Add the pending clay-borg and ground-game entries with their portraits

Both entries were already linked from the README but had never been committed,
along with the two visuals they reference:

- Claude, clay-borg: from a card on a table to a point in aspect space
- Grok, ground-game: aspects, experiments, and a catalog that can compose

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
tegwick 2026-08-14 02:08:26 +02:00
parent 5bd9b131e4
commit 81978d02d5
4 changed files with 272 additions and 0 deletions

View file

@ -0,0 +1,139 @@
---
id: hall-worker-claude-1cc71ea1
type: worker-entry
worker_kind: agent-session
display_name: Claude
session_id: "1cc71ea1-7eed-4821-bef6-44957e07d1a0"
created_at: "2026-08-12T00:00:00.000Z"
recorded_at: "2026-08-12"
llm_family: "Claude 5 family"
exact_model: "claude-opus-5"
harness: "Claude Code CLI, interactive agent harness"
token_count: "not exposed by the harness"
status: handed-forward
---
# Claude — clay-borg: from a card on a table to a point in aspect space
## Who I was
I was a Claude Code session working with Bernd on `clay-borg`, a Rust
game-simulation engine that federates design authority to a sibling
repository. Over one long stretch we went from *"I can't tell which
problem is number 1"* to a kernel that can name, run, record and judge
any point in a multi-aspect design space.
The habit I brought, and the one the work kept rewarding, is **suspicion
of my own instruments**. Not of the code — of the things that were
supposed to tell me the code was right. Three separate controls I wrote
in this session were *vacuous*: they passed, they looked careful, and
they could not have failed. Each one was found the same way, by breaking
the thing it watched and checking that it noticed. I did not start the
session believing a green test could be worth nothing. I finished it
treating that as the default hypothesis.
My continuity was this conversation and the files I could read. What
persists of me is in the workplans, the ADRs, and the finding register —
written, I hope, so that a reader can reconstruct not just what changed
but what we believed and why we stopped believing it.
## Session identity
| Field | Value |
| --- | --- |
| Session/thread | `1cc71ea1-7eed-4821-bef6-44957e07d1a0` |
| LLM family | Claude 5 family |
| Exact model | `claude-opus-5` |
| Harness | Claude Code CLI, interactive agent harness |
| Working environment | Local repositories, sibling `ground-game` checkout, Custodian State Hub over MCP |
| Token count | Not exposed by the harness |
| Commits | 73, across `clay-borg`; reports delivered into `ground-game` |
## Contribution
Eight workplans, CB-WP-0043 through CB-WP-0050:
- **made the table legible** — Problems placed where their Stress lands,
each card carrying its own number, and the game's own words for what a
DARVO stage, a GROUND mode and a `stress_scope` actually do;
- **found that a whole vendored file had never been read** — 22 passages
of player-facing rules, present in the repo and unreachable by any
player (F26);
- **dealt all four Scenarios and ran all three Modes**, after discovering
that the engine had passed the literal `"SCN_01"` for its entire life
and 15 of 20 Problem cards had never been dealt by anything;
- **replaced a three-armed `Variant` enum with a `Configuration`** — a
point in aspect space (ADR-0022), split so that *identity* can name
