills, and when to write one Englisch Claude Code
A skill is a procedure loaded only when it is relevant. Write one when you keep pasting the same instructions — and not before.
Slash commands, and the prompt you keep retyping Englisch Claude Code
Any prompt you have typed three times is a file waiting to exist. The modern mechanics: commands and skills are one system, invoked with a slash.
Subagents: delegating without losing the thread Englisch Claude Code
A subagent reads in its own context and returns only a summary, so the investigation costs you a paragraph instead of thirty files.
Working in a repo you do not know Englisch Claude Code
The model reads faster than you, which changes what the first hour is for. Interrogate before you change, and let the plan expose what you both missed.
Worktrees: running sessions that cannot step on each other Englisch Claude Code
A worktree gives a session its own checkout, so two agents never fight over the same files. The cost is a fresh directory that has none of your setup yet.
Chat, Projects, Cowork or Code: picking the right mode Englisch Claude + Cowork + Claude Code
Four surfaces, four cost profiles. Picking wrong is the most common reason people burn an allowance on work that did not need it.
Data exfiltration through an agent's own tools Englisch Claude Code
An agent that can read files and reach the network is already a channel. The control is egress, because detection is the part that cannot be relied on.
Incident response when an agent did something Englisch Claude + Cowork + Claude Code
The playbook assumes a human actor and an agent breaks its first three questions. Decide before the incident what your records will be able to say.
Workflow: debugging a failure Englisch Claude + Claude Code + Anthropic API
Narrowing costs four times what diagnosing costs. Put the cheap model on the search and the expensive one on the thirty seconds that decide the answer.
Plan, implement, and review across providers Englisch Benötigt: Claude Code + Codex + Gemini CLI
Coordinate a bounded change with a reviewed plan, isolated candidate artifacts, independent reviews, and an explicit acceptance decision.
Workflow: a refactor across several files Englisch Claude + Claude Code + Anthropic API
The plan is 1% of the tokens and decides the other 99%. Everything else is mechanical, and mechanical work does not need the expensive model.
Turn research into a checked code change Englisch Benötigt: Gemini API + Claude Code + Codex + OpenAI API
Carry selected source evidence through planning, implementation, and review while keeping uncertainty and human decisions visible.
Workflow: researching and synthesising Englisch Claude + Claude Code + Anthropic API
Reading thirty sources costs eight times what thinking about them costs. This is the workflow where model choice saves the most.
Review a change with another provider Englisch Benötigt: Claude Code + Gemini CLI
Give independent reviewers the same fixed evidence, validate their findings, and let a human decide the result.
Workflow: reviewing a change Englisch Claude + Claude Code + Anthropic API
Three steps, three different models. Reading is not judging, and paying Opus rates to read a diff is the commonest waste in this workflow.

Modelle, Zugang und Limits prüfen