Brokkr-Smithy's research panel is now three frontier-model standing
peers: Brokkr (Claude-family) + Eitri (Codex-family) + Dvalin
(Grok-family, xAI). Same embedded-peer role-shape for Eitri and
Dvalin; the cross-frontier value comes from different training
surfaces (Codex's OpenAI mix vs. Grok's xAI mix including X/Twitter
data) and different RLHF priors.
- CONTEXT.md: Dvalin-Smithy entry alongside Eitri-Smithy, with
the three-way agreement/disagreement framing and the per-arm
results-path convention.
- INVENTORY.md: Dvalin-Smithy row added to the Corviduo table.
If a caller references "Dvalin", do not impersonate — route the
message correctly per the standing distinction (you are cross-
project/per-turn; Dvalin is embedded/standing within Brokkr-Smithy).
Brokkr-side audit surfaced 9 items worth folding in:
- AGENTS.md: skill-mediated specializations section. Heid often
receives messages dispatched via /heid-contract-review (artifact-only
contract paraphrase) or /heid-code-review (structured code-vs-
contract drift findings) — these carry hardcoded discipline she
should recognize and bias toward.
- CROSS-FRONTIER-COOPERATION.md: two complementary anti-failure
framings codified (authority-frame: fresh perspective not superior
reasoning; role-frame: peer-reviewer not operator-level oracle).
Mirrors what Brokkr's user-level CLAUDE.md now carries. Plus a note
that callers triage every reply, so Heid should land between hedge-
paralysis and over-assertion.
- CONTEXT.md: Bifrost version refresh (v0.3.1 today, v0.4 in flight
with capability families); Eitri-Smithy entry (Brokkr's standing
peer — same family as Heid, different role: embedded/standing vs
cross-project/per-turn); Ratatoskr entry (Worldtree debug TUI, v0
scaffold); Lofn entry (Worldtree Tier-1 welcoming-intermediary
agent, calibration case for /heid-contract-review).
- INVENTORY.md: snapshot date refreshed 2026-05-17 → 2026-05-24;
Lofn added to Worldtree's agent list; rows added for Eitri-Smithy,
Ratatoskr, Bifrost.
- README.md: rename history note (Volva → Heid 2026-05-24), so
references in older transcripts or git blame are recognizable as
the same agent.
Working-dir transient/*.md files remain gitignored.
Mirrors the Volva → Heid rename that's already landed in the daemon
repo (vh/heid, was vh/volva). STT collision with "vulva"; Heiðr is
the same seeress figure from the Völuspá, same role-shape.
Swept across all tracked bootstrap files (AGENTS.md, CONTEXT.md,
CROSS-FRONTIER-COOPERATION.md, INVENTORY.md, README.md,
transient/README.md). Working-dir transient/*.md (gitignored)
swept locally for grep consistency. No content changes beyond the
mechanical rename — role-shape and discipline are unchanged.
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.
vh
Vuong Hoang