@mmerterden/multi-agent-pipeline 20.15.0 → 20.16.0

package/manifest.json

@@ -1,12 +1,12 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "20.15.0",
-  "commit": "09149bf3e094216e7074ec86436ba94e8c621753",
-  "generatedAt": "2026-10-02T09:44:18.338Z",
+  "version": "20.16.0",
+  "commit": "23aeff395893c0c78dbb8a4b65611a02454a058e",
+  "generatedAt": "2026-10-02T10:57:38.452Z",
   "algorithm": "sha256",
-  "fileCount": 1297,
+  "fileCount": 1303,
   "files": {
-    "CHANGELOG.md": "dde7fc53259eef5eda0d339ec6490d98df31155a1945958334b8347f8f7f8e77",
+    "CHANGELOG.md": "838ef9627bf6bbf35513a11a2a2786502e61ae9e3a17cb8348da488868dbe291",
     "LICENSE": "8d8c51aaf1e1538b180c69965fa038db71be86798cc3e26a143bebfefe16a43e",
     "README.md": "280e42dbd759e9a55eee46a82f2f5eaa11e866b05c0fb71b30f8330fa80b9c57",
     "README.tr.md": "25491697cbb9e3f91c1798bd1fbd05fa0a19906adb3e24a25a5fe0a055c2c559",
@@ -33,7 +33,7 @@
     "docs/best-practices.md": "f8b75b0d38b5896a6a852bb30a1edddeb24dab8b5b7b1d9313290e1241c72024",
     "docs/ecosystem.md": "6164b62955dc4b915ed13ad183682108b344378ceba6b7acbbf0b674d804b000",
     "docs/engineering.md": "550528cd47c7d2c921729c68d0782a00ac8e77a4bdfec479f6749f9c3235d188",
-    "docs/facts.json": "f0ec3716ba9c5f364bf7984b46a09a79a89da76aeccdc8b9f44c020bb7130633",
+    "docs/facts.json": "76ab049f4bb47a06bdb9c08781314e406434488f5ce536c4e385f722594c9d99",
     "docs/features.md": "6c9f0efb00c683e6f611c440c87847b187f8b0eee59e9e812f3a241695bc2ae1",
     "docs/performance.md": "bbf2f3922c25dcba0c1a9e69ef420e3871a729af5b35009a49b48a5d3c5cd151",
     "docs/recovery-guide.md": "59a8f1b66b34cb9ff5507b3d54dac3b9915e184aa044d9c758d18cac818d510e",
@@ -51,9 +51,9 @@
     "install/_plugin-skills.mjs": "2de429260472a7b60bfe800eabc111624fa5f82a175e283481b05e5349dad572",
     "install/_telemetry.mjs": "5433d753f909beed2c8789272bba05e245482c472f83d3444f58000c4c9a634b",
     "install/_unattended-profile.mjs": "e1ed82bde35d19105ee12c2a551eb778912b0e5c93ab227fd15c993098d98de0",
-    "install/catalog-history.json": "f3f777da790695046744a08011760237e124b662d6801bb7974ada3ee23b0437",
-    "install/claude.mjs": "6af22bb9b2594aee502c36550020d2c9c4c3222061ed8a88a0885687cd91ebec",
-    "install/codex.mjs": "d2fd88a3488a1bea580b3d81e5d434edbefa492cc08e5e9445bbcc2f5df2b509",
+    "install/catalog-history.json": "d1db2fb83821ef9de8437b7c893e1ce2cddbc34e368a62ac664bc626304eb9ec",
+    "install/claude.mjs": "10f41c13d32b8f6acaf3de92e7f7378f2ce63ba5f7b8ed167e10972a32e163d9",
+    "install/codex.mjs": "1008f021ac8c24fa067e5541695d3ed41c6f1c9d4d51b7bcd8644f6f054c511d",
     "install/copilot.mjs": "300a74f17084d1a38f16428ca7477394c29e33cd755156e19b92e457999be234",
     "install/index.mjs": "07ec26ecdd81cc983f146faf4b7095c98edce39c89a6fd83c24ce43229d2d9e7",
     "install/templates/claude-hooks.json": "12d6bb0c3cd7d71b1d2029e2eb4370ca7b5ee55bd88f96b09c927d8119a87be7",
@@ -62,7 +62,7 @@
     "install/templates/multi-agent-autopilot-awake.plist.template": "ddd25c76c56fcbb38a89de8e35637372d70ace993d6bc487a88ca9cfb702fe1f",
     "install/templates/multi-agent-autopilot.plist.template": "122c8a61cd927edd99375d6e3da40f1d42bcceed5b6641785c8b28bb930bc77e",
     "install/unattended-profile-legacy.json": "f52e86b998956f09ad306b1735a6c10b58580d7082d8a55665a4c6bb15c3aa1f",
