docs(skills): keep the hard lines as the exception to failing open

Failing open on uncertainty has one exception the two skills didn't name: when a change can't tell whether it would expose a credential, delete someone's data, spend money or publish, it stops and asks. agent-operated-software and both review-team copies now say so. The skill-edge digests are regenerated.
docs(skills): scope fail-closed to artifact integrity; ask what happens when a change can't tell
2026-11-08 17:31:56 -10:00 · 2026-11-09 02:52:26 +00:00 · 2026-11-09 02:30:48 +00:00
4 changed files with 12 additions and 4 deletions
@@ -68,7 +68,11 @@ When a tool produces an artifact, do not make every consumer invent a completene
 3. Flush and atomically rename the partial artifact to its final path.
 4. Write the manifest, then a `.done` sentinel last.

-Consumers fail closed on the shared proof. A filename or exit code is not content verification.
+Consumers of an artifact fail closed on the shared proof: don't read a file before its sentinel exists,
+because it may be half-written. A filename or exit code is not content verification. This rule is for
+artifact integrity only. For delivery, routing and checks, uncertainty fails open: deliver, and report
+what couldn't be checked. The hard lines are the exception: when a change can't tell whether it would
+expose a credential, delete someone's data, spend money or publish, it stops and asks.

 ## Build with an agent SDLC

@@ -53,6 +53,8 @@ These apply to every review, not just deep reviews.

 Does the change solve the user's problem with a maintainable design? Check affected contracts, invalid input, state transitions, recovery, consumers and unnecessary duplication.

+What does this do when it can't tell? If it stops or refuses, is there positive evidence or an operator opt-in? Without either, the default answer is to deliver and report the uncertainty, except at the hard lines (credentials, destructive deletes, money, publishing), where it stops and asks.
+
 ### Anti-slop lens

 Then, for every review: **"Will an agent working on this code in 3 months find two ways to do the same thing?"**
@@ -39,7 +39,7 @@
      "pods/development-team/references/refactoring.md": "c73addf5cc5f51806ab31ab5165a8183dd616bd72526905695245e54c29301af",
      "pods/orchestration-team/SKILL.md": "616f332495a8e6fb5b6a3933442c81008158f9d3790a55783860ccbcfa7d6047",
      "pods/oversight-team/SKILL.md": "a48de41350453a09b231e01a89cc1dd3d4a64e082df090a7b0e04034227d2bb4",
-      "pods/review-team/SKILL.md": "17d73cdf9623e05627aa823848968b0720d35e700e75ed45ac3042df1fa73f30",
+      "pods/review-team/SKILL.md": "038430cd21d560fdf94719c3534da1a3b94422869d0bedead6273daeda604212",
      "process/agent-browser/LICENSE.txt": "014bb31e83d5c2e76aea1cc6e82217346ab41362f32cb355ad0f5c10aa0aeaff",
      "process/agent-browser/LOCAL-INSIGHTS.md": "3e37c298514506099c8212e32c58e78cd77781637a368a5db1acf1982d93a0f4",
      "process/agent-browser/OPENRIG.md": "c53e4a9923c8425dee6968d9fa72b91f72845a893a6b48556493526c95c05ceb",
@@ -66,7 +66,7 @@
      "process/verification-before-completion/references/performance-claims.md": "7db2a496a9423ab409b4e3819f64cd6abd7dff2413ce78232e6d154e62126884"
    },
    "plugin": {
-      "agent-operated-software/SKILL.md": "9159d26e7884bc5205f8b06adaa65625c7d9c6bef41dc2f307d91da4cc1b424b",
+      "agent-operated-software/SKILL.md": "ec910bf5f631d7f20872786a565a0437a446fa2d5fd8b52b685979978243a6a8",
      "agent-operated-workflows/SKILL.md": "24e54cbfa979999f523516112670618b2926ae5d42c7aa0846c94db214857ea5",
      "applying-a-permission-policy/SKILL.md": "f7bba8d50b10fc8715f40a57bf82677ca9388c6718c8a162833d9c6daf2afdca",
      "claude-compaction-restore/SKILL.md": "7201d5cafb4a02f36031e82e4c07f4243852a89546f5913c275ee59e45fd42ce",
@@ -144,7 +144,7 @@
      "pods/development-team/references/refactoring.md": "c73addf5cc5f51806ab31ab5165a8183dd616bd72526905695245e54c29301af",
      "pods/orchestration-team/SKILL.md": "616f332495a8e6fb5b6a3933442c81008158f9d3790a55783860ccbcfa7d6047",
      "pods/oversight-team/SKILL.md": "a48de41350453a09b231e01a89cc1dd3d4a64e082df090a7b0e04034227d2bb4",
-      "pods/review-team/SKILL.md": "17d73cdf9623e05627aa823848968b0720d35e700e75ed45ac3042df1fa73f30",
+      "pods/review-team/SKILL.md": "038430cd21d560fdf94719c3534da1a3b94422869d0bedead6273daeda604212",
      "process/agent-browser/LICENSE.txt": "014bb31e83d5c2e76aea1cc6e82217346ab41362f32cb355ad0f5c10aa0aeaff",
      "process/agent-browser/LOCAL-INSIGHTS.md": "3e37c298514506099c8212e32c58e78cd77781637a368a5db1acf1982d93a0f4",
      "process/agent-browser/OPENRIG.md": "c53e4a9923c8425dee6968d9fa72b91f72845a893a6b48556493526c95c05ceb",
@@ -53,6 +53,8 @@ These apply to every review, not just deep reviews.

 Does the change solve the user's problem with a maintainable design? Check affected contracts, invalid input, state transitions, recovery, consumers and unnecessary duplication.

+What does this do when it can't tell? If it stops or refuses, is there positive evidence or an operator opt-in? Without either, the default answer is to deliver and report the uncertainty, except at the hard lines (credentials, destructive deletes, money, publishing), where it stops and asks.
+
 ### Anti-slop lens

 Then, for every review: **"Will an agent working on this code in 3 months find two ways to do the same thing?"**