open/config-audit
1
0
Fork 0
Code Issues Pull requests Releases Activity

feat(skill-listing): add SKL scanner for the skill-listing token budget

Browse source 
Fase 4 Items 2+3 (CC 2.1.114→181 gap-review). New orchestrated scanner
`skill-listing-scanner.mjs` (prefix SKL) flags every active skill whose
description exceeds the verified 1,536-char listing cap (CC 2.1.105, changelog
L1502). Past the cap, Claude Code silently truncates the description the model
reads to route skill invocation — dropping the trigger phrases at the tail.
HOME-scoped over all user + plugin skills via enumerateSkills (COL is the model).

- CA-SKL-001 (medium): description > 1,536 chars. Remediation folds in Item
  2(b) — recommends disableBundledSkills + skillOverrides + trimming
  (designvalg A: no standalone GAP-check, which would fire for nearly everyone).
- Designvalg B: v1 ships the verified cap ONLY. The aggregate 2%-of-context
  listing budget is deferred — it needs a context-window assumption that would
  turn a verified fact into a guess (would carry a CALIBRATION_NOTE if added).
- Choice C: recognize the skillOverrides settings key (CC 2.1.129) in
  KNOWN_KEYS. Left OUT of TYPE_CHECKS — the value is a per-skill object
  (off/user-invocable-only/name-only), not a string; a 'string' check (as the
  plan sketched) would create a NEW false positive. Verify-first deviation.

Registration: scan-orchestrator (13th scanner), humanizer (SKL → 'Wasted
tokens' + static/_default translations), scoring SCANNER_AREA_MAP (→ Token
Efficiency; no 11th area), README badge 12→13, CLAUDE.md (finding-id +
test-count), docs/scanner-internals.md, gap-matrix + plan status notes.

Snapshots reseeded hermetically (SEED_SNAPSHOT/UPDATE_SNAPSHOT): SKL entry with
0 findings in empty HOME, scanners_ok 11→12, claudeMdEstimatedTokens bump from
the CLAUDE.md edits flowing through the cascade. Contamination grep clean.

Suite 868/868 (856 baseline + 11 SKL + 1 skillOverrides). RED→GREEN logged
per cycle.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
This commit is contained in:
Kjell Tore Guttormsen 2026-06-18 17:36:28 +02:00
commit 7bb254780a
22 changed files with 390 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/lib/humanizer-data.test.mjs
View file

@ -8,7 +8,7 @@ import { TRANSLATIONS } from '../../scanners/lib/humanizer-data.mjs';
const __dirname = dirname(fileURLToPath(import.meta.url));
const FORBIDDEN_PATH = resolve(__dirname, '..', 'lint-forbidden-words.json');
const EXPECTED_SCANNERS = ['CML', 'SET', 'HKV', 'RUL', 'MCP', 'IMP', 'CNF', 'GAP', 'TOK', 'CPS', 'DIS', 'COL', 'PLH'];
const EXPECTED_SCANNERS = ['CML', 'SET', 'HKV', 'RUL', 'MCP', 'IMP', 'CNF', 'GAP', 'TOK', 'CPS', 'DIS', 'COL', 'PLH', 'SKL'];
function stripBacktickSpans(s) {
return s.replace(/`[^`]*`/g, '');
@ -24,7 +24,7 @@ test('TRANSLATIONS exports an object', () => {
assert.ok(TRANSLATIONS !== null);
});
test('TRANSLATIONS covers all 13 expected scanner prefixes', () => {
test('TRANSLATIONS covers all 14 expected scanner prefixes', () => {
for (const prefix of EXPECTED_SCANNERS) {
assert.ok(TRANSLATIONS[prefix], `missing scanner prefix: ${prefix}`);
}

4
tests/lib/humanizer.test.mjs
View file

@ -171,8 +171,8 @@ test('humanizeFinding sets category Conflict for CNF/COL', () => {
}
});
test('humanizeFinding sets category Wasted tokens for TOK/CPS', () => {
for (const s of ['TOK', 'CPS']) {
test('humanizeFinding sets category Wasted tokens for TOK/CPS/SKL', () => {
for (const s of ['TOK', 'CPS', 'SKL']) {
const out = humanizeFinding(makeFinding({ scanner: s }));
assert.equal(out.userImpactCategory, 'Wasted tokens');
}