thinceller Turn an agreed spec or conversation into a plan a fresh subagent can execute one task at a time, with no other context.
Global constraints
State project-wide requirements once, at the top of the plan — versions, naming conventions, style rules, anything that applies to every task. Every task's requirements implicitly include this section; don't repeat it per task.
Task breakdown
A task is self-contained when a fresh subagent, given only that task's text, has everything it needs to do the work and know when it's done. That's the only sizing rule — no fixed step count or timing.
Each task states:
- Goal — what this task accomplishes.
- Files — exact paths to create or modify.
- Interfaces — what this task consumes from tasks it depends on (exact signatures, not descriptions) and what it produces for tasks that depend on it. This is how a task's implementer learns the names and types neighboring tasks use, without reading those tasks.
- Verification — the exact command to run and the expected result.
No placeholders
Every task needs the actual content an implementer needs to act on. These are plan failures:
- "TBD", "handle edge cases", "add appropriate validation"
- "Similar to Task N" (write it out — the implementer may work tasks out of order)
- References to types or functions not defined in any task
Self-review
Before finalizing, check the plan against the spec: does every requirement map to a task? Do names and signatures used in later tasks match what earlier tasks define? Fix inline rather than re-reviewing.
Saving the plan
Check .claude/engineering.local.md for a plans: key in its frontmatter — a path, or none to skip saving. If the file doesn't exist, ask once where (or whether) to save this plan, accept "don't save" as an answer, and mention /setup-engineering for making the choice permanent. Never write plans into CLAUDE.md or AGENTS.md.
Once the plan is saved, implement is a candidate for executing it.