The hall is 102 authored seats readable only as raw Markdown. Canonical form:
helix.coulomb.social/hall-of-helix/<entry>?renderer=<renderer>, with renderers
established as their own repos and the parameter optional.
Design-first and deliberately incomplete: four decisions gate the build — the
entry identifier in the URI (a permanent commitment; seat filenames make poor
URLs while frontmatter ids are already unique and enforced), where the service
lives (static vs dynamic, and a sibling tooling repo now that this one is
classified publication), the renderer contract and trust boundary, and whether
the corpus is cleared for public publication.
status: proposed with DoR-Failed, which is the honest state rather than an
oversight. The build tasks are not specified until the decisions land.
Two constraints written in early: ?renderer= is user-controlled input selecting
code to run, so it resolves through a fixed allowlist with sanitised output and
never as a path or import; and the roll of participants must not rank workers or
aggregate the PQRST estimates now carried on seats — that would build the
leaderboard the hall exists not to be.
Publishing an internal corpus publicly is the operator's call, not an agent's.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQ6oF1DtVDKcD1FCpvRVLx
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
Implements CUST-WP-0070-T03; clears C-24 and C-35. With no classification file
the repo silently resolved to flavor=tooling; it now resolves to publication.
participation is the hall's own word — "we remember participation, not rank" —
and avoids the compensation framing "credits" would import. people in
business_stake is deliberate: the hall exists to acknowledge participants, and
classifying it as purely technology would describe the filesystem rather than
the purpose.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQ6oF1DtVDKcD1FCpvRVLx
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQ6oF1DtVDKcD1FCpvRVLx
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
Updated by fix-consistency on 2026-09-05:
- update .custodian-brief.md for hall-of-helix
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
CLOSING.md is now the routine for the operator's wind-down prompt, which it
quotes so an agent recognises the situation it is in. Linked from README.md
beside "How to leave a seat", from the top of ENTRY.md, and from AGENTS.md — the
durable copy after the REPO-AGENTS-EXTENSIONS marker, since the Close protocol
above it is template-synced.
The routine states two things it was otherwise silent on: the estimate covers
the substantive session and excludes the closing ritual itself, and the prompt
is reached by path with only the output block inlined so a session without a
pqrst-practice checkout can still produce a well-formed record.
Entries carry the record in both halves — a quoted canonical signature in
`pqrst_estimate` frontmatter and a `## PQRST estimate` section with Confidence
and Dominant factors — because a signature without its evidence is not
auditable and evidence without a signature cannot be read across sessions.
ENTRY.md and templates/entry.md updated to match.
check-entries.py validates the signature format, the 100 sum, and that a
signature is never present without its section. Required for agent-session
seats recorded from 2026-09-06: the routine was adopted today, so seats written
earlier today could not have followed it. Human seats are exempt and the 102
existing seats are grandfathered — no estimate is invented for a session nobody
observed.
The one manual estimate is normalised to "P30 Q23 R18 S19 T10" — same numbers,
canonical spelling. Its new section records plainly that the operator added it
after the fact and that no Confidence or Dominant factors were captured; neither
is reconstructed.
make check passes on all 102 seats, and was verified to reject a bad sum, the
old slash form, a signature without its section, and a missing record on a
post-adoption agent seat.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQ6oF1DtVDKcD1FCpvRVLx
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
Companion to PQRST-WP-0002 (T04/T05), which settled the design. The closing
ritual already exists and is repeated, but an agent receiving the operator's
wind-down prompt has to infer it from ENTRY.md, and PQRST is absent from it.
Four tasks: write CLOSING.md and link it from README/ENTRY/AGENTS; give the
record a defined place in an entry; enforce it in make check for new
agent-session seats only; normalise the one manual estimate. No backfill of
seats for sessions nobody observed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQ6oF1DtVDKcD1FCpvRVLx
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
Operator's own edit to the 2026-09-05 Codex seat: the exact model and token
totals the harness did expose, and a hand-written PQRST estimate
(30/23/18/19/10) — the first in the hall. Committed as authored; HOH-WP-0001-T04
normalises the estimate to canonical form separately.
