bug(unic-archon-dlc): `goals-check` counts, the precheck reads, and only the counter reaches `evidence.json`

Observed

Run 3 build c283e296. implement-review-precheck found 11 defects, one a documented standard breached (an invented icon glyph frozen into three snapshot baselines) and three acceptance criteria broken (13 snapshot on the wrong element, 24 focus ring missing a bound token, 25 no hover story). Five minutes later goals-check marked all 30 criteria COVERED, including those three: it counts that something exists that answers the criterion; the precheck reads what it contains. evidence.json certifies from verification and goals-check only, by the Box's own design ("a prompt that both judges and certifies grades its own homework"), so the run completed with verdict: pass and two empty failure lists. report.md § 5 carries the precheck's findings, marked "not posted — /pr-review posts".

Why it matters

Same family as #465: a run that found a documented-standard breach is indistinguishable at the exit code from one that found nothing. The reader who trusts evidence.json never opens report.md.

Evidence

• Findings register, § "G. What run 3 taught about the instrument", row G8: https://github.com/unic/unic-agents-plugins/blob/bcf688a/docs/research/2026-08-31-dlc-run-2-findings.md
• Run record and harvested artefacts: ~/Desktop/run3-parked/ on the maintainer's machine (artefacts-c283e296/report.md § 5 and § 6, evidence.json, build-state.json)
• Dispatch record: #457 from comment 5698289748 down

Not decided

• Whether evidence_policy should read the precheck's hard findings as a failure, or goals-check should read the precheck before marking a criterion covered.
• Whether the open-pr description must carry the precheck's hard findings (it carried the glyph flag unprompted in run 3).

Filed 2026-09-17 by wayfinder-orchestrator-10 from run 3's measurements. needs-specs: grill before dispatch.

Start with evidence.json, report.md § 5 and § 6, and findings register § "G. What run 3 taught about the instrument" row G8. Resolve whether evidence_policy consumes precheck hard findings or goals-check reads them first; done means a documented breach is represented in the certified result rather than producing a false pass.