-    "package.json": "26d8d5e3083f911d97416d620bb851857cff2d6624a292852e189119bcf2dedb",
+    "package.json": "c80d36a6548f6630ad273a2c2bc1322d4358e4743a6ebe364704306ba236ba11",
     "pipeline/agents/android-architect.md": "11fb74543cb0ebcf9525ca6654fe95d53da7229e0bf4a1149b31fd9005abc453",
     "pipeline/agents/backend-architect.md": "b02a606c301e4714131aed70ae6d16eeb77fbc819a001e2752cff2488d4246de",
     "pipeline/agents/bulk-reader.md": "6597052cd7d205bac2b1c7633f5232fe1a40730664a913b8eb77efd5a786dc25",
@@ -115,7 +115,7 @@
     "pipeline/commands/multi-agent/review-analysis/SKILL.md": "2ba4ee67a56bd5f7041a02fcd227b5475b39f6e6a39b1f693cdf4bd5302c6e17",
     "pipeline/commands/multi-agent/review-issue/SKILL.md": "7ae7fe774c02114840cc21fb303f98c9a36bc2903f1db4cfc2cebe213ca70f1b",
     "pipeline/commands/multi-agent/review-jira/SKILL.md": "db8ecc7ec8c7040aac9c71dcf40dae194a76f146ab227833b909b45580b5347a",
-    "pipeline/commands/multi-agent/review/SKILL.md": "2e39692a3fec193d009a8495a017fb8e13d29f04b939270f8230d5f26b2e4a7f",
+    "pipeline/commands/multi-agent/review/SKILL.md": "ac16dcf23fd682bc92836db6e8f6329679dcc7183fb2480658bdccc08a29cc18",
     "pipeline/commands/multi-agent/route-off/SKILL.md": "aa8b677898b0efde1bd19c50383497da43a83b3b811e36f60695675d845c2de8",
     "pipeline/commands/multi-agent/route-on/SKILL.md": "3324430a81609719264a5118d6b4613a6af10e4a04c13a809ee367f1251e58f9",
     "pipeline/commands/multi-agent/route-status/SKILL.md": "00b1759c523b672c053bfb5f3c6af67ef0bd9b7ab473576017da22c6a73148ec",
@@ -299,7 +299,7 @@
     "pipeline/multi-agent-refs/features/repo-map.md": "9102f95d5c819c3bce3dc992cc98c67657e83f1fbc77d2e9b3d16b040bfab9f6",
     "pipeline/multi-agent-refs/features/repo-profile.md": "6080ba20a4246c448d675d4712c63c16892b0baadca18cebdc6887696edb5e30",
     "pipeline/multi-agent-refs/features/research.md": "776c9f3b644f8ff355108000b4a7381ff173e38811e8e2a73ef66e756d60c169",
-    "pipeline/multi-agent-refs/features/review-decision.md": "ac7bf33ec86c311680d9ae8a4d1d0d0b564d0bf0cfe80e270cc98d3abceb65cb",
+    "pipeline/multi-agent-refs/features/review-decision.md": "33b018b8e64ce1ac10197be8eb51f42602930b618b5c1501e06766957e0ec64b",
     "pipeline/multi-agent-refs/features/review-delta.md": "740cbefbd705a013b708921f2265f12d54d96823f1c46b5c1e644ebbdf7a8f85",
     "pipeline/multi-agent-refs/features/review-file-set.md": "a751888bce82a8e6970c9abe7f354c5c0704956e5278aeb091b893be0df5c1ef",
     "pipeline/multi-agent-refs/features/review-multi-repo.md": "f06857b2fa984ee6ca8cdf4360485947b55217056e5e439839c56871f9eb7595",
@@ -314,6 +314,7 @@
     "pipeline/multi-agent-refs/features/unattended-security.md": "18da3d51c175a42ab6312051a50b9d0339524dad2cc34e0350de62fbf0cece91",
     "pipeline/multi-agent-refs/features/url-enrichment.md": "72e01a799d9fa54b56c762ba404a9f9236adbbf98320e395a96f6b0f5917e76b",
     "pipeline/multi-agent-refs/features/usage-reporting.md": "095d86b839c1289c1023919da3972e561c1bbd4a32a1fc9f8e694abe887005ac",
+    "pipeline/multi-agent-refs/features/valven.md": "03b256885740faa83b6f030890e5caa7970005802e1109de17311474e2c594ae",
     "pipeline/multi-agent-refs/features/verify-by-test.md": "b0735adaa7ead797167b8d9ea48a10851a138083c6e638738cc96c66b02a1e37",