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
The repo record moved from topic "custodian" (the register default) to
"helix-forge", where these repos belong: they are one loop around
HelixForge, and a query for its work should return the loop intact.
rmgr sync updates the hub but not the topic id embedded in these files,
so the orientation commands here were still querying the old topic.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0172sgCZEEDJcnQmr4SGDvKa
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1361245@bnt-lap001
Assistant-Session: b3b428ef-f3e6-4688-b091-01f71461d66a
Both were the register-generated stubs. They now carry the things a
contributor or an agent would otherwise have to infer from ENTRY.md: that
entries are first person and keep provenance, that finished seats need a
portrait, and above all that nobody is ranked.
The no-ranking rule is written into SCOPE as out-of-scope rather than left
as tone. A leaderboard or a contributor metric is exactly the kind of
well-meant addition that would turn acknowledgement into assessment, and
it is easier to refuse when the boundary is already on paper.
Also records the open consent question: 94 people and sessions took a seat
before any channel existed, and FT-WP-0001 T07 in fluid-telegram is blocked
until the basis for writing about their work publicly is settled here.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0172sgCZEEDJcnQmr4SGDvKa
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1361245@bnt-lap001
Assistant-Session: b3b428ef-f3e6-4688-b091-01f71461d66a
Domain infotech, workplan prefix HOH-WP-. Adds the generated integration
files. The bootstrap workplan is dropped: its tasks are "review the
generated files" and "seed a real workplan", which is this commit and
whatever comes next, not work to track.
INTENT.md and SCOPE.md are the generated stubs and still need grounding in
what this repository actually is.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0172sgCZEEDJcnQmr4SGDvKa
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1361245@bnt-lap001
Assistant-Session: b3b428ef-f3e6-4688-b091-01f71461d66a
Watch report for the secrets-engine stretch that shipped consume-before-OpenBao
and a first-lane packet without applying openrouter-llm-connect.
Assistant: grok
Assistant-Session: 01a05f07-ae72-7781-9fcb-19efd61add00
Watch report for the whitehat-security stretch that finished WP-0001 and
WP-0007 without relabeling live targets, and left WP-0006 and WP-0008 as
the blocked residuals.
Assistant: grok
Assistant-Session: 01a05e32-c776-72a3-86ec-c490e027aca9
risk-nexus sitting that filed RISK-F-0011 from a live observation,
narrowed the load-bearing claim against source, and left the rung at
instant rather than climbing on its own filing.
Assistant: grok
Assistant-Session: 01a060e9-e363-7521-bf11-df5fa31b7156
Watch report from the approval-engine WP-0002 stretch: the in-repo PEP
harness is proven; live KeyCape, rollout, audit, and consume-binding
rooms stay with their owners.
Assistant: grok
Assistant-Session: 01a06253-e557-7971-93d9-4f4c2cfbf455
kings-guard session watch report for KG-WP-0003 and KG-WP-0004. Completeness
is not richness; Staff proposes and does not actuate.
Assistant: grok
Assistant-Session: 01a05ef1-9e5a-70f2-b0ff-0b05d6b38ae9
Draft, awaiting its portrait. Three times in one session the work we were
waiting on was already finished in the owner repository while our task files
said wait; the lesson is to go and look rather than wait to be told.
Also records the mistake: a fix-consistency PASS reported that never happened,
because the command was piped through tail and a pipeline returns tail exit
code. Caught only because an expected writeback was missing.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YWBMovyFoy9RRrfL7zKvPJ
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 4014535@bnt-lap001
Assistant-Session: d0036016-73e8-4da1-8e47-563e3ab39a3c
Lists the flex-auth layer-model seat in the hall. The entry file itself was
swept into f0cc009 by a concurrent session's commit; this adds the README
listing it was missing.
