Applies references/tool-calling-cut.md section 5 under the section 8 rulings
(Q1 A, Q3 C, Q4 B). Briefs: agents wait in the foreground in calls of at most
270 s and never end a turn before the report; commits from Git Bash; every
dispatch names its model; agents cap at about 300k context or 150 calls.
SKILL.md: Self rotation rule, notify-before-report defect, Shared tools
section, sizing by calls, Yggdrasil limits corrected to the script's 5 slots
and 6 GiB. tools/INDEX.md lists ygg-verify.sh. Changelog quotes the rulings.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Operator ruling eureka-substrate:ruling:gap-home. The 19 gap-* follow-ups
moved from idunn-watchdog by superseding resolutions; the recipe and two
cited ids now name the new root.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
cargo-mutants --jobs N workers all built into /src/target and tested each
other's binaries, so parallel kill counts were noise (idunn-watchdog Soul
s3). Cargo's default target dir is already inside /src.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Slot queueing, not compilation, dominates a Soul pass. Soul now reruns
the tests the cut touches while probing, runs the full suite once at the
end with its mutation run, batches probes, and mutates in parallel.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
sccache 0.18.0 as RUSTC_WRAPPER with a shared eureka-sccache volume.
Idunn lib test build: 51 s cold, 29 s warm (83/83 hits). Slot wait, not
compilation, is the larger cost.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Soul proved bash -o pipefail -c "bash job.sh" leaves the script without
pipefail; a failing piped test came back exit 0. Probe: false|cat exits 1,
true|cat exits 0.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The gap table in campaign-state.md duplicated eight typed follow-ups; it now
gives the query instead. The first campaign no longer admits the list; every
campaign runs the query. Imagination edits the model page when a probe
changes a row. Stewardship is universal (operator, 2026-09-30).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Self's triage of Soul pass 2 on 272f5ca:
- Soul's rehydrate runs rulings in force, so standing operator directions
(including ones admitted after the spec) reach it, and it claims against
them. A verdict claim has no ruling reference, so Soul starts the claim
text with the ruling id; recorded as a substrate gap (epiphany-pipeline).
- Gaps table: a cold semantic embed exceeds the client's 15 s deadline
(Huginn, with the embedder).
- Self does not TaskStop an agent halted on Unavailable; it holds the
unadmitted record and is resumed when the organ answers.
- A fix batch's cut_report is the next attempt on the finding's in-force
cut_spec, on that spec's branch; landing elsewhere needs a revised spec
first (SKILL step 5, Hands brief).
- mutations holds survivors plus the kills Soul should rerun (at most 64);
totals go in verification evidence.
- InvalidInput and TooLarge are caller-fixable and retried after fixing
the call; only Unavailable after a retry and other errors stop.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Self's triage of Soul's first pass on hands/cut15-typed-state:
- Soul views every ruling the cut_spec cites and makes one claim per
ruling, beside the promises; Hands' self-report never bounds the pass.
- Only Self closes a finding Fixed, after a Soul pass on the fix holds.
Finding and verdict reads filter faculty Soul; faculty being
attribution-only joins a new substrate-gaps table in campaign-state.md.
- A fork before Hands' first commit ends the pass with the question
alone; the blocked-spec check reads questions raised in a spec.
- One rule for an organ that does not answer: missing tools stop, one
retry on Unavailable (admit replays are safe), then a resumable stop
that never sends the record as prose.
- Survivor triage goes in deviations, one entry per survivor, because
MutationRecord has no reason field (a recorded gap).
- The target document is written and committed before the campaign and
target cite it; Self's checklist names working_branch and target_doc.
- Operator directions are rulings with no answers and the words verbatim.
- One Rehydrate definition with a no-campaign / unknown-slug branch;
per-brief recipes; Eyes reads the mind read-only; the postmortem
template sources from the mind.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
SKILL.md, briefs.md and README now route every faculty through the
instance's mind: Self calls whoami first and stops when the organ is
unreachable, admits stewardships, campaign, target and rulings;
Imagination admits questions and cut specs; Hands views its cut_spec and
admits a cut_report; Soul admits a verdict and its findings, staying
read-only on repos. Triage outcomes are resolutions and follow-ups, and
progress is a set of recipes instead of a status header. Briefs give ids
and recipe names and start with a Rehydrate block; they no longer paste
specs or rulings. "Record the substrate you needed and did not have" stays,
and its record is a follow_up. The errors-never-echo rule is unchanged.
Huginn Cut 15 (Epiphany notes/huginn-organ-cut.md at 74804d83), under Q-H6 A.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
references/cut-map.md becomes references/campaign-state.md: the
eureka-state tools, the typed document set with its keys, the admission
rules that shape a batch, the resolution matrix, the selection vocabulary
(aliases, roles, hops, projection, paging, semantic), and the recipes that
replace the status header and the deleted open_items, rulings_in_force and
history presets. The prose-map template shrinks to body facts, the model
page and rationale.
