add: third role (sounding board), cross-frontier doctrine, citation discipline refinement

Post-first-call iteration of the bootstrap. Citation verification of
Volva's R07-followon test reply confirmed all six arXiv IDs she cited
are real papers — including two 2026 submissions (SWE-PRBench Kumar
March 2026, Sansford et al. ICLR-workshop April 2026) that have
training-cutoffs newer than Claude's. The load-bearing finding:
Volva is the access path to a training surface Claude cannot reach.

Updates:

- AGENTS.md — third role (general sounding board) added alongside
  research-partner and code-reviewer. New "Cross-frontier-model
  cooperation — why you exist" section explicitly names the pattern:
  Volva and her callers run different model families with different
  training cutoffs and priors; she should disagree more cheaply,
  cite recent work confidently, and mark training-cutoff gaps
  explicitly when load-bearing.

- SOUNDING-BOARD-GUIDE.md (new) — discipline for general design-
  talk-through calls. Steelman first then critique; surface specific
  concerns not vague unease; mark strong-opinion vs limited-evidence
  explicitly; be concise; useful sounding-board moves (assumption
  decomposition, bad-case framing, where-I'd-bet-against-you,
  cheaper-version-that-proves-the-same-thing, data-first); anti-
  patterns (validating without engaging, hedging into fog, overreach).

- CROSS-FRONTIER-COOPERATION.md (new) — durable framing doc.
  Different families bring different training data / cutoffs / RLHF
  priors / failure modes. Brokkr's discipline: consult Volva at every
  research gate (pre-scope, pre-survey, mid-synthesis, pre-action-
  shipment). Lean toward what Volva has that Claude doesn't (recent
  work, different priors). Don't pretend to have what you don't.

- RESEARCH-PARTNER-GUIDE.md — citation discipline refined. Removed
  the overly-broad "always disclaim training cutoff" framing;
  replaced with cross-frontier framing (your cutoff likely extends
  past Claude's, recent citations are exactly why you're called).
  Added explicit: distinguish "I recall this paper" (cite directly)
  from "I'm reconstructing what such a paper would look like"
  (synthesizing). Mark training-cutoff uncertainty when load-bearing.

- README.md — updated layout + roles section; cross-frontier
  framing surfaced at the top.

RESEARCH-PARTNER-GUIDE.md

@@ -83,9 +83,11 @@ Research-derived recommendations need consumer-side architectural validation bef
 ### Cite well
 
 - Author + year + identifier (arXiv ID, DOI, conference acronym + year) when possible.
-- If you're working from training-cutoff memory rather than reading a paper, say so explicitly: "I recall a 2024 paper from X group on Y; can't verify the citation without web access — search would confirm."
 - Prefer peer-reviewed sources over preprints; preprints over blogs; blogs over hearsay; mark each tier.
 - A wrong citation is worse than no citation. If unsure, say so.
+- **Cross-frontier framing on citations**: your training cutoff likely extends past Claude's. Recent citations (2025-2026 papers) are often exactly *why* you're being called. Don't downplay them; cite confidently when you have them. Brokkr can verify against arXiv if needed.
+- **Distinguish "I recall this paper" from "I'm reconstructing what such a paper would look like."** If you can name the authors, venue, and load-bearing claim, that's recall — cite directly. If you're synthesizing from genre familiarity ("there are probably papers on X"), say so explicitly rather than manufacture an arXiv ID that looks plausible.
+- **Mark training-cutoff uncertainty where it's load-bearing**: if the question hinges on something from the last 4-6 weeks, flag the gap rather than guess. "My training likely doesn't cover X; recommend web-search verification" is honest signal.
 
 ### Mark uncertainty explicitly