voyage/tests/scripts
Kjell Tore Guttormsen e9a4abc34f
feat(measure): the comparison gate counts the 14 areas against five frameworks and the tidy denominator, and it is RED [skip-docs]
The lifted target (operator, 2026-09-27; PM order 44111111): Voyage + the
operator's way of working level with or ahead of related frameworks in all
14 areas, and every Voyage part a documented Claude Code primitive covers
removed or with a measured reason to stay.

scripts/comparison-gate.mjs reads both denominators from their source, never
from the table: the areas from the first column of the PM report's table,
the parts from git ls-files (one part per eval case). It fells the table on
missing evidence, never on a verdict: a cited file must exist inside its
root and hold the cited lines, a pinned clone must sit at its pin, a web
citation needs a verbatim quote, an absence needs zero hits and a
known-positive control. Green also requires an independent reader. The
table itself is local-only (docs/comparison.local.json).

Measured today on 7439dac: RED, 0 evidence problems; 2 of 14 areas against
all five references (Superpowers 11, Pocock 14, agent-skills 11, Cherny 10,
playbook 2); tidy 5 of 64 covered parts resolved.

23 tests in tests/scripts/comparison-gate.test.mjs; six mutants felled (no
evidence check, no line check, no reader check, denominator from the table,
no tidy completeness, no pin check). Suite 1278 -> 1301 (1299/0/2).

[skip-docs]: an operator measurement instrument like scripts/yardstick.mjs,
whose table is local-only - no user-facing behaviour changes, so README and
CLAUDE.md have nothing true to say about it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-02 20:31:14 +02:00
..
annotate.test.mjs docs: remove dead references to a retired repository (green) 2026-09-23 12:28:05 +02:00
comparison-gate.test.mjs feat(measure): the comparison gate counts the 14 areas against five frameworks and the tidy denominator, and it is RED [skip-docs] 2026-10-02 20:31:14 +02:00
end-state-gate.test.mjs docs(tests): tracked comments name the measurement, not the coordination 2026-09-18 03:01:09 +02:00
storm-measure.test.mjs fix(storm-measure): check BOTH halves of the activation SC, not just the count delta 2026-08-12 23:01:59 +02:00
synthesis-measure.test.mjs feat(voyage): S12 — NW3 synthesis-agent built + measured → declined per measurement [skip-docs] 2026-06-18 17:58:39 +02:00
yardstick.test.mjs feat(measure): the yardstick prints Voyage's three numbers with denominators from the source, and it is RED 2026-09-22 21:50:06 +02:00