Huginn Cut 15 (Epiphany notes/huginn-organ-cut.md at 74804d83), under Q-H6 A.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A Hands pass on Aetheria Cut 12.3 edited and built the main checkout by
using absolute Read/Edit paths, while its shell sat in the worktree.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Operator ruling, 2026-09-25: Epiphany and Aquarium call this organ Life
(role id `reorientation`), and it is "a much better fit as the actual
load-bearing organ". The eureka-site landing page already says Life.
SKILL.md (frontmatter description, faculty table, dispatch lines, step 6,
model allocation), README.md and briefs.md now say Life. The role itself is
unchanged. SKILL.md defers to global doctrine for the agent type, which the
operator owns and which still says mind-steward. Dated records keep the old
name: changelog entries as written, a note on the 2026-09-15 Epiphany
comparison, and "then called Mind Stewards" in the CultCache postmortem.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Operator direction, 2026-09-25: moderate inference spend mainly by making
cuts smaller, so each Hands agent carries less context. Sonnet degrades at
about 0.5M tokens.
SKILL.md step 3 now owns cut sizing: Self estimates the brief, the source
Hands must read, one verification and one fix round, and the item count,
treats 0.5M as the danger line, splits when the estimate passes about half
of it, and checks the reported token total afterwards. The Self-owned
clauses ("Self sizes a cut", one fix batch per file) moved out of the Hands
brief template into step 3; the Imagination template's split clause names
the budget. Section 5 no longer frames the 2026-09-23 spend as misplaced:
the operator counts it as legitimate work, the regret being the model.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From the StreamPixels transport campaign, 2026-09-23 to 2026-09-24:
- SKILL.md section 5: quota is spent through scope. One Soul gate per cut,
fix batches only for critical-path findings, and narrow passes for
small deltas.
- briefs.md: one fix batch per file (800k and 550k runs); require a
non-zero test count for each named file; a failure called
"pre-existing" still needs a one-line cause.
- changelog: the evidence, with StreamPixels commit refs.
Staged by path. The unrelated uncommitted Ghostlight hunks in briefs.md
and changelog.md are left in the working tree.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A brief said "use ygg-verify.sh" where earlier ones gave the full path. The
agent could not find it, verified the whole batch on the operator's
workstation instead, and said so plainly rather than claiming the bar was met.
A name is a guess; a path is an instruction. The brief must also say what to
do when a named tool is missing: stop and report, never substitute, because a
substitution can silently relocate work onto a host the load budget forbids.
Second scar. A redundancy ruling of Self's was wrong for the second time in
one campaign, and this one shipped: a guard was deleted on the premise that
aliases are unique per descriptor, which the source contradicts, and a legal
document shape then faulted on every hop path. Both Self and Hands reasoned
from the same unchecked property. Build the input that would need the guard
and watch the other authority handle it, or the argument is just the claim
restated.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The same commit mutated three times at -j4 gave three different survivor sets,
while every -j1 run reproduced the same one. Likely the shared cargo target
directory under concurrent builds, which is this file's existing scar wearing
a new hat.
A score survives concurrency roughly intact, because a genuinely killed mutant
stays killed. A survivor list does not, and survivors are what drive rulings.
Stryker's concurrency flag is in the same position, so figures taken at four
in earlier campaigns are provisional; the rulings they informed rest on the
hand-confirmed mutations beside them.
Second entry: three fixtures in two days passed by coincidence rather than by
rule. Values whose bit pattern happened to match the assertion, hashes that
happened to sort the right way, a file wrapped in a directory so a different
path ran. Breaking the rule and watching the test fail is what separates these
from coverage, and it is already in the brief.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Three Soul passes over one file and a selection batch found the same thing
three ways. Every artifact-digest test wrapped its file in a directory so a
different code path ran, while production passes a bare file immediately
before launch. A row-tiebreak test passed with the rule reverted and swapped,
because of which real hash happened to sort first. An xattr test pinned
presence while the privilege lives in the value.
None of these looked like gaps. They looked like coverage, which is why they
survived. Write the fixture at the shape production uses, and derive keys from
ids discovered at runtime rather than hoping their order cooperates.
Second scar, same campaign: a counter was an honour system, so it became a
port, and the port is an honour system one level up. Soul restored the bug
around it with the suite green. Where a rule says all access goes through one
place, the enforcement belongs in the build, not in a habit. If the fix is
another thing to remember, it is the same defect one level up.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Three scars from one Idunn batch.
A test pinned a cost regression with a ratio whose clamp always fired, so it
was really a fixed 200 ms threshold, on a host that now runs three jobs at
once. Clean code had already measured 198.9 ms. The reported 33x separation
was an artifact of one pair straddling the clamp; the real figure was 1.63x.
Count the calls instead, and treat a reported ratio as a claim to check rather
than a result to accept.
