Skip to main content
wiggum new <name> [options]
Starts an AI-guided interview to generate a detailed, project-aware feature specification. The spec is saved to .ralph/specs/<name>.md.

​
The interview

The interview has five phases:
PhaseWhat happens
ContextShare reference URLs, docs, files, or GitHub issues relevant to the feature
GoalsDescribe what you want to build in plain language
InterviewAI asks up to 10 clarifying questions about scope, edge cases, and constraints
GenerationProduces a detailed, implementation-ready feature spec
CompleteShows summary, saves spec to .ralph/specs/
During the interview, the AI uses your codebase context — it reads files, searches for patterns, and explores your directory structure — to ask questions specific to your project.

​
Flags

​
name
string
required
Name for the feature spec. Used as the filename in .ralph/specs/.
​
--issue
string (repeatable)
GitHub issue number or URL to pull as context. The issue title, body, and labels are pre-loaded into the interview. Can be specified multiple times.
wiggum new my-feature --issue #42 --issue #38
​
--context
string (repeatable)
Additional reference URL or file path to include as context. Can be specified multiple times.
wiggum new my-feature --context https://docs.example.com/api --context ./design-doc.md
​
--auto
boolean
default:"false"
Headless mode — skip the interactive interview. Generates a spec directly from --goals and any issue/context provided. Useful for scripting, CI, and agent integration.
wiggum new my-feature --auto --goals "Add JWT auth middleware with refresh tokens"
​
--goals
string
Feature goals description. Used with --auto for headless spec generation.
​
--provider
string
AI provider for spec generation. Overrides the default.
​
--model
string
AI model to use for the interview.
​
-e, --edit
boolean
default:"false"
Open the spec in your editor after creation.
​
-f, --force
boolean
default:"false"
Overwrite an existing spec with the same name.

​
Spec output

The generated spec includes:
  • Feature overview and goals
  • Implementation steps with file paths
  • Edge cases and error handling
  • Testing strategy (unit + E2E)
  • Acceptance criteria
Specs are plain markdown — agent-agnostic and compatible with Claude Code, Codex CLI, or any agent that can read files.

​
Examples

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