Process: session wrap-up protocol — doc-update, then clean-context review subagents

.claude/skills/alignment/SKILL.md

@@ -9,6 +9,13 @@ disable-model-invocation: true
 Review staged or uncommitted code to ensure quality, test coverage, and alignment with the
 project's spec (`docs/spec/`) and architecture playbook (`docs/architecture/`).
 
+This skill is also executed by a **clean-context subagent** at session wrap-up (see
+CLAUDE.md → Session wrap-up protocol). When running as that subagent: you deliberately
+have no session context — judge the diff against the written contracts only, and return
+the summary (rule #15) as your final message so the session agent can relay it. If a
+change looks deliberate but its rationale is recorded nowhere, that absence is itself a
+finding.
+
 ## Scope
 
 Determine the review scope using `git diff` (unstaged) and `git diff --staged` (staged).

.claude/skills/eng-council/SKILL.md

@@ -55,6 +55,13 @@ unavailable, the seat still sits — grep is the fallback evidence.
 
 Pick the mode from what's in front of you; say which mode is running.
 
+The two review modes are also executed by a **clean-context subagent** at session
+wrap-up, after `/doc-update` and the alignment pass (see CLAUDE.md → Session wrap-up
+protocol). When running as that subagent: you deliberately have no session context —
+judge the diff against the codebase's own population of shapes, and return the report as
+your final message so the session agent can relay and arbitrate it. A deliberate-looking
+divergence whose rationale is recorded nowhere is itself a finding.
+
 ### Sweep — whole codebase
 
 For: milestone boundaries, the one-off backfill, "how healthy are we?" on demand.