principles.py runs ruff (C901, PLR0913, BLE001, S110, B006, B008, ARG), lizard (CCN, NLOC, parameters per function span) and jscpd (clones) on the lines a change touches and maps each hit to SRP, fail fast, KISS/YAGNI or DRY; a missing tool prints skip, every threshold is a required flag. It reuses the diff parsing of defaults.py, registered in sys.modules before it runs because dataclasses look the module up there, and hands lizard only the suffixes its 1.24.1 readers claim, since lizard parses any other file as C. kvb-code-clean step 3 calls it with McCabe's 10, pylint's 5 parameters, jscpd's 50 tokens and 50 NLOC; make install adds lizard 1.24.1 (pipx) and jscpd 5.4.2 (npm). The lizard and jscpd parsers are tested on fixture output only: neither tool has run for real yet.
🎯 Fix: 90 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: new
🛡️ Security: 100 %
💰 Value: ?
🏆 Score: 86
🚦 Gate: ⚠️ time new: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One pass before every commit or stage request: step 1 deletes added comments (docstrings and headers included), step 2 forbids defaults with defaults.py and defaults.md, step 3 applies the kvb-check-principles lenses, now with KISS/YAGNI, fail fast and coupling, to the touched units. commit-no-verify and commit-next run it; references, the test path and the README map follow. defaults.py rewords two texts that MEDUSA flagged as SQL injection and env exposure signatures.
🎯 Fix: 93 %
💥 Break: 3 %
💸 Cost: 101 %
⏱️ Time: –
🛡️ Security: 100 %
💰 Value: ?
🏆 Score: 89
🚦 Gate: ⚠️ cost 101 % > 100: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
