config-audit/tests
Kjell Tore Guttormsen ba9f82f952 feat(tokens): stale plugin-cache disk-cleanup finding, honestly labelled Dead config (v5.9 B3b)
The B3a cache filter already exposes discovery.staleCacheVersions; surface them
as a finding so the user knows the superseded plugin versions are safe to delete.

Honesty (Verifiseringsplikt): the finding loads on ZERO turns, so it must NOT
read as a per-turn token cost. TOK normally humanizes to "Wasted tokens"; a new
per-finding category override ('plugin-cache-hygiene' -> "Dead config") plus a
dedicated humanizer translation ("Old plugin versions are sitting on disk (safe
to delete) ... cost zero tokens per turn ... housekeeping, not a performance
problem") keep the prose accurate instead of the generic "using more space"
default. evidence carries the explicit "zero live-context impact" note.

- token-hotspots: Pattern H emits CA-TOK (low) from discovery.staleCacheVersions
  when stale versions exist (`--global`); silent otherwise.
- humanizer: CATEGORY_TO_IMPACT lets a finding's category override the
  scanner-default impact label (raw `category` field unchanged -> --json/--raw
  byte-stable). humanizer-data: honest static translation for the finding.
- Tests: finding fires/severity/category, lists stale keys + zero-impact note,
  silent when none; humanizer override -> Dead config; honest translation locked.
- Docs: tokens command render note (disk-cleanup, not a token problem) +
  --no-exclude-cache flag; README + CLAUDE.md rows (7 patterns, cache-aware).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 18:17:55 +02:00
..
agents feat(humanizer): update agent system prompts [skip-docs] 2026-05-01 19:53:59 +02:00
commands feat(humanizer): update action command templates [skip-docs] 2026-05-01 19:50:47 +02:00
fixtures fix(plh): require CLAUDE.md commands/agents/hooks section only for shipped components 2026-06-20 09:06:20 +02:00
helpers feat(scanner): add AGT agent-listing always-loaded budget finding (v5.9 B1) 2026-06-23 15:02:59 +02:00
hooks feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
knowledge fix(tokens): refresh stale "Opus 4.7" framing to model-neutral + Opus 4.8 anchor 2026-06-18 15:27:36 +02:00
lib feat(tokens): stale plugin-cache disk-cleanup finding, honestly labelled Dead config (v5.9 B3b) 2026-06-23 18:17:55 +02:00
scanners feat(tokens): stale plugin-cache disk-cleanup finding, honestly labelled Dead config (v5.9 B3b) 2026-06-23 18:17:55 +02:00
scenarios feat(humanizer): scenario read-test corpus + runner (SC-4) [skip-docs] 2026-05-01 18:16:23 +02:00
snapshots feat(scanner): add AGT agent-listing always-loaded budget finding (v5.9 B1) 2026-06-23 15:02:59 +02:00
json-backcompat.test.mjs feat(ost): v5.6 C — output-style scanner (CA-OST, count 13→14) 2026-06-20 21:02:44 +02:00
lint-default-output.mjs feat(humanizer): forbidden-words lint runner + test wrapper (SC-3) [skip-docs] 2026-05-01 18:11:15 +02:00
lint-forbidden-words.json feat(humanizer): forbidden-words data file (tier1/2/3) 2026-05-01 16:53:37 +02:00
raw-backcompat.test.mjs feat(ost): v5.6 C — output-style scanner (CA-OST, count 13→14) 2026-06-20 21:02:44 +02:00
scenario-read-test.mjs feat(humanizer): scenario read-test corpus + runner (SC-4) [skip-docs] 2026-05-01 18:16:23 +02:00
scenario-read-test.test.mjs feat(humanizer): scenario read-test corpus + runner (SC-4) [skip-docs] 2026-05-01 18:16:23 +02:00
snapshot-default-output.test.mjs test(snapshots): make byte/snapshot tests hermetic + re-seed baseline 2026-06-18 12:26:00 +02:00