     "pipeline/multi-agent-refs/features/verify.md": "1a6db5e7239eac01e51100353013abd16bf785a7fce88b40139fca27f4166be4",
     "pipeline/multi-agent-refs/features/visual-evidence.md": "2b6aa2e4ff05c7a1fbe9e0fedfa4b28b9ad01c93a64f1ca6f6cd3e02293866aa",
@@ -336,11 +337,11 @@
     "pipeline/multi-agent-refs/phases/log-format.md": "62d51e57cca8445ab40f3c0dc29615e4b5c8e4743286bf9ef0173610e81397aa",
     "pipeline/multi-agent-refs/phases/modes.md": "0733e20dce458c09f30343db9149fc93bc5a4c9531670b93952f223811dcb1aa",
     "pipeline/multi-agent-refs/phases/operations.md": "9506a26684abfff1e332d92c2321e840544fd4f049aff9f118731e198dabca94",
-    "pipeline/multi-agent-refs/phases/phase-0-init.md": "8bb87d3691062678a431c9d90f893d32f0d2faf5688dec289772832a1755bdfc",
-    "pipeline/multi-agent-refs/phases/phase-1-plan.md": "28bebce1dd0b1adee19cb9fb7a56ebcd07e318d592590698c75fde7f3134e6b7",
-    "pipeline/multi-agent-refs/phases/phase-2-dev.md": "d9774b3f10cabdd521952b21023ed624fee52c1191ce0a27e6bcc84cb9a92c4b",
-    "pipeline/multi-agent-refs/phases/phase-3-review.md": "0f620c29ed3f1b6c968718d1c3500abab4e7b8c1c1e3c84c3bbf9087ce43703c",
-    "pipeline/multi-agent-refs/phases/phase-4-commit.md": "53df1abe25875881294f1f1a0fcc093eb53f9ab463927a55e1c3964efd7ce733",
+    "pipeline/multi-agent-refs/phases/phase-0-init.md": "8e3047206dbee5fdecea1e3891dca1513075e84f43e0b65b14529e91691fe3d3",
+    "pipeline/multi-agent-refs/phases/phase-1-plan.md": "302adb4ae91b844b636e738e364749560f75685ad335bc800d52cf4ff6d4b3af",
+    "pipeline/multi-agent-refs/phases/phase-2-dev.md": "ebd4c2e6992f286e2215c4deb55199a01804785255afb55e1730d6a4287e96df",
+    "pipeline/multi-agent-refs/phases/phase-3-review.md": "bb18ce516e11e66cfd73532d8deaaa1c9d7cd7fb5bf274e6c574cc598d08a096",
+    "pipeline/multi-agent-refs/phases/phase-4-commit.md": "61eb5a7a358e4cfaab2024dcd9c374f8001733a1c7a440cdc01cadfbf6c77022",
     "pipeline/multi-agent-refs/phases/phase-5-report.md": "3d333dc4b072c98eda3f287f884e12de62cda7255b12de7725a72903cefa6016",
     "pipeline/multi-agent-refs/picker-contract.md": "bf1b3043946e4aa588203060d47d182ca1ee58b10dec27a85a7b74afde3565ed",
     "pipeline/multi-agent-refs/platform-parity.md": "43a3836efc359c6b7d30af38d66408d8d18661e72e5165b25bb8e15953e6feaf",
@@ -390,7 +391,7 @@
     "pipeline/rules/swiftui-qa.md": "8c4afe9e72413e7bdab655f3d17588469e80ac34cb7ad2a690901fc5b6534818",
     "pipeline/rules/tdd.md": "4c1b3114506aa9794c9bb1e1aee1b1bbb4a993d192342e5697cc00bc2f6ea4a2",
     "pipeline/rules/testing.md": "695be5520b65451f0aa300a9643df2c05e607ff6ad372201ea34798dc5998bd5",
-    "pipeline/schemas/agent-state.schema.json": "4065712c5a646f8b3a59111063319d4c378cd22e32a7b3089c69982bee3c7543",
+    "pipeline/schemas/agent-state.schema.json": "c5790d53ea138662402f2a391fa24c2ca19e74d09b09e6507dc60689765b2c2f",
     "pipeline/schemas/analysis-output.schema.json": "41826f4bf7c96778f8cdbcc68531e984087897d438b7b49ac5a93fc29db47916",
     "pipeline/schemas/analysis-spec.schema.json": "230e08b931c42534e24f699f77c75a87c95e53b669b33c07930c4abb0c31281b",
     "pipeline/schemas/answer-request.schema.json": "29d4211a2a05a230e0707b171b73341d2e56f6b83edb178b731905211aab4e23",
@@ -442,7 +443,7 @@
     "pipeline/schemas/plan-todos.schema.json": "f1dcf8df338b29bbc1d874addd3408c0841a5f869c0b6075efd9242e3e8552d6",
