Skip to main content
wiggum run <feature> [options]
Hands a feature spec to your coding agent and runs an autonomous loop: implement → run tests → fix failures → repeat. The loop continues until all tests pass or the maximum iterations are reached.

​
How it works

  1. Wiggum loads the spec from .ralph/specs/<feature>.md
  2. Combines it with project prompts, guides, and context from .ralph/
  3. Delegates to Claude Code (or your configured coding agent)
  4. The agent implements the feature, runs tests, and fixes failures in a loop
  5. When done, wiggum generates a summary with diff stats and activity log

​
Flags

​
feature
string
required
Name of the feature spec to run. Must match a file in .ralph/specs/.
​
--worktree
boolean
default:"false"
Run in a git worktree for isolation. Allows running multiple features in parallel without conflicts.
​
--resume
boolean
default:"false"
Resume from the last checkpoint if a previous run was interrupted.
​
--model
string
default:"sonnet"
AI model for the coding agent. Options depend on your provider (e.g., opus, sonnet for Anthropic).
​
--max-iterations
number
default:"10"
Maximum number of implement-test-fix cycles.
​
--max-e2e-attempts
number
default:"5"
Maximum number of E2E test retries.
​
--review-mode
string
default:"manual"
What happens after the loop completes:
  • manual — stops at PR creation, you review manually
  • auto — creates PR and runs automated review
  • merge — creates PR, reviews, and auto-merges if approved

​
Examples

wiggum
# then type /run add-dark-mode in the TUI