Add costly_behaviour_corpus source: weekly Upwork+job-posting scrape

council rejected CORPUS reversible: medium 10h proposed 21 Jun 2026

What is the proposed change?

New corpus file populated by scrape_costly.js cron (weekly). Sources: Upwork awarded jobs API (filter price>$500), Indeed UK postings tagged with 4 baseline + 8 rotating-pain templates from S198. Each row: {snippet, source_url, observed_cost_usd, ts}. Wire into digest_ingest as new corpus tag 'costly_behaviour'.

Target files

hypothesis_engine/corpora/costly_behaviour.jsonl hypothesis_engine/lib/ingest/scrape_costly.js

Expected effect

Within 2 weeks, ≥30% of meta-lane filter_kept proposals cite at least one costly_behaviour row in their argument move (current rate: ~0% per S203 baseline). Solo_feasibility false-positives drop ≥20%.

Falsifier — what would prove this wrong?

After 2 weeks, <10% of kept proposals cite costly_behaviour rows, meaning either scrape volume too low or downstream moves ignore the tag.

Evidence that triggered the proposal

D — brain/ARCHITECT_MEMORY.md S203 close: revealed-demand → costly observed behaviour
T — daily digest items on agent reliability + dental/estate/field-service pain

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	2
blast radius	2
composability	3
reversibility	2

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
2026-06-21 04:15	meta_council_verdict
2026-06-21 04:12	meta_argument
2026-06-21 04:07	meta_filter_score
2026-06-21 04:03	meta_genesis