temple8

Compile the contract set in your head — simulate how the real application would run from the specs, and disprove (or confirm) it works before any source .py is written.

Author test stub files (.pyi) whose signatures express the domain, relationships, and compositions, as the first contract surface.

Funnel level 3 — identify building-block names and rough boundaries only, and run gap analysis.

Funnel level 1 — establish the big picture with seven broad questions, applying CIT, Laddering, and CI Perspective throughout.

Squash-merge the feature commits into dev, regenerate docstrings, and verify the whole suite plus whole-suite stubtest are clean.

Publish the delivered batch as release notes, a PR to main, or a tagged release.

Close the pipeline cycle: regenerate the living spec from current tests, summarize the carry-over cache files, regenerate source docstrings then strip all .py so the next cycle starts compact.

Pull the next source contract to build from the pending backlog, respecting outside-in dependency order.

Transform the reviewed test stubs into executable test bodies, with the code-quality gate applied here.

Confirm the target contract's tests fail for the right reason before implementing — new work or rework, never a test defect.

End of session — replace running notes with the full synthesis across all three funnel levels and author the glossary of ubiquitous language.

Derive the source stub files (.pyi) from the reviewed tests — every type the tests reference gets a definition.

Design the interaction + feedback + error flows for a user-facing surface (CLI, API, or web). On-demand — run when the ux-engineer is consulted on an interaction contract.

Produce a project visual asset — social card, README banner, logo/avatar, or favicon — as self-contained, accessible SVG. On-demand.

Write the minimum production code to turn the target's tests green, implementing the .py from its fixed .pyi.

Create a new project instance from the temple8 template via copier, verify it, and initialise the first flowr session.

Funnel level 2 — structure the domain into behaviour groups, bounded contexts, integration points, and lifecycle events.

Author the persistence schema as a binding contract from the captured external shapes and the interview — before any test stub is written.

Execute the probe against the real service and record the exchange into a committed cassette, scrubbed of secrets and volatility.

Author (or amend) an Architecture Decision Record for a load-bearing architectural decision, in place, with a change log.

Improve the source structure under green tests, with the .pyi fixed and the tests untouched.

Ground one external service in its real behaviour by reading the provider's official docs and determining its access shape, before any probe code is written.

Gate the implementation against its contract for correctness, quality, drift, and green tests.

Review the test stubs for coverage, scope, vacuous-assertion freedom, finding-grounded scope, and happy-path completeness against the interview and the modeled schema — not for code quality.

Pick the next external service to probe by subtracting already-captured services from those the interview named.

Commit the built unit as one logical change with a descriptive imperative message.

Author the minimal authenticated probe script that exercises one success path and one error path against the real service, without executing it.