Tasks NNN — [Feature name]
Execution skill: superpowers:subagent-driven-development — one implementer per task, then a two-stage review (spec compliance, then code quality). superpowers:test-driven-development applies inside every task: no production code before a failing test that demands it. Reach for superpowers:systematic-debugging on any surprise rather than guessing.
Derived from plan.md (approved). Each task is small, independently verifiable, and reviewed as its own diff. Split where a reviewer could reject one task while approving its neighbour — not where the work merely changes subject. A task is done only when it satisfies the definition of done in CLAUDE.md.
Global Constraints in plan.md apply to every task and are not repeated per task.
T1 — [what this task makes true]
Satisfies: [the spec criteria this task delivers — R3, P1 #2, SC4. A task satisfying nothing is a task the spec did not ask for.]
- [ ] RED: write the failing test, named for its criterion. Watch it fail, and check it fails for the reason you expect rather than for a setup mistake.
- [ ] GREEN: the smallest change that passes. Not the change you would like to write.
- [ ] REFACTOR: only with the test green.
- [ ] Confirm the test has teeth — break what it guards, watch it fail, restore. A test that passes against a broken implementation is worse than none, because it reads as coverage.
- [ ] Commit.
Verified by: [test name, command, or observable result. Name the test, so the traceability table in spec.md is a transcription rather than an excavation.]
T2 — [...]
Satisfies: [...]
- [ ] [one action, two to five minutes. If a step needs a paragraph to explain, it is two steps.]
Verified by: [...]
Notes
Staging area for decisions and surprises found during implementation — including anything that turned out differently from what plan.md assumed. Move each one into spec.md, research.md, or docs/ before closing the feature; this section is not a home.