Pierwsze kroki
Zainstaluj Codewhale, podłącz swój model i zleć mu zadanie. Konfiguracja Fleet jest opcjonalna.
Install Codewhale
The command below installs the latest published release on macOS or Linux. Use the install guide for Windows, package managers, or building the unreleased source candidate.
Full install guidecurl -fsSL https://codewhale.net/install.sh | shConnect your model
Codewhale needs a model to answer. Save your own provider key, as in the DeepSeek example below, or run a local model such as Ollama, which needs no key. You pay the provider directly.
Connect a providercodewhale auth set --provider deepseekGive it a task
Open Codewhale in your project folder and ask for something concrete. Start in /mode plan to have it explain the project without changing anything, then switch to /mode work for edits and commands. It shows each edit as a diff and asks before running a shell command.
Set modes and approvalscodewhaleAdd a Fleet when you need one
When a task would benefit from several models and roles, run /fleet setup inside Codewhale to save roles and the model each one uses. From your shell, codewhale fleet status counts the Fleet runs that are queued, running, or finished.
Run a workflow/fleet setup codewhale fleet status
Co dalej
Review what changed
See every edit in a session, roll files back to an earlier turn, and get a code review before you push.
Set modes and approvals
Plan, Work, or Operate for the kind of work; Ask, Auto-Review, or Full Access for when it stops to ask you.
Run commands on events
Run your own scripts when a session starts, before a tool call, or when a turn ends — to add context, enforce a rule, or get notified.