Verify every test expectation in entity test suites against the authoritative adcp spec and library sources. Adds spec permalinks to each test for traceability. Flags discrepancies where our tests assume behavior the spec doesn't define. Run this after…
Orient a fresh session against the tickets in this worktree before any plan is written: read them, ground them in the pinned AdCP version, and measure what BDD coverage actually exists. Use at the start of every session in a ticket worktree, including after…
Start work on one or more GitHub tickets: branch off freshly-fetched origin/main, create a sibling worktree, and give it an isolated beads database. Use when picking up a ticket or a small batch of related tickets. Follow with /prime to orient in the new…
Derive integration tests from existing unit test xfails and UNSPECIFIED stubs. Uses integration-from-stub formula: catalog → review → triage → architect → write-integration → fix-green → reconcile-xfail → verify → commit. Each stub's expected behavior is the…
Apply the Google developer documentation style guide to everything this repo writes in prose: beads epic/task titles and descriptions, YAML formula step names and descriptions, `.claude/notes/*.md` engineering notes, commit messages, docstrings, and code…
Start an isolated PostgreSQL container for integration testing. Each worktree gets its own container on a unique port — no mutex, no conflicts. Use this before running integration tests in a worktree agent.
Two-pass BDD step assertion completeness inspector. Pass 1 (Sonnet): triage all Then steps — FLAG or PASS. Pass 2 (Opus): deep trace flagged steps with full production context, producing architectural judgment on what the correct assertion should be. Use…
Derive obligation tests using the test harness. First checks for harness availability, then generates compact tests using domain-specific test environments. Hard gate: no harness -> no tests (stops immediately). Replaces obligation-test for harness-enabled…