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>
Two worktrees sharing one cargo target get one artifact hash, and a plain
cargo test in the older checkout ran the other's mutant binary. Found by
Soul on the Huginn Cut 10 second fix batch.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
One line took three passes to pin. The suite proved the wait was not one
constant, then a scenario proved it was not any constant, and a clamp walked
through both. Capping a wait so shutdown gets noticed is the most ordinary way
that line will ever be broken, and it is a function of the argument rather
than a replacement for it.
So when a rule says a value is derived from an input, one mutant has to be a
function of that input, and the probe values have to sit where such a function
would show. Constants are only ever the first case.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Twice in one day a rule was honestly recorded as impossible to pin, and twice
the claim was wrong: one fell to a probe built from the crate's own public
surface, the other to a client opening a closed port in fifteen lines. An
unreachability claim is a hypothesis and gets falsified like any promise, so
it is written as not yet reached and the next pass opens by reaching it.
The same pass found why a rule kept being pinned by constants. The scenario
held its callers after the wait whose duration was the rule, so every mutant
of it landed behind the observation, and a hard-coded two seconds walked
through the whole matrix on both targets.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Two ways a green sweep lied on the same afternoon. A bridge's whole mutation
history lived in scratchpads that no longer exist, so the rules it defended
were defended by nothing anyone could rerun; a probe that is the only killer
now gets committed by the next Hands pass. And a loosening that could not fail
was quietly swapped for an easier target, leaving an instance check that
survived comparing only lengths and only first bytes, because no fixture pair
had ever shared a length. An unfalsifiable loosening is a finding about the
fixtures, and the fixture is what gets fixed.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Re-cutting came from questions answerable on day one and asked on day three,
not from maps that lacked detail. A model table now precedes every cut map,
one row per persistent kind, and no cut is mapped while a cell is empty. The
operator's forks are gathered once rather than discovered across five cuts.
In the other direction, the per-file anchors are required only where the code
exists and they say what not to touch. Transcribing the body of code nobody
has written yet is a map at full scale, and the only spec complete enough
there is the code. Cutting faster means less prose per cut, not more code.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Most later Soul passes found rules the suite could not see rather than
defects, because Hands proved each rule with a revert and Soul with a
loosening. Hands now does both. Reports carry findings, promises and
numbers and nothing else, and a second pass on a cut is scoped to the fix
batch. Operator-approved after a cost review of one day's campaigns.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Three lessons from Ghostlight L1.
1. Three agents ended their turns while their own detached cargo job was
still running, even though the briefs already said to wait for long jobs.
The stall stopped only once the briefs named the mechanism: block inside
a tool call.
2. A test built on a random draw passed by luck, failing 3 of 40 looped runs.
3. An operator's question about why a mechanism works exposed a defect
that had been present all along.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
"Default" inherits the root session's model, so once the root moved to
Fable every Hands and steward ran on Fable against the skill's own
allocation. The operator noticed before Self did. Self names the tier on
every dispatch from now on.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Three passes in one day ended their turn on "waiting" with the rule already
in their brief. The rule named the outcome and not the mechanism, and an
agent that has started a detached job reads "wait" as "stop and be woken".
Both briefs now name the loop.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Two consecutive Soul passes on Cut 6b ended their turn while a mutation run
or a build was still going, delivering no findings until Self resumed them.
The Hands brief has carried this rule since the Ghostlight run; the Soul
brief now carries it too.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A Soul pass ran a mutation that changed nothing and it killed a test. The
harness's text round-trip had collapsed a non-ASCII literal, so the
corruption alone failed the test and every mutation through that path would
have reported a kill. A working suite and a broken one look the same from
the verdicts; only a control tells them apart.
The audit that followed found every committed suite lossless and the
corrupting script inline and gone, which is the standing "no artifact on
disk" finding applied to Soul. So the rule binds Soul's harness as well as
Hands', and the Hands and Soul briefs both carry it.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Both rules come from the Ghostlight L0 run, which hit the missing typed-state
primitive six ways and nearly lost the requirement each time, because every
workaround worked. Doctrine already says not to wait on a service that does not
exist; nothing said to leave evidence while working around it. Now it does.
The second is a verification defect, not a state one. A Mind Steward reported a
stale phrase gone because a line break had split it from its grep. Prose
reflows, so an exact search over it has the same limits as any other text
scanner, and a check that cannot see its target closes the question instead of
answering it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The Soul template now attacks constructibility at sealed boundaries (a
derive is a public constructor, and on stable rustc a compile_fail test does
not pin its error code). It also asks for forgeries shaped like real values
and treats text scanners as tripwires with stated limits.
The Hands template now says to wait for long jobs instead of reporting a
to-do list, to restore mutations without git checkout, to measure warnings
from forced rebuilds, and to prefer semantic tools for semantic properties.
The fork rule now weighs proportion: a fork guarding only against the
project's own code gets a default and a recorded follow-up.
Evidence: Ghostlight's library extraction postmortem, recorded in the
changelog.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Soul checked the committed history. The script already threw on a missing
anchor, the affected mutation existed only in the working copy, and every
committed verdict was real. The rule stands, and gains the uniqueness check,
but the incident was narrower than first recorded.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two rules from the Eureka campaign's own cuts. A deletion can take a live
rule's only test with it, so a cut that deletes must list every rule that lost
its test and either delete the rule or pin it in the same cut. And a mutation
whose anchor never matched is not a passing mutation: a multi-line anchor
matched nothing on a CRLF tree, reporting a verdict it had not earned.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The operator stopped a design in which a repo owned the pipeline store. Three
Soul passes had gone into a per-clone lease, git-directory resolution and
committed attribute checks, and the resolution still landed a store in an
unnamed directory. An instance owns its mind instead, and a service owns the
state.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Operator ruling: Eureka has no Persona. Self is the operator surface, and a
blocking question may be pushed through whatever notification MCP the user
configures, so Eureka owns no transport. Answering over a chat channel is a
later campaign.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The rules come from the first Eureka pipeline-state cuts. Soul could not rerun
mutations that were only named. A digest captured from new code proved nothing
about the old code. A detached mutation script died silently on a parse error.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Eureka is extracted from the Aetheria CultCache migration and is the Claude
Code counterpart of Epiphany. It covers the faculty loop, brief templates,
the cut map shape, the postmortem template, the worked example, a dated
comparison with Epiphany, and a changelog tying each rule to its evidence.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>