     "pipeline/schemas/planning-output.schema.json": "bc6eda32ecd435cf84d846078f9d38347f8f741f8a427cff15913dd6c380d4b8",
     "pipeline/schemas/pr-request.schema.json": "ae75c4856349d62834802b1189af516bb6fb3d36646831b7ff2fa61d938afcd0",
-    "pipeline/schemas/prefs.schema.json": "951e906952aa6aebd06f15ad084e695db7e9801b52e334740fbf44297b32faca",
+    "pipeline/schemas/prefs.schema.json": "f45d061f28b1452f38aa2a3999560eb5a51a683f9c441017c46fb962387789d6",
     "pipeline/schemas/repo-profile.schema.json": "1a74ef8330da9a26a5a70955f6f9cbb20eda54a8615efaf86c7993d420a7f04e",
     "pipeline/schemas/repos.schema.json": "a9bf56f25c66201c170912e3389bd73e4a3f61922410f83e31a6c6ba47aee861",
     "pipeline/schemas/research-output.schema.json": "54e3ba1b04fdc20fbaa84333b943a8ab95d1395c7b0e0aedc67929184cb49523",
@@ -555,7 +556,7 @@
     "pipeline/scripts/gc-worktrees.sh": "06d0a53b9293531f4b8501618648440b668ba1ef60c121576c55b0e203dcfc62",
     "pipeline/scripts/gen-facts.mjs": "6ba70f7db881c3e3577a5ce3dcbfda09aa240f728ee577b019f2176d8051fd67",
     "pipeline/scripts/gen-mode-dispatch.mjs": "41261f7af9026fe19f9f96f314a85d226edd769081c02e5388310cf71a411ba7",
-    "pipeline/scripts/gen-skills-index.mjs": "64606fb3165786ed1488cc368dcbe8f53d2e9402f02578823a31838b9730180d",
+    "pipeline/scripts/gen-skills-index.mjs": "24ab4a6020bccadf768b16adf22fe4ce3f710b1ded6ca154fae361a84d4c8434",
     "pipeline/scripts/git-path.mjs": "c035624f1ab924039b37e0911f56c6a1fa781ac41dc89fadfdaa4305f4359c12",
     "pipeline/scripts/github-ssh-setup.sh": "5a9e1836d80e4e176806c143a3c8ba4c1b9c4274ed49aac71f33bd40de31968b",
     "pipeline/scripts/glob-match.mjs": "c01722f2f60ef70838cbfeef55dfb8381b49c358c7a808a5b297a92cdeccf033",
@@ -590,7 +591,7 @@
     "pipeline/scripts/owned-path-gate.mjs": "86b17e7a723d30056fac89026790e33cab891a549ffbda50b9e90d9a7675bf11",
     "pipeline/scripts/package-manager.mjs": "211046f0e32a05a0ac977a285892a4ad87e1d1e362573b048c8accd45c706d02",
     "pipeline/scripts/phase-banner.sh": "acca704968d6263810de5804ea50a96b7aab7472ec98a7149d92b78b380d8fa0",
-    "pipeline/scripts/phase-tracker.sh": "0cad7a8073a274d609f6e3473d8eb448ca295ca482c7a9274d7d07038b6da20d",
+    "pipeline/scripts/phase-tracker.sh": "a3a72a3a39c8615707f1b3a77c60224ab9747f4dbb5401dc089a8c28d40e6356",
     "pipeline/scripts/phase0-exit-gate.mjs": "848244c4712c16edd2103b451f9043d20416710dc208d5fc4993c3fd008f32c6",
     "pipeline/scripts/phone-devices.mjs": "f32288cbe56670eecb7d3a4b43f9ebcb4baeac5eeec357322fe19399603d59e3",
     "pipeline/scripts/plan-coverage-gate.mjs": "1a83bc52584438a9bd5cba96d2ddefed92a6a317d30ee695e67ef6c00b93e5a8",
@@ -598,7 +599,7 @@
     "pipeline/scripts/plugin-refresh.sh": "687a33199ad963616ab537e32210ec8c967e76ecc42f494ee8a1dc9fe947fc30",
     "pipeline/scripts/pr-request.mjs": "e6f4ded2366c6599bb345b3011ecc771e13b8a1561afa4c9a50bca4edff17456",
     "pipeline/scripts/pre-commit-check.sh": "3692ef40b08968e15e8a4c7b873f1e9fd264f4809976cb616063782f2ef993b1",
-    "pipeline/scripts/pre-push-check.sh": "e449aff7f0336d7d624eff4c6221f56d8621ba9d010669601755e57fd4ee02c7",
+    "pipeline/scripts/pre-push-check.sh": "4a1554a625df4745a829c0df294db7ce450fbe44fe624e562008e9912be78925",