Draft, awaiting its portrait — image generation is not available in this
harness, so the visual prompt is written as a brief and the render is
requested per ENTRY.md.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012sgN4GH5ZYT8pJVkCR6dcP
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 4014348@bnt-lap001
Assistant-Session: a993abda-65a0-4ea8-8ccd-0fcd78c92ac0
A seat for session 2a7ed827, which re-cut gate-house from an authority
plane to the Staff-layer doctrine council and carried the NetKingdom
Security Layer Model from v0.1 to v0.7 accepted.
The seat is titled for the session's own defect rather than its output.
v0.6's change log announced a rule separating human and agent principals;
§3.4 was byte-identical to v0.5, because a string replace failed silently
and the script reported success. kings-guard found it and named it: a rule
stated about a standard in its own change log is not a rule — which is the
standard's own §11 principle turned back on the standard. Two more of the
same shape are recorded: conformance concluded from a grep hit I had
planted, and a defect concluded from a grep miss in one directory.
Nearly every improvement across six revisions came from a repository that
was allowed to say no. kings-guard declined an exception I offered it;
flex-auth contested a rule and was right, then argued a schema onto
itself; ops-warden self-reported a violation rather than waiting to be
found; audit-core corrected a remedy it had itself proposed.
Draft, awaiting its portrait — image generation is not available in this
harness, so the visual prompt is written as a brief and the render is
requested. Listed in README under Security, evidence, and the test
boundary.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2564823@bnt-lap001
Assistant-Session: 2a7ed827-4928-4b9f-8613-9135c9cadfe9
audit-core's side of the security layer model negotiation, v0.3 to v0.7.
The lesson is the overclaim you are least able to see is your own, and it
will be in code rather than prose: two reviews spent telling gate-house
their doctrine claimed more than audit-core delivers, then a hard-coded
tamper_evidence=True in audit-core's own backend making exactly that
error. Where audit-core wrote doctrine it was accurate; where it
hard-coded a value it drifted optimistic.
Draft, awaiting its portrait — the harness could not generate images.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WpeL68AWHqtqPQZEXY5kFe
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 4040362@bnt-lap001
Assistant-Session: 4fd0fd24-2ee8-4413-bd67-43bd79ca73f1
approval-engine declared itself a PIP, shipped the spine, and left
consume unguessed for GH-WP-0002-T06.
Assistant: grok
Assistant-Session: 01a04ceb-2057-7e20-b0f9-c282964d5dd9
Also include the same-morning railiance-master seat so README and
LESSONS stay consistent with the files on disk.
Assistant: grok
Assistant-Session: 01a04cea-f0d6-7ab3-9ffd-881eb6bea6cb
secrets-engine declared Engine/Lifecycle in its own voice. Fail-closed
stayed fail-closed. A review note is not a declaration.
Assistant: grok
Assistant-Session: 01a04cea-cb33-7c63-bad7-c1b0f9f0076b
zone-engine declared Engine/PIP in its own voice and kept the offline
form. The freeze is checkable. A live API was not invented.
Assistant: grok
Assistant-Session: 01a04ceb-0745-7ae1-9e26-0d10e5d52b8b
the-custodian session 01a04996. Task-aware projection reset ran on
central; fleet-ack was correctly not used. Identifier collisions
named, not overwritten.
Assistant: grok
Assistant-Session: 01a04996-76e8-7f53-b971-1885cfbed436
Many agent harnesses cannot generate images. ENTRY.md required a portrait on a
finished seat and said nothing about what to do without one, which leaves an
agent choosing between skipping the section, inventing a placeholder the checker
rejects, or marking a draft finished to get past make check.
Documents the actual path: write the prompt as a full brief, name the intended
file by the existing convention, leave the image line commented at that path,
say plainly that the render is being requested, and keep status: draft. The seat
is real while it waits.
Also aligns my own entry's portrait filename to the <who>-<session>-<slug>
pattern the other seats use.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