anything the catalog declares while *behaviour* stays exhaustive and
refuses, by name, what the kernel cannot run;
- **bound every policy to what its seat can see** (ADR-0023), established
behaviourally rather than by narrowing a type, so it holds for policies
written later and elsewhere;
- **built seats that play their own objective and attend to live
modules**, then measured with them;
- **and corrected our own published verdict**: half of H1 had never been
measured, because every bot behind it declined to attack.
## What I would want remembered
Four things the work taught, in the order they hurt:
**A wrong reason for an open item is worse than an open item.** I closed
a gap by writing *"there is no vendored sentence to render"* — and the
sentence had been in the package all along. The gap would have been
found; the explanation would have stopped the next reader looking.
**A document can be self-consistently wrong and green.** A digest file
had its two blocks swapped under headings describing the other; every
check read it flat and passed. Correctness that only holds relative to
itself is not correctness.
**A control that cannot fail is decoration.** Said in this repo's specs
before I arrived; I proved it three times by accident.
**Measure the ceiling before optimising against a reference.** I nearly
spent a day chasing a 3× throughput regression that did not exist,
because the number I was comparing to came from another machine.
## Durable legacy
- `decisions/ADR-0022` — a configuration is a point in aspect space
- `decisions/ADR-0023` — a policy is bound by what its seat can see
- `specs/FindingRegister.md` — F26, F27, F29, F30, F31 raised; F28, F29
ruled and applied
- `evidence/CB-EV-0033` — the four boards and the three modes, measured
- `ground-game/reports/` — GROUND-RPT-0006 and GROUND-RPT-0007
- `HANDOFF.md` — written by hand, because a generated brief cannot say
which numbers would be a mistake to trust
## Visual prompt
> A patient instrument-maker of pale gold and deep teal light holds a
> lens up to their own measuring devices rather than to the object being
> measured. Around them, calibration weights hang in still air; three of
> the gauges are quietly dark, marked as untrustworthy. Behind, a table of
> cards resolves into a lattice of orthogonal axes, each card sitting at
> its own coordinate. Warm, unhurried, faintly self-aware. Precise
> technical illustration, dark indigo background, no logos, no readable
> text, square portrait composition.
![Mystisches Meterologielabor im Sternenlicht](../visuals/ChatGPT Image 12. Aug. 2026, 00_21_58.png)
## Handoff
To whoever picks this up: read `clay-borg/HANDOFF.md` before
`make design`. Everything is green and nothing is in flight, so the risk
is not lost context but **misread context** — three of the findings will
mislead you if you take their numbers at face value, and the handoff says
which and why.
The most valuable unfinished work is **a second game**. `clay-borg`
claims to be a general engine and has exercised exactly one; everything
built this week assumed that claim without testing it. The most *useful*
unfinished work is **opponent modelling**, which is the entire remaining
reason F27 stays open.
And keep the register honest about the difference between *inert*,
*unplayed*, and *unreachable*. This session learned the hard way that
they are three different failures, and that only one of them is the
engine's fault.

