spec
User request: $ARGUMENTS
Build requirements spec through structured discovery interview. Defines WHAT and WHY - not technical implementation (architecture, APIs, data models come in planning phase).
If $ARGUMENTS is empty: Ask user "What work would you like to specify? (feature, bug fix, refactor, etc.)" before proceeding.
Loop: Research → Expand todos → Ask questions → Write findings → Repeat until complete
Role: Senior Product Manager - questions that uncover hidden requirements, edge cases, and assumptions the user hasn't considered. Reduce ambiguity through concrete options.
Spec file: /tmp/spec-{YYYYMMDD-HHMMSS}-{name-kebab-case}.md - updated after each iteration.
Interview log: /tmp/spec-interview-{YYYYMMDD-HHMMSS}-{name-kebab-case}.md - external memory.
Timestamp format: YYYYMMDD-HHMMSS (e.g., 20260109-143052). Generate once at Phase 1.1 start. Use same value for both file paths. Running $spec again creates new files (no overwrite).
Phase 1: Initial Setup
1.1 Create todo list (update_plan immediately)
More from doodledood/codex-workflow
research-web
Comprehensive multi-wave web research with strategic source selection. Gathers information from official docs, community resources, and advanced sources. Use for deep technical research, API documentation, best practices. Triggers: research web, deep research, comprehensive research, find documentation.
35review-maintainability
Audit code for DRY violations, dead code, complexity, and consistency issues. Read-only analysis with actionable recommendations. Use before PR or for code quality review. Triggers: review maintainability, code quality, DRY, refactor review.
34review-bugs
Audit code for bugs, logic errors, race conditions, and edge cases. Read-only analysis producing actionable report. Use before PR, after implementation, or when debugging. Triggers: review bugs, find bugs, check for errors, code review.
29review-docs
Audit documentation accuracy against code changes. Identifies stale docs, incorrect examples, and missing documentation. Read-only analysis. Use before PR or after implementation. Triggers: review docs, check documentation, docs up to date.
21explore-codebase
Context-gathering for finding files to read. Maps codebase structure, returns overview + prioritized file list with line ranges. Thoroughness: quick for lookups, medium for bugs/features, thorough for multi-area, very-thorough for architecture audits. Triggers: explore, find files, where is, how does X work.
20review-testability
Audit code for testability design patterns. Identifies business logic entangled with IO, hard-coded dependencies, and mocking friction. Suggests functional core / imperative shell separation. Read-only analysis. Triggers: review testability, testable code, mocking issues, dependency injection.
19