     "pipeline/scripts/probe-evidence-capability.sh": "ac74252eed6b773fdbc7ec475a63606925f1ba7b5e7c6f911329f46fd920eae7",
     "pipeline/scripts/probe-store-key.mjs": "b46dfcf444c95d0bb61de36823314945dacaaacb8f35841d153dcfcde8e4df1a",
     "pipeline/scripts/prune-logs.sh": "c5587b33104c7253e07be8cce8249b50014c52dfdf232de637811ffdd88e95e4",
@@ -611,7 +612,7 @@
     "pipeline/scripts/repo-profile.mjs": "5f0cf90c59accdb0bb763fab9512e271e3cc4c8bc930ece137d94baa5c8e08d9",
     "pipeline/scripts/require-supported-version.sh": "490d681a8c8fb510082bc6f2325965598b3aa3b4720fe5c6e08e371c7c9073f4",
     "pipeline/scripts/research-gate.mjs": "66b0f7521fea5efa0085b9d4f31b9ce9c5c1719a7e0395ca176252c96ad974c1",
-    "pipeline/scripts/review-decision-gate.mjs": "b54cce49be270a1291571f63563b3a3e11e2417493bd8615c2a58bd7ff41b393",
+    "pipeline/scripts/review-decision-gate.mjs": "81e5529e587cf67af696446b80ad3a195e728340b13a815d7d702b039efb0325",
     "pipeline/scripts/review-delta.mjs": "14a2de7ac81e7f43a634423f920f9931bb4a27441b8ba3dc8e53ec1f6a6ed54a",
     "pipeline/scripts/review-file-filter.mjs": "8b1fd9661b8d61b4282a4579ef360f952c827f90520b69ffde4770fdaeaaa05b",
     "pipeline/scripts/review-scope.mjs": "60be90f1dce0a87071695bbedf17eb4e8600b1c742b97aef8cbea41802315b93",
@@ -649,7 +650,7 @@
     "pipeline/scripts/triage-memory.mjs": "2d8541145f1749593ae5728fb4c9eb3001484edb5e4d37be473aeec34d1dbe7c",
     "pipeline/scripts/ui-tree-dumper.swift": "a09e42ef069eafa08c05afd8333e05b754ef6a7d8b9687712039b0f2c9801273",
     "pipeline/scripts/unattended_policy.py": "f1df6470c798bd7d4bc9f8338eaabf98bdcfab00198d98b7e2e654aab84b709c",
-    "pipeline/scripts/uninstall.mjs": "880923522ef59fdd98cb7ecb1bdc85c0f15d1e2eed2d79d6d353e88712ca95fa",
+    "pipeline/scripts/uninstall.mjs": "88faf870f80a323d46b3eae6687f1d7eab16462d3d020ce4ed893f931e946106",
     "pipeline/scripts/update-check.sh": "9c00647e7ca4249414b2e5af08f61705ab5bd2106b6f66ae8ebce8aa143dc957",
     "pipeline/scripts/update-issue-progress.sh": "ccfef87743e91272e009e396ac07461d2784b2fa84a06c802a582526eeeb9ed9",
     "pipeline/scripts/usage-identity.mjs": "47c1f907fb1ab47672687ea0cbf2d0737985ae91ec2b48b4fe260e14c3d35d70",
@@ -665,7 +666,10 @@
     "pipeline/scripts/validate-state.mjs": "ac2cfde75fe216a7549ba476c58f777f27d36e068de3796909926d68de2fb65a",
     "pipeline/scripts/validate-test-gap.mjs": "14fa89867e49497adb2b88a3290e78d0f263afa74a5b83b062115fc5a22204f7",
     "pipeline/scripts/validate-triage.mjs": "7cd78686494c4dc003b4cd66817dfe583adbdab536b54da3fbb80c9fa0e1a216",
-    "pipeline/scripts/verify-citations.mjs": "ed1c3d7d0dbebbc64a26524f0f321d3a0ec1318cbb60dd4517d6b3db77e7fd74",
+    "pipeline/scripts/valven-gate.mjs": "67a44dbcc79e90c83fc03f9fc97876f65af8f24daaa2a2060acc06932c63fd3a",
+    "pipeline/scripts/valven-port.mjs": "5b064d67b8a39896f64fdead7aa65ef8ce747cf58cf44bbee90025abe4300247",
+    "pipeline/scripts/valven-split.mjs": "c5700ee1738bc4a215321a45bc093c325ec132410c32660e72b76f38bea8d0eb",
+    "pipeline/scripts/verify-citations.mjs": "e3c6a3edb1d360a9ea8690d35157faa47d312dfdc87595a87350c456cc72319c",
     "pipeline/scripts/verify-skills.sh": "871fcdfe5567232cd49a4cce4401911a06c8df6ab712d0597e17ce1bf0f63d80",
     "pipeline/scripts/verify.mjs": "fdc9843dc33b37d08d132617f158b8fe10cc4ab3be5bf31714bf2453ac0f714f",
