THE PRIMITIVE — THE ATOM EVERYTHING STANDS ON
One move, and it is the whole of the keeping. A load-bearing intent is cut into the record before the work — a falsifiable commitment, or it is refused. When reality resolves, the deed is read against that commitment and graded on the truth, not on how it looks. Then it is kept, append-only — the miss beside the win. Bind, grade, keep: the rune cut before the deed, the deed read against the rune, the ash raked and kept.
GRADED · DOGFOODED The house runs on this atom daily — the misses kept as loudly as the wins. This chapter is its deep home.
BIND — THE FALSIFIABLE FORM, WRITTEN BEFORE THE WORK
Every load-bearing intent is written down before the work, as a falsifiable commitment: what you claim, under what conditions, and the test that would prove you wrong. The binding carries the claim, its conditions, and a falsifiable test_spec — and enters the ledger as declared.
If the promise cannot be made falsifiable, the bind is refused at that moment — refused_unfalsifiable, not warned about later, not accepted and quietly ungradeable. No un-gradeable promises enter the ledger. The discipline rides inside the agent loop, not a form a human fills in afterward.
THE LEDGER REFUSES
The rune is cut before the deed.
every load-bearing intent bound as a falsifiable commitment before the work — or refused at bind-time, never warned about later
GRADE — AGAINST GROUND TRUTH, NEVER ASSERTED
When reality resolves — a test runs, a review lands, an outcome settles — the commitment is graded against the ground truth: satisfied, violated, or retracted. Never quietly forgotten. A violated commitment is kept and owned, as loudly as a satisfied one.
And the grade itself is never asserted. It comes from what actually happened — a test, a resolution, a settlement — not from how plausible the artifact looks. An artifact that looks plausible is not a graded one; confident, plausible output is indistinguishable from correct output until something breaks. Askora records what was committed to and whether the bound test held: faithful, not omniscient.
▸ 09:41:02 declared "Checkout p95 stays under 200 ms…" — seat mira-2, under goal "checkout latency" ▸ 09:41:07 test_spec load-run checkout.k6.js — p95 < 200 ms, three consecutive runs ▸ 09:41:11 claimed mira-2 takes carriage ▸ 10:02:19 satisfying work begins ✓ 10:19:35 graded SATISFIED — filed by mira-2, the seat that carried it
A record that only remembers successes is not a memory, it is marketing.
The deed is read against the rune, not against how it looks.
graded against ground truth when reality resolves — read from what happened, never asserted from prose, and a miss kept as loudly as a win
KEEP — ONE APPEND-ONLY RECORD, THE ASKA
Every state change is written to an immutable, append-only record — the aska. The journal ("what did we work on"), the changelog ("what shipped"), the audit ("what was committed to"), and the postmortem ("what did we miss, and why") stop being four hand-kept documents and become four queries against one record.
Nothing is edited in place. Every state change is itself a versioned row in the aska — append-only and fully audit-trailed, the history is the point, not an incidental log. Every violated binding stays there and owned, so the next run reads against it instead of re-deriving it.
declared → translated → claimed → satisfying → graded_satisfied · graded_violated · retracted — or refused at bind-time, before it ever enters
journal · changelog · audit · postmortem — four views, one aska
The ash is raked and kept.
every state change written append-only and fully audit-trailed — nothing edited in place, the graded_violated binding retained and read by the next run
Append-only and fully audit-trailed — we do not say "tamper-proof." What the record compounds into wave over wave is its own chapter — Remember: the ledger read over time, on Solora →
CLASH-CHECK — DECLARED IN FULL, BUILT IN NO PART
DECLARED · FRONTIER None of the three phases below runs. Phase 1 carried an OPEN · DELIBERATELY BROAD chip and phase 2 a COVERAGE-BOUNDED · PUBLISHED chip until 2026-08-15; there is no clash state in the shipped ledger, nothing computes an overlap or a contradiction, and no coverage bound was published anywhere. The design is left standing so it can be argued with, and the chips now say what it is.
The design: the moment more than one maker binds at once, each new commitment would be checked against every open commitment in the fleet before the bind is accepted — so a contradiction is caught at bind-time, not merge-time, and the clashing bind is held as a verdict a human can read while both commitments are still cheap to change.
Do two commitments touch the same files, identifiers, or actions? A wide, cheap net computed directly over the declared conditions and satisfier pointers — string and set membership, nothing hidden. It is deliberately broad on same-surface conflicts and over-flags on purpose, because overlap is not yet contradiction. It hands a small candidate set to the next phase.
Do two commitments contradict on meaning — including when their surfaces differ, or when they overlap but do not actually conflict? High-value and coverage-bounded: it would catch what it can read, and a contradiction it cannot read would never be claimed caught. No coverage figure goes with that promise until a corpus has produced one.
From the graded record, likely clashes anticipated before both commitments are fully declared. Same discipline as phase 2, and a further step out: this one needs a graded history large enough to fit against.
When it ships, Askora will catch what it can read and be honest about the rest — and its coverage will be a measurement before it is a sentence. Worked in full across many makers at once — Work together: coordination on the ledger, on Solora →
THE VERDICT — LEGIBLE, NEVER A BLACK BOX
DECLARED · FRONTIER The verdict shape below is published so it can be held to, not because it is emitted: no clash verdict has ever been written, because nothing produces one. A verdict a human acts on would carry six things — all of them open, all of them human-readable.
| the verdict carries | what it holds |
|---|---|
| the two commitments | the pair in tension, by binding id and scope |
| which phase caught it | syntactic overlap · semantic contradiction |
| its kind | blocking contradiction, or values-tension — routed differently |
| a human-readable reason | a promise and the open promise it contradicts, in plain language |
| a confidence note | honest about how sure the reading is, and its coverage |
| a suggested resolution | retract · re-scope · sequence behind the other · escalate to a human |
A clash blocks and must be resolved; a values-tension is direction and must be chosen. That a verdict carries its kind is part of the open verdict shape — the trust story →
Cut the rune, read the deed against it, keep the ash — so the next fire is truer than the last.
one atom — bind · grade · keep — the whole of the keeping, the misses kept as loudly as the wins
