Self-review as a supervisory control program; CI verifies instead of reviewing

.agents/skills/self-review-solve/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: self-review-solve
+description: "Resolve the Boatstack self-review: fix open findings or run a fresh review, converge the loop, and seal the receipt."
+---
+
+<!-- generated-by: yskill; source: skills/self-review-solve; digest: sha256:7a4e94f0b8209fc350d1b32a99e9a08dfce9b474af1b52e62e135ca6cf92a89b; version: 0.1.38 -->
+
+This adapter exposes the canonical Yield workflow at `skills/self-review-solve`.
+Read its SKILL.md, then run from the repository root:
+
+    .yield/bin/yskill run 'skills/self-review-solve'
+
+	Follow each returned operation exactly. Answer each operation directly:
+
+	    .yield/bin/yskill respond <run-id> --value <answer> --skill 'skills/self-review-solve'
+
+	For structured agent results, use --result-json instead of --value.
+
+Do not skip an operation or invent its response.

.agents/skills/self-review/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: self-review
+description: "Run the Boatstack supervisory-control self-review for the current branch and report the verdict without changing code."
+---
+
+<!-- generated-by: yskill; source: skills/self-review; digest: sha256:af1e55e2f98923141dbb4d9407110e8df8307c42e61821e8f68cb964a2e66fef; version: 0.1.38 -->
+
+This adapter exposes the canonical Yield workflow at `skills/self-review`.
+Read its SKILL.md, then run from the repository root:
+
+    .yield/bin/yskill run 'skills/self-review'
+
+	Follow each returned operation exactly. Answer each operation directly:
+
+	    .yield/bin/yskill respond <run-id> --value <answer> --skill 'skills/self-review'
+
+	For structured agent results, use --result-json instead of --value.
+
+Do not skip an operation or invent its response.

.claude/skills/self-review-solve/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: self-review-solve
+description: "Resolve the Boatstack self-review: fix open findings or run a fresh review, converge the loop, and seal the receipt."
+---
+
+<!-- generated-by: yskill; source: skills/self-review-solve; digest: sha256:7a4e94f0b8209fc350d1b32a99e9a08dfce9b474af1b52e62e135ca6cf92a89b; version: 0.1.38 -->
+
+This adapter exposes the canonical Yield workflow at `skills/self-review-solve`.
+Read its SKILL.md, then run from the repository root:
+
+    .yield/bin/yskill run 'skills/self-review-solve'
+
+	Follow each returned operation exactly. Answer each operation directly:
+
+	    .yield/bin/yskill respond <run-id> --value <answer> --skill 'skills/self-review-solve'
+
+	For structured agent results, use --result-json instead of --value.
+
+Do not skip an operation or invent its response.

.claude/skills/self-review/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: self-review
+description: "Run the Boatstack supervisory-control self-review for the current branch and report the verdict without changing code."
+---
+
+<!-- generated-by: yskill; source: skills/self-review; digest: sha256:af1e55e2f98923141dbb4d9407110e8df8307c42e61821e8f68cb964a2e66fef; version: 0.1.38 -->
+
+This adapter exposes the canonical Yield workflow at `skills/self-review`.
+Read its SKILL.md, then run from the repository root:
+
+    .yield/bin/yskill run 'skills/self-review'
+
+	Follow each returned operation exactly. Answer each operation directly:
+
+	    .yield/bin/yskill respond <run-id> --value <answer> --skill 'skills/self-review'
+
+	For structured agent results, use --result-json instead of --value.
+
+Do not skip an operation or invent its response.

.cursor/skills/self-review-solve/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: self-review-solve
+description: "Resolve the Boatstack self-review: fix open findings or run a fresh review, converge the loop, and seal the receipt."
+---
+
+<!-- generated-by: yskill; source: skills/self-review-solve; digest: sha256:7a4e94f0b8209fc350d1b32a99e9a08dfce9b474af1b52e62e135ca6cf92a89b; version: 0.1.38 -->
+
+This adapter exposes the canonical Yield workflow at `skills/self-review-solve`.
+Read its SKILL.md, then run from the repository root:
+
+    .yield/bin/yskill run 'skills/self-review-solve'
+
+	Follow each returned operation exactly. Answer each operation directly:
+
+	    .yield/bin/yskill respond <run-id> --value <answer> --skill 'skills/self-review-solve'
+
+	For structured agent results, use --result-json instead of --value.
+
+Do not skip an operation or invent its response.

.cursor/skills/self-review/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: self-review
+description: "Run the Boatstack supervisory-control self-review for the current branch and report the verdict without changing code."
+---
+
+<!-- generated-by: yskill; source: skills/self-review; digest: sha256:af1e55e2f98923141dbb4d9407110e8df8307c42e61821e8f68cb964a2e66fef; version: 0.1.38 -->
+
+This adapter exposes the canonical Yield workflow at `skills/self-review`.
+Read its SKILL.md, then run from the repository root:
+
+    .yield/bin/yskill run 'skills/self-review'
+
+	Follow each returned operation exactly. Answer each operation directly:
+
+	    .yield/bin/yskill respond <run-id> --value <answer> --skill 'skills/self-review'
+
+	For structured agent results, use --result-json instead of --value.
+
+Do not skip an operation or invent its response.

.gitattributes

@@ -2,3 +2,9 @@ docs/architecture/boatstack-*.md text eol=lf
 docs/architecture/boatstack-*.mmd text eol=lf
 docs/architecture/boatstack-*.json text eol=lf
 docs/architecture/boatstack-standard-flow.mmd text eol=lf
+# The review policy is admitted by exact bytes: the program fingerprint hashes
+# the worktree assets while verification re-admits them from the base
+# revision. A CRLF checkout (Windows autocrlf) would make the two disagree,
+# so the policy assets and sealed receipts always materialize with LF.
+.github/codex/** text eol=lf
+.github/reviews/*.receipt.json text eol=lf