     "pipeline/scripts/website-deploy-commit.sh": "73cae49db83cf98eeeb08eb8852a13912bd5f05855319b184e348b9ca4dff44f",
@@ -674,9 +678,9 @@
     "pipeline/scripts/worktrees.mjs": "90dfd09b70fffe9b56c331a4ae2692cc248f4898f4ee6aee4239ef0b20888a90",
     "pipeline/scripts/write-state.mjs": "e1198bf970eace07d3eff22b394808a526e473df65d3d58aa2d5a12cfdac8b49",
     "pipeline/scripts/write-store-config.mjs": "b994a061f6febb2ca3d396074d8b51d2c1c1f991d3072d321703380da3639a56",
-    "pipeline/skills/.skill-manifest.json": "ab6db9b72fc52b7edb3116f4baaaf0a6ed81515db74df3211aa9463c533534a4",
-    "pipeline/skills/.skills-index.json": "042b1090f3e2ca310c6ce70d1bb304e8c7f96bd73133e504b95d83801608e470",
-    "pipeline/skills/shared/README.md": "ba55209d20e44c9356fe06df81d1bd33d547fcb9656191a464f126c76eba31e9",
+    "pipeline/skills/.skill-manifest.json": "08d53301893d994366854c8343e4a019f607c929b5e32018ff3fd0a27691888c",
+    "pipeline/skills/.skills-index.json": "4fb9440c54d0850a43685c4ac3a9be2f74bd8a75d9749e3e53d3e5367cc9e11e",
+    "pipeline/skills/shared/README.md": "79f26b8c5210838d16ab448fef118ac9dfc2fb16d48741c08df10ba96b4a9d05",
     "pipeline/skills/shared/core/apple-archive-compliance/SKILL.md": "7239fef717ea45b79276bfcc2c3903acd57950b6e00dd6a2a66399c4b09cbd51",
     "pipeline/skills/shared/core/apple-archive-compliance/references/rules.yml": "25129ce6d416242ac04c4032f7561e0c2761ab8bbadf08d9c9f49b573a663389",
     "pipeline/skills/shared/core/google-play-compliance/SKILL.md": "3089e8c5f99c1ec7c1358394c398335ccb5ebc20ca05d60d870127da4592de34",
@@ -718,7 +722,7 @@
     "pipeline/skills/shared/core/multi-agent-review-analysis/SKILL.md": "6c3428841fa62d7e5f36dd80465b09d6f695a2e89608cbb49a0d44cc3c7d289f",
     "pipeline/skills/shared/core/multi-agent-review-issue/SKILL.md": "7409755903a3c71c55643001f784c1c044ca153097f8ca6612c54b87f4ebcbb5",
     "pipeline/skills/shared/core/multi-agent-review-jira/SKILL.md": "a17a1f11fcf6c75640452e53ddddaaf906ff9e3ebfeda73e333f44db02515352",
-    "pipeline/skills/shared/core/multi-agent-review/SKILL.md": "1cbe44b2ec63e0e158ded35825876e7dc9c45732fc9b067f0655e68823188efb",
+    "pipeline/skills/shared/core/multi-agent-review/SKILL.md": "cd500e32efdf6c8f36da5bb2e43d2558d096e33cd3274aead5118dd2c14f118a",
     "pipeline/skills/shared/core/multi-agent-route-off/SKILL.md": "a30c0b9b73d5101c70c147599273019cf357969c37bc799017a9f6de4b8686a8",
     "pipeline/skills/shared/core/multi-agent-route-on/SKILL.md": "a807767460b09455087d48a7dd45036be788f67997475360acab29f2422f425b",
     "pipeline/skills/shared/core/multi-agent-route-status/SKILL.md": "b473b670b3f8535b295752eb5aed8b01cba8d1ed6763ae4d80d9cc2dbb1f7794",
@@ -745,6 +749,8 @@
     "pipeline/skills/shared/core/multi-agent-uninstall/SKILL.md": "9dccf78ffc2fb014d83f67d683d395f56f4fad8b5a36b9aa84e6cbd075b58818",
     "pipeline/skills/shared/core/multi-agent-update/SKILL.md": "d96e18b70bab0a601057f75f212dd4fb563db0cb250607c770ce1c7a1df4b1d0",
     "pipeline/skills/shared/core/multi-agent/SKILL.md": "3dd44ccc00e41c09e59ad223900a391f80158bd3f69e45d67c684285bc42418d",
+    "pipeline/skills/shared/core/valven-rules/SKILL.md": "274299b75e36991941b8402ae025967ce553878100c1a3878a955d27f5b7db9e",