Two fixtures in the same batch would have lied, and mutating caught both. A
setuid fixture chowned after chmod, which silently clears the bit. An
observe_frozen test tampered where a different check also fires, so it stayed
green with the check it pinned deleted. A third term could not be pinned
honestly at all, and Hands deleted the fixture rather than keep one that
implied otherwise.
Last, Self ruled a mount carry nosuid without checking that Docker offers it.
It does not, and the stronger mitigation was already in place. A ruling naming
a flag is a factual claim about a tool.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Soul reported four containment checks where one sufficed, each surviving
deletion on its own, and Self ruled three deleted. With all three gone a
symlink whose whole target is ".." at the root escapes containment. The method
was sound; the conclusion did not follow from it. A redundancy finding has to
be probed at the combination that will actually be deleted.
A Hands hand-trace caught it, because the brief says a deletion judged unsafe
comes back with evidence rather than being quietly kept. That rule stays, and
it applies to deletions Self ordered.
Second scar, same batch: Soul's HTTPS rig had evaporated by the time Hands
was told to commit it. Probes stay throwaway, but once Self rules one becomes
a committed test it is no longer scratch, and the handover has to happen while
it still exists.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A QUIC test suite passed every scenario on Windows against an unrelated
msquic.dll picked up from PATH, a tenth the size of the pinned build. The
same missing copy failed loudly on Linux. Windows' search order makes silent
substitution the default failure mode.
Two rules follow. A verification step that loads a pinned native library
reports what it actually loaded, by size or hash, rather than only that the
run passed. And a defect found on one platform gets checked on the other
before it is closed, because both earlier fixes for this lived inside
if(NOT WIN32) and nobody looked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two Hands were dispatched into one working tree. The second switched the
branch out from under the first's running build, then found an uncommitted
edit it had not made and stopped rather than forcing the checkout. Nothing was
lost because of that refusal, not because of anything Self did.
The rule was already written and Self ignored it, so the fix is not a louder
warning to Hands. A brief that names a repo path without naming a worktree is
a defect in the brief.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two scars from one Hands report. The map it read was five days old because
Self commits maps to whatever branch it is standing on; SKILL.md now says
main, and says every brief names the map's branch.
The same agent refused a mid-task instruction from Self that it could not
distinguish from an injection. The instruction was genuine. The fix is not to
make the agent more trusting: scope expansion should arrive as a new dispatch,
not appended after a tool result.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A Mind Steward pass falsified SKILL.md's claim that the stopgap runs at most
two jobs at once. The operator raised it to three this morning and the script
carries that; SKILL.md did not. An agent steering by SKILL.md would have
under-parallelized verification and quietly contradicted an operator ruling.
The changelog's entry for the same day is worse: it records caps of 6 CPUs and
16 GiB, which match neither the script nor SKILL.md. I cannot tell whether
that was ever live. The correction says so rather than inventing a history.
Both surfaces now name ygg-verify.sh as the owner of its own numbers. Prose
that restates a running tool's configuration goes stale in silence, which is
how three surfaces disagreed inside one day.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Operator ruling 2026-09-22: better nothing than a harness that punishes
refactoring. Behavioural tests plus the ecosystem's mutation tools on a cut's
diff; Soul's hand mutants stay one-off probes. The stopgap image carries
cargo-mutants instead of pwsh and is tagged by its Dockerfile's hash.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Hands and Soul measure suites with Stryker.NET, cargo-mutants, StrykerJS or
mutmut scoped to the cut's diff, and triage every survivor by name. The
hand-written anchor harness is demoted to code no tool reaches. Evidence in
the changelog: Aetheria's 23 harnesses stranded on refactors and one anchor
silently re-targeted; a Stryker spike killed everything they defended and
found the splash-handedness bug they missed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Records the three defects Soul's H14 pass found and this pass fixed:
the startup-repair marker check for H1's kept sidecar, the unique
overwritten-copy naming, and the case-sensitive content/hash/no-op
comparisons. Points at the fixing commits.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Restore-Targets never checked what a target's bytes actually were before
restoring over them, so a build step or stray edit landing mid-run or
between entries was overwritten without a trace (Soul's finding on the
Huginn memory-organ Cut 10 fourth fix batch, 2026-09-22; that same batch
had lost a Hands edit this way). Restore-Targets and the entry loop's
pre-write step now hash the target first: a match against the M0 original
or this entry's own mutant restores as before, anything else is saved to
<target>.eureka-mutation-overwritten, warned about loudly, and fails the
run with a non-zero exit and no further entries.
Demonstrated in the scratchpad with a throwaway repo whose test command
appends a line to the target mid-run: pre-fix the run went green and the
target came back pristine; post-fix it failed loudly and kept the
appended line. Recorded in references/changelog.md.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A Ghostlight Hands agent amended and force-pushed a kernel commit while
Self pushed map commits to the same branch. The briefs and the scars
list now forbid it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>