Model keeps using a banned shell reading method after an explicit ban

Status Open
Maintainer reply None cached
Activity 0 comments · opened Sep 25, 2026

What happened
After the user banned sed-style shell reads of source files, the model continued to read code with sed.

Expected
Stop using a method the moment the user bans it; use the sanctioned file-reading tool.

Context: a project CLAUDE.md plus the user's auto-memory define a mandatory, ordered code-review checklist (read every touched file, the whole diff, linked issue and thread; cite the normative source per component; grep callers; check duplication, new structure and scope; then a single short verdict). The model had the checklist loaded in context and had been reminded of it repeatedly in the same session. Reviewing a multi-thousand-line pull request.

Reported by the user; no transcript or private content included.

View original on GitHub ↗