planlisted
Install: claude install-skill chan4lk/specclaw
# specclaw plan
**First, run** `specclaw-ensure-init .specclaw` — idempotently creates `.specclaw/` if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).
Turn an approved proposal into an executable plan.
## Flags
- `--author-spec` — delegate spec authoring to the `spec-author` subagent for an interactive, technique-driven dialogue (5 Whys, Jobs-to-be-Done, Inversion, Pre-mortem, MoSCoW). When this flag is present, **pause for explicit user approval of `spec.md`** before generating `design.md` and `tasks.md`. Without the flag, behavior is unchanged (single-shot generation, no dialogue) so `/specclaw:auto` remains non-interactive.
Detect the flag as a whitespace-delimited token anywhere in ARGUMENTS (positional-agnostic), and strip it before using the rest of ARGUMENTS as `<change>`.
1. **Validate:** run `specclaw-validate-change .specclaw <change> plan`. If it fails, report missing prerequisites and stop.
2. Read `.specclaw/changes/<change>/proposal.md`.
3. Analyze the existing codebase (file structure, patterns, dependencies relevant to the change). **Also read `.specclaw/context.md` if it exists** — it contains project-level coding rules, patterns, architecture decisions, and constraints; apply them throughout spec, design, and tasks generation.
- **Codebase survey:** build a structured survey and keep it in your working context for spec/design/tasks generation: top-two-level directory summary