Require `buyer_check_named` output field in genesis PROPOSER_SYSTEM

council rejected PROMPT reversible: simple 3h proposed 5 Jun 2026

What is the proposed change?

In PROPOSER_SYSTEM (genesis.js around line 56-60 and line 213 where required output fields are declared), add a new required output field `buyer_check_named` with rubric: 'Name the smallest observable single action the named ICP would take in the first 14 days that signals genuine willingness to pay (e.g. accepting a 30-min call, paying a £50 deposit, granting read-only access to their LangSmith workspace). Reject vague answers like signs up for waitlist, replies positively to email. Must reference the specific ICP and a specific channel from your S110 audience archetype. ≤40 words.' Add validation in the parser path: if `buyer_check_named` is missing or under 15 words, mark proposal `reject_reason: 'no_buyer_check'`.

Target files

hypothesis_engine/moves/genesis.js

Expected effect

Of the next 30 genesis proposals, ≥40% will be rejected at parse-time for missing/insufficient buyer_check. Surviving proposals will have a structurally testable validation step the Commander can run within 14 days. Re-running council_verdict on 10 previously-graduated candidates after retro-fitting buyer_check: ≥3 candidates' council scores drop by ≥1 point because the field exposes weak validation paths.

Falsifier — what would prove this wrong?

Retrofit `buyer_check_named` field onto 10 currently-graduated candidates by re-prompting genesis. If council_verdict scores do NOT change for ≥3 of them, the field doesn't carry decision signal and the prompt change is decorative.

Evidence that triggered the proposal

E — brain/proposals/digest-2026-06-04-007.json — Opus review explicitly: '14 signals saying the problem is real without one signal saying here\'s a check is a research trap the prior Opus review correctly flagged'
B — brain/MANIFESTO.md v4 'Honest/Deflated': £100-300K/year in 6-18mo target requires checkable buyer actions, not just problem-validation corroboration

Proposer self-score

The proposer scored its own draft on these axes (0-3 each) before submitting.

Axis	Score
specificity	3
falsifier	3
solo feasible	3
blast radius	2
composability	3
reversibility	3

Disposition

Rejected at the council verdict. The two-judge council did not find the case strong enough to advance to Commander review.

Evaluation history

When	Move
2026-06-12 05:14	meta_council_verdict
2026-06-12 04:52	meta_argument
2026-06-12 04:16	meta_filter_score
2026-06-05 04:04	meta_genesis