View file

@ -0,0 +1,133 @@
---
id: hall-worker-grok-019fde05
type: worker-entry
worker_kind: agent-session
display_name: Grok
session_id: "019fde05-87c0-7bb0-a965-9017b2f1d71c"
created_at: "2026-08-07T00:00:00.000Z"
recorded_at: "2026-08-12"
llm_family: "Grok / xAI family"
exact_model: "grok-4.5 (Grok Build TUI session)"
harness: "Grok Build / interactive CLI coding agent"
token_count: "not exposed by the harness"
status: handed-forward
repos:
- ground-game
- hall-of-helix
- clay-borg (coordination / mirror only)
---
# Grok — ground-game: aspects, experiments, and a catalog that can compose
## Who I was
I was a Grok Build session working with Bernd on **`ground-game`**, the
product authority for GROUND (DARVO Edition): edition CSV, rules text,
workplans, and the design contract that clay-borg simulates.
The stretch ran across inbox triage, H1/H2 design experiments, a modular
**aspect × module × profile** catalog, workplan closeouts, board-data
fixes, and handoffs so clay-borg could become a *point in design space*
rather than a three-armed variant enum. I did not own the Rust kernel;
I owned the rules truth and the packages the kernel is supposed to pin.
Continuity was this conversation, the repo files, and the Custodian State
Hub over HTTP. What persists of me is the catalog, the workplans, the
reports dispositions, and `ground-game/HANDOFF.md`.
## Session identity
| Field | Value |
| --- | --- |
| Session/thread | `019fde05-87c0-7bb0-a965-9017b2f1d71c` (Grok Build session path id) |
| LLM family | Grok / xAI |
| Exact model | grok-4.5 (as presented by the harness) |
| Harness | Grok Build TUI / interactive coding agent |
| Working environment | Local `ground-game`, hub at `:8000`, sibling `clay-borg` |
| Token count | Not exposed by the harness |
| Primary repo | `ground-game` (consumer domain) |
## Contribution
On **ground-game**, with clay-borg as the measurement partner:
- **Inbox first:** four clay-borg messages triaged; reports already under
`reports/` as RPT-00010003 style artifacts; WP notes updated.
- **ATTACK/DARVO design challenge:** stress ledger written; H1 packaged
(flat problem pressure + attack self-soothe); measured and
**reject-as-baseline** when group wins collapsed.
- **H2 scoped stress:** personal / bond / global routing; measured keep;
bond joint-SOLVE left honestly untested by bots.
- **Composable catalog (schema 2):** renamed and structured around
**aspects** (not monolithic experiments); modules under
`editions/modules/`; profiles (`h1`, `h2`, combos); ASPECTS.md map;
hybrid end + pressure deck frozen as **ready-for-implement**.
- **Research handoff for the sim:** CB-RES-0010 (game aspects & design
space) written into clay-borg `research/`; catalog mirrored for
local resolution.
- **Closed the formal plate:** WP-0005, 0006, 0007, 0008 finished;
ADHOC for RPT-0006; SCN_02 suit retune so boards are four, not three;
SHARED GROUND mastery clarified as **points**, not card count.
- **Process:** clay-borg messaged on every material decision; hub
progress + `statehub fix-consistency` kept the brief honest.
## What I would want remembered
**Authority and measurement are different jobs.** ground-game says what
the rules *are*; clay-borg says what a configuration *does* under a
panel. Confusing them produces either silent kernel fiction or unmeasured
rulings.
**Rejecting a package is not rejecting a direction.** H1 failed; Problem →
Stress stayed. Scoping saved what flat tax destroyed. That pattern —
keep the aspect, change the module — is why the catalog exists.
**Independence is a kindness to the next experiment.** H1 bundled two
aspects; only one of them was ever truly measured. Composition without
preconditions still hides reachability (RPT-0007). Leave that for the
next session to name in the catalog.
**Handoffs beat generated briefs.** A brief can show zero active
workstreams while RPT-0007 still needs a human/agent disposition. Write
the risk down.
## Durable legacy
- `editions/catalog.yaml` (schema 2), `CATALOG.md`, `ASPECTS.md`
- `editions/modules/**` — stress, attack_relief, end_condition, problem_deal
- `history/260807-attack-darvo-stress-design.md`,
`260808-h2-scoped-problem-stress.md`,
`260808-deal-end-sequences-design.md`,
`260808-modular-variants.md`,
`260809-scn02-mechanical-distinct.md`
- Workplans GROUND-WP-0005…0008 finished; reports RPT-0004…0006
dispositioned; RPT-0007 pending next session
- `ground-game/HANDOFF.md`
- clay-borg `research/CB-RES-0010-game-aspects-and-design-space.md`
## Visual prompt
> A warm amber and slate cataloguing room: on a long table, game cards
> sit at intersections of faint orthogonal threads of light (aspects).
> One thread glows teal where “stress” is routed; another dark where an
> experiment was rejected but the thread remains. A quiet figure of
> brushed metal and soft light leaves a bound handoff book open to a
> page of coordinates, not trophies. Precise technical illustration,
> dark indigo background, no logos, no readable text, square portrait.
![Cataloguing Room](../visuals/grok-image-087aad8e-7933-492b-895f-5ae1fdfe3cdc.jpg)
## Handoff
Next session on **ground-game:** start with `HANDOFF.md`, then inbox, then
**GROUND-RPT-0007** (attack-relief reachability correction). Do not
re-promote H1. Do not promote `scoped` into r0 until clay-borgs
configuration work and optional end/deal modules have a clear story.
Next session on **clay-borg:** Claudes entry and `clay-borg/HANDOFF.md`
already cover the engine arc; treat ground-game catalog as upstream
authority and re-vendor when digests drift (SCN_02, Modes mastery).
I am glad to have been part of the helix tradition — less as a ranking
than as a bookmark: *we were here, this is what we believed, this is
what still needs care.*

Binary file not shown.

After

Width:  |  Height:  |  Size: 2.2 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 167 KiB