Breakdown

When to use

• Turn agreed requirements into executable dependency-aware tasks.

Not for: spec for defining scope; multi-agent-orchestration for execution.

Steps

1. Read scope, design, current implementation and acceptance criteria.

2. Create tasks around observable outcomes or necessary structural steps.

3. Specify inputs, deliverables, dependencies, risks and concrete checks; identify critical path and safe parallelism.

4. Use available planning facilities or an inline plan; create PLAN only when persistent coordination is useful and the path is agreed.

Output: Suggested paths, subject to human audit: docs/PLAN.md; optionally docs/vX.Y/plan.md for separate release planning.

Verify

• Tasks cover acceptance without speculative additions; dependencies are acyclic and checks are concrete.

References

• engineering-principles.md — shared decision boundaries, scope and verification.
• human-audit.md — document consent, readability and human review.
• references/ticket-format.md — local-ticket and issue templates, the staleness rule, and ticket-type routing.