benbrown/peltier.io
2
1
Fork 0
mirror of https://github.com/bdbrown4/peltier.io.git synced 2026-11-07 10:58:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

skill: attempt mode points at explain for the next hypothesis

Browse Source 
The attempt-mode guide predates crates/explain and stopped at the ROI
report. It now names the post-verdict step: run just explain on every
rejection before forming the next hypothesis — below-bar, null, and
regression are three different next moves the verdict string alone does
not distinguish. Advisory framing preserved (quote the record, not the
inferences). Mirror regenerated.

Verify mode needs nothing: consumer repos have no ledger, and its
read-it-honestly table already encodes the same narrative doctrine.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
benbrown
2026-07-20 10:05:41 -04:00
co-authored by Claude Fable 5
parent c42a46cc92
commit 3946438fd6
2 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/skills/peltier/references/attempt.md
+12
View File
@@ -84,6 +84,18 @@ dollars, and/or latency percentiles — every figure with its CI, workload, and
methodology printed inline. It flags any row that was not accepted, so a
rejected attempt cannot be laundered into a dollar figure.
## Explain — read this before your next hypothesis
just explain <run-id>
Advisory diagnosis of the row you just wrote (SPEC §3.7): *why* it won or
lost, derived solely from the ledger — deterministic, never on the accept
path, with everything beyond the machine record prefixed `inference:`. Run it
on every rejection before forming the next hypothesis: "real improvement,
below the ship bar", "indistinguishable from no change", and "a measured
regression" are three different next moves, and the verdict string alone does
not tell you which one you got. Quote the record, not the inferences.
## Unattended
just agent-attempt <target> <run-id>