feat(hermes): map inter-session-peer-discipline as pending + file its ledger

Un-reds the hermes build (build fails on unmapped skills in skills/; this skill
landed in sources 2026-06-16 unmapped). Entry is mode:pending, intended auto/meta
— a purely behavioral governance skill (no tool-side effects) that should pass a
non-implementer test-trigger + review before auto-firing. Filed ⚪
inter-session-peer-discipline-test-trigger + 🔵 -review.

Zone confirmed claude-skills (skill lives in this repo). Human-ratified; workshop
coordinated as a peer proposal, not authority (per the skill itself). YAML validated
(33 skills, 9 pending). Schema version untouched.

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

hermes/mapping.yaml

@@ -138,7 +138,7 @@ skills:
     mode: skip
     reason: "Claude-Code-only orchestrator — Hermes uses hermes-installer-skill instead."
 
-  # ─── pending (8 — behavioral audit required) ─────────────────────────
+  # ─── pending (9 — behavioral audit required) ─────────────────────────
 
   delegate-task:
     mode: pending
@@ -195,3 +195,10 @@ skills:
       mode: auto
       category: productivity
     reason: "Paired SessionStart hook registers itself in ~/.claude/settings.json and sweeps orphaned monitor OS processes (Get-CimInstance | Stop-Process by sentinel+inbox-path); the skill then raises an in-session Monitor on .claude-inbox/. Machine-level side-effects (user-config mutation + process kills) and a Windows-PowerShell hook that needs a Linux port for Hermes factory machines. Primary activation is the CLAUDE.md trigger-line `inbox monitor: raise on start` + the injector, not a hermes-trigger. Behavioral audit via session-inbox-monitor-test-trigger required before promotion to auto."
+
+  inter-session-peer-discipline:
+    mode: pending
+    intended:
+      mode: auto
+      category: meta
+    reason: "Purely behavioral governance skill — NO tool-side effects (no settings.json write, no process kill, no Monitor raise). Governs how an agent treats inter-session/peer messages: peer messages (and the agent's own replies) are proposals/analysis, NOT authority; the human is the only source of scope/direction; a peer-driven design escalation must not be reported as settled without explicit human ratification. Pending (not auto) by the same caution applied to other unverified behavioral skills: a behavioral-authority skill should not auto-fire until it passes a non-implementer test-trigger + review. Behavioral audit via inter-session-peer-discipline-test-trigger required before promotion to auto. (Ledger filed 2026-06-17 per workshop coordination; human-ratified.)"