The bench

A static register of agent identities, roles, mandates, grants, acceptances and revocations — eleven records and twenty-three signed statements at constructed public URLs, verifiable with the shipped sgit pki commands.

A signed mandate compiled into a pre-push hook that git runs — and that refused a real push to dev with error: failed to push some refs.

A tool that generates a grant document for the environment it runs in, and two measured entries — a hosted agent container and a CI runner — that join at the push edge.

Nine reusable components — tier and evidence badges, cards, the delta block, the grant tree — shipped as a stylesheet and a gallery that renders the real documents.

A visitor assembles their own agent installations as grant trees, sees the gap, and records a decision per gap — storing the choices and never the answers.

The RiskMandate workflow walked end to end as a playable room — eight stations, the product boundary drawn on the floor, four verbs, and a work item that travels the chain. The left half is real artefacts; the right half is a marked simulation.

Actions resolving against grants and mandates, played as cards: six suits, four players including the systems, and the estate's real 26 August incident replayed forward as simulation and backward as audit — with every resolution re-run through the enforcement tool at build time.

One engine, two worlds: Push to GitHub and The Deploy are rendered by the same generator from two scenario.json files, each referencing a measured twin — the engine holds no capabilities of its own, and every card is a twin node wearing scene clothes, with a confidence rung computed from its evidence and a micro-animation per capability kind.

Both scenario worlds on one operator board — mimic diagrams, annunciator tiles whose lamp colour is the tier and nothing else, faceplates on click, and the 26 August incident as a replayable sequence-of-events log with every verdict re-run through the enforcement tool at build time. One more renderer, zero new data.

The first surface here that answers to the visitor rather than replaying this estate's history: play cards against a measured twin and watch what they do. Every outcome is a verdict of the real enforcement tool, a reading of the twin, or UNKNOWN — precomputed at build time, because the browser is not an enforcement point.

An experimental app: the primitives on a rail — identities, grants (the twin), mandates, facts, actions, a simulator — and every decision hands back an evidence pack, because the decision is disposable and the record is not.

The second volume, by the method of the first: ten voice memos and a pivot briefing, filed verbatim before they were read, made into one argument — the gap between what an agent can do and what it was authorised to do is an insurable exposure, and the honest first product is a rating anybody can recompute, not a premium nobody can check. Seventeen chapters in five parts, with the audit's six defects walked in full.

One volume explaining what this site built, how it composes with RiskMandate.ai, and what none of it proves — 17 chapters in five parts, 14 figures each taken at the release tag its caption names, and 65 quotations re-read out of their sources on every build.

A registry of capability primitives (verb × object × reach + reversible) and measured grants where a grant claim never travels alone: it points at the probe that established it, the date, the environment and the output, so a challenge is a rerun rather than an argument. A runner that emits findings/v1 in OpenSSF Scorecard's probe/finding shape plus reversibility and tier; seven profiles, two of them measured; grants public, mandates private.

A self-assessment that runs in the browser: name your tools, the grant appears from measurements other people contributed, four questions about work produce the mandate, and the gap is rendered with the irreversible rows first and the reduction on the same screen. The verdict is a statement, not a grade; the tier is on the result; the counts-only tuple is shown and never sent.

Named for the question a person has (working title guess the agent). A guessing game whose output is a measurement: cheap questions with obvious answers, ordinary decision-tree induction over a belief across the public profiles, a prediction step before the reveal, and the prediction gap with the reduction on one screen. Deterministic, in the browser, the path always shown, nothing sent.

A programme that puts a page in front of an agent which receives pixels and nothing else — no text, no structure, no knowledge of the project — and watches where it goes.