config-audit/scanners
Kjell Tore Guttormsen f75ed5655c feat(plh): flag plugin-agent frontmatter Claude Code ignores (v5.5.0 / E)
Plugin subagents silently ignore `hooks`/`mcpServers`/`permissionMode`
frontmatter — these are honored only for user/project agents in
.claude/agents/ (code.claude.com/docs sub-agents). Setting them in a
plugin agent is dead config; `permissionMode` is MEDIUM because it
implies a restriction Claude Code does not apply (false security).
hooks/mcpServers are LOW.

Additive to PLH's agent-frontmatter loop (no new scanner, count stays
13). One humanizer pattern covers the three field titles. Hermetic
temp-fixture test (positive + negative). Suite 954 -> 957, byte-stable.

Part of v5.5.0 "steering-model I". Foundation (active-config-reader
enumeration) deferred to v5.6 with B — A/E are additive and don't
consume it.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
2026-06-20 11:11:12 +02:00
..
lib feat(plh): flag plugin-agent frontmatter Claude Code ignores (v5.5.0 / E) 2026-06-20 11:11:12 +02:00
cache-prefix-scanner.mjs fix(tokens): refresh stale "Opus 4.7" framing to model-neutral + Opus 4.8 anchor 2026-06-18 15:27:36 +02:00
claude-md-linter.mjs feat(cml): context-window-scaled CLAUDE.md char budget (mirrors CC 40.0k warning) 2026-06-19 13:34:40 +02:00
collision-scanner.mjs feat(config-audit): cross-plugin collision scanner COL (v5 N6) [skip-docs] 2026-05-01 07:46:15 +02:00
conflict-detector.mjs fix(permissions): param-aware DIS dead-allow + CNF conflict matching 2026-06-18 13:06:20 +02:00
disabled-in-schema-scanner.mjs feat(dis): flag forbidden-param permission rules CC silently ignores 2026-06-19 14:04:25 +02:00
drift-cli.mjs feat(humanizer): forbidden-words lint runner + test wrapper (SC-3) [skip-docs] 2026-05-01 18:11:15 +02:00
feature-gap-scanner.mjs feat(feature-gap): recommend disableBundledSkills under skill-listing pressure 2026-06-18 21:38:19 +02:00
fix-cli.mjs feat(humanizer): forbidden-words lint runner + test wrapper (SC-3) [skip-docs] 2026-05-01 18:11:15 +02:00
fix-engine.mjs fix(hkv,rul): add 3 verified hook events; correct globs-rule wording 2026-06-20 09:56:00 +02:00
hook-validator.mjs fix(hkv): remove post-session — it is a runner hook, not a settings event 2026-06-20 10:12:52 +02:00
import-resolver.mjs feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
manifest.mjs feat(humanizer): wire humanizer into 6 remaining CLIs with --raw 2026-05-01 17:47:09 +02:00
mcp-config-validator.mjs fix(mcp-config-validator): remove invented trust field (verify-first) 2026-06-18 14:22:56 +02:00
plugin-health-scanner.mjs feat(plh): flag plugin-agent frontmatter Claude Code ignores (v5.5.0 / E) 2026-06-20 11:11:12 +02:00
posture.mjs feat(humanizer): forbidden-words lint runner + test wrapper (SC-3) [skip-docs] 2026-05-01 18:11:15 +02:00
rollback-engine.mjs feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
rules-validator.mjs fix(hkv,rul): add 3 verified hook events; correct globs-rule wording 2026-06-20 09:56:00 +02:00
scan-orchestrator.mjs feat(skill-listing): add SKL scanner for the skill-listing token budget 2026-06-18 17:36:28 +02:00
self-audit.mjs feat(skill-listing): add SKL scanner for the skill-listing token budget 2026-06-18 17:36:28 +02:00
settings-validator.mjs feat(set): validate autoMode structure + flag it in shared settings (CA-SET) 2026-06-19 22:14:26 +02:00
skill-listing-scanner.mjs refactor(skl): extract skill-listing budget to shared lib (single source of truth) 2026-06-18 21:23:01 +02:00
token-hotspots-cli.mjs fix(tokens): refresh stale "Opus 4.7" framing to model-neutral + Opus 4.8 anchor 2026-06-18 15:27:36 +02:00
token-hotspots.mjs fix(tokens): refresh stale "Opus 4.7" framing to model-neutral + Opus 4.8 anchor 2026-06-18 15:27:36 +02:00
whats-active.mjs feat(humanizer): wire humanizer into 6 remaining CLIs with --raw 2026-05-01 17:47:09 +02:00