Answers before the workflow gets expensive.
Most CafeKit mistakes come from skipping scope, skipping validation, or treating chat as state. This page clarifies the common edge cases.
Is OpenCode currently supported?#
No. Current releases support Claude Code and Codex CLI. OpenCode support ended in CafeKit 0.17; the site keeps the frozen 0.16 command map only for migration history.
Should every task start with /cf:specs?#
No. Use specs for meaningful feature work. Use /cf:debug and /cf:fix for bugs. Tiny local fixes may not need a full spec.
Why does CafeKit care about task files?#
Task files preserve scope, steps, completion criteria, and evidence. They are the bridge between human intent and machine-checkable state.
Is NO_TESTS a pass?#
No. NO_TESTS only means no real test suite ran. Build health, runtime proof, and task evidence still matter.
Can a task be marked done from chat?#
No. done requires fresh verification and a current final inline Receipt in the task. C3 remains the user's completion decision.
What should I use for production bugs?#
Start with /cf:debug when root cause is unknown. Use /cf:fix after diagnosis or when the bug and target fix are already clear.