fire-service-pack-standardlisted

# Fire Service Pack Standard **Spec:** AIP-BS-FIRE-SERVICE-PACK-STANDARD · **Version:** 2026-09-17 · **Canonical:** https://aipathway.com.au/explore-ai/fire-service-pack-standard A test recorded against the wrong asset, or with no photograph of the tag, did not happen. Eight checks in a fixed order, four queues, required evidence per asset class, and why unbound is not the same as pass. ## Read the standard first The full specification is in `reference/fire-service-pack-standard.md` in this skill. Read it before writing code. It is about 3,000 words and it is the whole job: the checks in order, the objects with their fields, what must never be automated, and a pass test. For the current version, fetch https://aipathway.com.au/explore-ai/fire-service-pack-standard.md. This copy is 2026-09-17. The checks are also structured data, so you do not have to infer a test plan from the prose: https://aipathway.com.au/explore-ai/fire-service-pack-standard/checks.json gives each check a stable id, the ports it observes, what to inject and what to assert. `npx @aipathway/conformance show fire-service-pack-standard` prints them and comes with a stub and a runner, so a build can be driven through those ports and asserted without a live phone number. Verdicts are not pass/fail: a check needing a live number returns `with_us` rather than failing you, and one asking what you measured before building returns `evidence_required`, which no amount of working code turns green. ## How to use