Four flows, one rule: the human judges, the engine measures
uscha has a front for new systems and a front for existing ones. Both end at the same place — a human verdict the engine can check. These four diagrams show the greenfield flow, the brownfield flow, the curation mechanism (kit 1.64–1.65) where a single human decision is the only judgment in the loop — and the diamond leg (1.72–1.90) they all feed: compile, certify under a withheld oracle, round-trip. Every piece of the kit on one page is in the component map.
Discovery — you bring the idea, the method proposes the shape
The skill explores first, then asks one question at a time — each with a recommended answer. You confirm or correct; you never author the shape from a blank page. The package is written to the repo as decisions crystallize.
Reverse Discovery — extract facts, then quarantine the claims
The running system's behavior is the truth. The skill extracts facts (map, golden), then authors candidates in quarantine — never specs. The old rule "never author an inferred spec" was renegotiated in ADR-009: you may author candidates, you may never promote them without a verdict.
INV-GOLDEN-01 is enforced mechanically on Claude Code (a blocking PreToolUse hook); on every other target the kit reports it as advisory — the measured control everywhere is golden-diff, which compares bytes.
Curation — one human verdict, everything else measured
This is the differentiator. A candidate is machine-validated; a candidate with no
verdict blocks the PR, naming itself (INV-CURATION-01). The single human decision
splits into three buckets. A fix declares its expected divergence, which the golden
oracle then checks. roundtrip reports traceability by id — advisory, never a gate.
Compile, certify, round-trip — the forward leg the three flows feed
The curated package becomes a typed graph. Any model compiles it; the engine only validates the output contract and never compiles. A withheld oracle — authored before any compilation, never in the prompt — certifies whether the result is the same system. Then the reverse organs try to re-anchor the asset from the compiled code, and that ratio is published with its ceiling.
Tests are run by the engine, not reported to it: test-run runs the declared command and only the reports it wrote count. A QA pass is registered when it starts (review-start), so a verdict is tied to the tree it reviewed — a later source edit sends that tool back through the loop. With review_tiers declared, the effort follows the change: the tier the changed paths reach picks the tools, and a fix is re-reviewed on its diff. With review_tiers (2.16) that tool re-reviews only what the edit changed, and the engine sets how much review a change needs from its paths.
Every node above maps to a real subcommand or invariant in qa_ledger.py.
These three flows are the human-judgment layer. The forward leg they feed — the LLM as compiler
under a validated contract, blind compilations judged by a withheld oracle, and the measured round
trip back — is the diamond: same doctrine, one level up.