approval-engine/README.md
tegwick 2a5a47df89 Align to security layer model v0.7 and open the engine spine
The statute is accepted at v0.7; the operative form is
net-kingdom/SECURITY-COMPANION.md v0.2. INTENT now declares Engine / PIP
in its own voice, carries the §9.6 threat decomposition, the load-bearing
heartbeat obligation, issuer and freshness on the claim, consumption as a
mutation, and the custody question closed rather than held open.

SCOPE.md is the first-cut boundary (nothing shipped). layer.yaml is the
machine-readable declaration. The review under history/ scores intent vs
scope vs the empty implementation. APPROVAL-WP-0001 sequences contracts
before code and keeps consumption unimplemented until GH-WP-0002-T06.

Registered with State Hub as infotech / approval-engine.

Assistant: grok
Assistant-Session: 01a04ceb-2057-7e20-b0f9-c282964d5dd9
2026-08-29 11:58:28 +02:00

24 lines
1.1 KiB
Markdown

# approval-engine
**The approval as a durable, authenticated, consumable object — issued before an
action, verified at the moment of use, and provably not replayable.**
An Engine, role **PIP**, in the NetKingdom security layer model (statute v0.7,
accepted; operative form `net-kingdom/SECURITY-COMPANION.md`). It answers one
question, totally and decidably:
> Is this approval valid right now — for this exact action, target, actor, and
> purpose — and has it already been used?
It does **not** decide whether the action is permitted. That is `access-engine`,
which stays NetKingdom's only policy decision point. An approval is one input to
that decision.
Deliberately small, boring, and strict: atomic supersession and single
consumption are what make Canon test `T-06 — Approval Replay` passable.
Flexibility here would be a defect. Graded, evidence-based progression belongs to
`maturity-engine`; the two engines are deliberate opposites.
See [INTENT.md](INTENT.md) and [SCOPE.md](SCOPE.md). Declaration: [layer.yaml](layer.yaml).
Origin: `flex-auth` `FLEX-DEC-2026-001`, raised while assenting to the security
layer model.