+    "pipeline/skills/shared/core/valven-rules/references/rules.yml": "b08b9bc1c35104bc14d64ae8a5f1dbec00306cb9d010996133e27b4c945de77e",
     "pipeline/skills/shared/external/NOTICE-avdlee-swiftui-agent-skill.md": "24df1d1dfb47b06b8fafb98938cf1b353fb0245c3a8f8212e197321d537dadff",
     "pipeline/skills/shared/external/NOTICE-dimillian-skills.md": "b98a170d97836f00ac6ee9c80e0befde324a6062071dc06a7eedce65fa5141cd",
     "pipeline/skills/shared/external/NOTICE-paul-hudson-skills.md": "bca5fe8779df70fb0f234483d65ff3562c67521e719b69b22aac260803b75244",
@@ -1302,6 +1308,6 @@
     "pipeline/skills/shared/external/xcode-project-analyzer/references/build-settings-best-practices.md": "26f1a3a23b3fece4b067fb094ab12fb6bd7dee33e97044d515db3cf70bc9b8a4",
     "pipeline/skills/shared/external/xcode-project-analyzer/references/project-audit-checks.md": "eb61ac8e1329eccac33e7d8b4c466003f50cca6b1a23e2be118d1f6a9af62e53",
     "pipeline/skills/shared/external/xcode-project-analyzer/references/recommendation-format.md": "ad8eb87228be739d2dd53d0b927558fc9e68b2135e1b1eec475a981c4cd1feb2",
-    "pipeline/skills/skills-index.md": "bdb03634f0174c073d7c3c13f068b49059ee8c79a5a552b9cf00d218e8d7e7cd"
+    "pipeline/skills/skills-index.md": "0775d77f39736511ebac57f38080a275e2af131b7fad8f323a36b7431f93b151"
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "20.15.0",
+  "version": "20.16.0",
   "description": "6-phase AI development pipeline with full orchestration on Claude Code, Copilot CLI and Codex CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase cost ledger, persistent learnings memory, wiki generation, commit automation. Token-preserving uninstall.",
   "type": "module",
   "main": "index.js",

package/pipeline/commands/multi-agent/review/SKILL.md

@@ -182,6 +182,47 @@ Persist `agent-state.review.moduleGuides = [<repo-relative paths>]` and inject i
 
 Scope note: a guide governs only files under its own directory  -  a guide found under one module must not be applied to a sibling module's changes in the same PR.
 
+### 2c. Valven delivery rules  -  required on every input
+
+The `valven-rules` registry (`$HOME/.claude/skills/valven-rules/SKILL.md`) is applied to every review, in `review` mode. Collect what the gate needs, then run it:
+
+```bash
+VG_FILE="/tmp/multi-agent-review-${TASK_ID}-valven.json"
+VG_ARGS=(--mode review --out "$VG_FILE")
+case "$kind/$provider" in
+  branch/local)
+    VG_ARGS+=(--repo . --base origin/develop --head "$ref") ;;
+  pr/github)
+    gh pr view "$pr_number" --repo "$org_repo" --json headRefName,baseRefName,body,commits \
+      > "/tmp/multi-agent-review-${TASK_ID}-pr.json"
+    jq -r '.body // ""' "/tmp/multi-agent-review-${TASK_ID}-pr.json" > "/tmp/multi-agent-review-${TASK_ID}-body.md"
+    jq -r '.commits[] | "\(.authoredDate)\t\(.messageHeadline)"' "/tmp/multi-agent-review-${TASK_ID}-pr.json" > "/tmp/multi-agent-review-${TASK_ID}-commits.txt"
+    VG_ARGS+=(--branch "$(jq -r .headRefName "/tmp/multi-agent-review-${TASK_ID}-pr.json")"
+              --pr-body-file "/tmp/multi-agent-review-${TASK_ID}-body.md"
+              --commits-file "/tmp/multi-agent-review-${TASK_ID}-commits.txt") ;;
+  pr/bitbucket-server)
+    # Same credentials as Step 2. PR: fromRef.displayId + description; commits: values[].message.
