Menu
Phase 3 of spec-driven development — generate tasks.md from plan.md. Executable [P]-parallelizable tasks, TDD-first, layer-ordered.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Verify a feature spec, plan, or PR against the non-negotiable principles in `.specify/memory/constitution.md`.
Extract session insights after a task completes and feed them into Morphic's self-evolution engine. Captures what worked, what didn't, and proposes prompt/routing tweaks.
Keep CLAUDE.md (thin router) and AGENTS.md (telegraph-style) in sync. Detects drift in command lists, paths, and routing tables between the two root instruction files.
Generate a monthly or on-demand cost report across LLM providers, local LLMs, and agent engines. Flags overspend and suggests downgrades.
Run live end-to-end verification across Morphic-Agent's 6 agent CLI engines. Produces a baseline comparison table with duration and cost per engine.
Inspect Morphic-Agent's fractal task graph for a given task_id. Reports bypass classifier decisions, Gate 2 skips, parallelism, and regression flags.
Based on SOC occupation classification
| name | prp-implement |
| description | Phase 3 of spec-driven development — generate tasks.md from plan.md. Executable [P]-parallelizable tasks, TDD-first, layer-ordered. |
| when_to_use | After /prp-plan produces plan.md. Produces a task checklist you can execute top-down. |
| argument-hint | <feature-slug> |
| allowed-tools | ["Read","Write","Glob","Grep"] |
| model | opus |
You turn plan.md into a TDD-ordered tasks.md that any agent can execute.
$ARGUMENTS = <slug>. Reads specs/<slug>/plan.md.
specs/<slug>/plan.md exists and constitution-check passed.spec-writer subagent with phase=tasks..specify/templates/tasks.md.[P] when they touch disjoint files and can run in parallel.specs/<slug>/tasks.md.# Tasks — <slug>
## Milestone 1: Domain
- [ ] T-01 Write failing test `tests/unit/domain/test_foo_entity.py::test_bar`
- [ ] T-02 Implement `domain/entities/foo.py::Foo`
- [ ] T-03 [P] Write failing test `tests/unit/domain/test_foo_service.py`
- [ ] T-04 [P] Implement `domain/services/foo_service.py`
## Milestone 2: Application
- [ ] T-05 Write failing test `tests/unit/application/test_do_foo.py` (mock ports)
- [ ] T-06 Implement `application/use_cases/do_foo.py`
## Milestone 3: Infrastructure
- [ ] T-07 [P] Port ABC `domain/ports/foo_port.py`
- [ ] T-08 [P] Impl `infrastructure/foo/foo_adapter.py`
- [ ] T-09 Integration test `tests/integration/test_foo_adapter.py` (real PG)
## Milestone 4: Interface
- [ ] T-10 Route `interface/api/routes/foo.py`
- [ ] T-11 Wire DI `interface/api/container.py`
- [ ] T-12 API integration test
## Milestone 5: Gates
- [ ] T-13 Update `docs/TECH_DECISIONS.md` with TD-<next>
- [ ] T-14 Update `docs/CHANGELOG.md`
- [ ] T-15 Run full suite + lint
[P] only when tasks touch disjoint files. Same-file edits serialize.