feat(hooks): additionalContext injection advisory + filter-before lever (v5.10 B5) [skip-docs]

HKV now flags hooks that build hookSpecificOutput.additionalContext from
un-grepped command output as an INFO advisory (weight 0, never severity-bearing
— excluded from the self-audit nonInfo set). That field enters Claude's context
every time the hook fires (plain stdout on exit 0 does not), so an unfiltered
payload is a recurring per-turn token cost.

- New lib scanners/lib/hook-additional-context.mjs: pure assessHookAdditionalContext
  (unit-tested, no IO) + IO wrapper assessHookContextForRepo (walk hooks->scripts).
  Heuristic: additionalContext + verbose-prone capture (cat/git log/execSync/…) &&
  no filter (grep/head/jq/.slice). Deliberately low precision -> advisory only.
- HKV: emits the advisory inline on scripts it already reads (after the M5 verbose
  check). Additive, info severity -> frozen v5.0.0 + SC-5 snapshots untouched.
- feature-gap: new filterHookLeverFinding companion, fires ONLY when >=1 chatty
  hook is detected — surfaces the filter-before-Claude-reads lever (CC
  filter-test-output.sh). Silent otherwise (opportunity, not noise).
- docs: README HKV + GAP scanner rows; scanner-internals.md HKV row + full B5
  implementation note. CLAUDE.md kept lean ([skip-docs]); B5 fully documented in
  README + scanner-internals.

Mechanism verified 2026-06-23 against code.claude.com/docs context-window.md
(additionalContext enters context; plain stdout does not). Suite 1239 -> 1254 green.
Version/badges/CHANGELOG wait for the v5.10 release cut.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

tests/fixtures/hooks-additional-context/hooks/scripts/chatty.sh

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+# Chatty hook: dumps unfiltered command output straight into additionalContext.
+# Every SessionStart this whole payload enters Claude's context (not just stdout).
+NOTES="$(cat ./STATE.md)"
+LOG="$(git log --oneline)"
+printf '{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"%s\n%s"}}' "$NOTES" "$LOG"

tests/fixtures/hooks-additional-context/hooks/scripts/filtered.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+# Bounded hook: greps the log down to only failures before injecting context.
+# This is the filter-before-Claude-reads pattern — should NOT be flagged.
+ERRORS="$(cat ./test.log | grep -E 'FAIL|ERROR' | head -20)"
+printf '{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"%s"}}' "$ERRORS"