Autonomous Mode

Ralph loops over ready work until the spec ships, blocks, or hits the iteration cap.

scripts/ralph/ralph.sh
scripts/ralph/ralph.sh --watch
scripts/ralph/ralph.sh --watch verbose

Review gates

Configure in scripts/ralph/config.env:

REQUIRE_PLAN_REVIEW=1
PLAN_REVIEW=codex
WORK_REVIEW=codex

Supported review backends include RepoPrompt, Codex, Copilot, and none. Production Ralph runs should use a real review backend.

Execution contract

Ralph should not invent new scope. Each loop must:

1. Re-read the spec and ready task.
2. Check current git state.
3. Execute only the ready work.
4. Run configured review.
5. Record receipt state.
6. Stop on blocker, missing requirement, or unsafe ambiguity.

flowchart LR
  Ready["Ready task"] --> Execute["Fresh execution"]
  Execute --> Review["Review backend"]
  Review --> Receipt["Receipt"]
  Receipt -->|pass| Continue["Continue"]
  Receipt -->|block| Human["Human handover"]

Team usage

In teams, Ralph should run after product and technical ownership have already happened:

/flow-next:interview fn-1 --scope=business
/flow-next:interview fn-1 --scope=technical
/flow-next:plan-review fn-1
scripts/ralph/ralph_once.sh

Do not use Ralph as a substitute for product clarification. It is an execution loop, not a product owner.

Monitor

scripts/ralph/ralph.sh --watch
scripts/ralph/ralph.sh --watch verbose

Use watch mode when you want to keep the Ralph terminal visible during a long run. It shows the current task, review state, receipts, and stop reason without requiring a separate global TUI install.

Stop conditions

• Review verdict is not shippable.
• Required command or tool is unavailable.
• The ready task requires a decision outside the spec.
• Git state is unexpectedly dirty.
• Evidence cannot be produced.
• Iteration cap is reached.

A clean stop is success. It preserves the handover so a human can decide the next step.