Garry TanandClaude Fable 5 5852da35ad fix(auq): the interactive fence is quota-silent — it defers to the skill's own decision points ...

Burn-in calibration: run 1 (fence tail 'when unsure, ask') overshot the
plan-ceo review band at reviewCount=8; run 2 (tail mentioning 'HOW MANY
questions') undershot at 1. Any ask-count language in the fence anchors the
model in one direction or the other. The tail now says only: classify as
interactive, then follow the skill's own decision-point instructions exactly
as written. Pins updated to forbid count language in either direction.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-08-31 20:58:35 +00:00

..

sections

v1.75.0.0 feat: ponytail import wave — simplification review lens, arm benchmark, reuse ladder, instruction-tier digest (#2722)

2026-08-29 10:10:35 -07:00

SKILL.md

fix(auq): the interactive fence is quota-silent — it defers to the skill's own decision points

2026-08-31 20:58:35 +00:00

SKILL.md.tmpl

v1.71.0.0 feat: token-load reduction — preamble runtime scripts, gated onboarding, 20 skill carves, CLAUDE.md trim (#2691)

2026-08-27 09:50:31 -07:00