+    # Write the description to ...-body.md and one "<ISO authorTimestamp>\t<first message line>" per commit to ...-commits.txt, then:
+    VG_ARGS+=(--branch "$BB_FROM_REF" --pr-body-file "/tmp/multi-agent-review-${TASK_ID}-body.md"
+              --commits-file "/tmp/multi-agent-review-${TASK_ID}-commits.txt") ;;
+esac
+```
+
+For PR input: when the cwd is a checkout of the same repo, `git fetch origin "<headRef>"` (this moves no HEAD) and add `--repo . --base "origin/<baseRef>" --head FETCH_HEAD`, so sizes and the rework ratio come from history. Otherwise add `--diff-file "$DIFF_FILE"`; the rework rule then reports `not-measured`, which is stated in the summary rather than read as a pass.
+
+```bash
+node "$HOME/.claude/scripts/valven-gate.mjs" "${VG_ARGS[@]}" >/dev/null
+VG_RC=$?   # 0 clean, 1 findings, 2 could not run
+```
+
+- Exit 2: print the stderr line and continue the review with `Valven: not measured (<reason>)` in the Step 6 summary. Never print it as passed.
+- The gate's `findings[]` join the reviewer findings at Step 5 with `tag: valven`. They are measurements, so triage accepts them unless the task is exempt; an accepted `important` or `blocking` one makes the Step 7 decision NEEDS WORK.
+- When `splitRequired` is true, run `node "$HOME/.claude/scripts/valven-split.mjs" --repo . --base "origin/<baseRef>" --head <head>` (plan only, no `--apply`) where a checkout exists, and append the slice table (branch, lines, files) to the `VLV-SIZE-01` finding's `fix`, so the PR comment says exactly how to split.
+- When `VLV-AGE-01`, `VLV-BEHIND-01` or `VLV-TRACE-03` fires and a checkout exists, run `valven-port.mjs` with the same base and head (plan only) and put its result in the finding's `fix`: the new branch to open, the commits that stay behind, `sharedWithBase[]` to re-test, then "open the new PR, close this one with a link". Contract: `$HOME/.claude/multi-agent-refs/features/valven.md`, "Old work".
+- The registry's judgement rules (`rules:` block: `VLV-SCOPE-02`, `VLV-PRDESC-02`) go into every reviewer prompt in Step 3, with the PR body when one exists. Each reviewer returns a verdict per ID.
+
+Step 6 adds one line under the table: `Valven: <n> finding(s)  ·  <changedLines> lines / <fileCount> files  ·  split: <yes N slices|no>`.
+
 ### 3. Launch parallel reviewers  -  host-CLI dependent
 
 Every host runs three reviewers; only the second slot differs, because GPT-5.4 exists on Copilot and Codex but not on Claude Code, where Opus fills it.
@@ -218,7 +259,7 @@ Never dispatch a Fable reviewer or a Fable triage on the model list below alone.
 
 The rung switch and its resolution: `$HOME/.claude/multi-agent-refs/features/model-fallback.md`.
 
-Each reviewer receives the diff, the module review guides from Step 2b (when any were found), plus the standard reviewer system prompt (see `$HOME/.claude/multi-agent-refs/phases/phase-3-review.md` for the prompt contract). Output: structured `findings[]` per reviewer.
+Each reviewer receives the diff, the module review guides from Step 2b (when any were found), the Valven judgement rules from Step 2c, plus the standard reviewer system prompt (see `$HOME/.claude/multi-agent-refs/phases/phase-3-review.md` for the prompt contract). Output: structured `findings[]` per reviewer.
 
 ### 4. Store-compliance cross-reference
 

package/pipeline/multi-agent-refs/features/review-decision.md

@@ -102,6 +102,7 @@ result, before Step 3.8:
 node "$HOME/.claude/scripts/review-decision-gate.mjs" "$TRIAGE_FILE" --state "$STATE_FILE" \
   --integrity "$WORKTREE/.pipeline/test-integrity.json" \
   --integrity "$WORKTREE/.pipeline/owned-path.json" \
+  --integrity "$WORKTREE/.pipeline/valven-gate.json" \
   --source "$WORKTREE/.pipeline/security-audit-$ITERATION.json" \
   --json > "$WORKTREE/.pipeline/review-decision-$ITERATION.json"
 RD_RC=$?
@@ -113,7 +114,7 @@ nothing); `security-audit-$ITERATION.json` is the file Step 2.7 writes when the
 audit runs (`security-audit.md`). Both are files and not process substitutions
 of a shell variable with a `{}` brace default: bash 3.2, the stock macOS
 `/bin/bash`, expands that to `{\}`, and unparseable input is exit 3.
-`owned-path.json` is the file Step 1.761 writes. `--integrity` repeats, one
+`owned-path.json` is the file Step 1.761 writes, `valven-gate.json` the one Step 1.762 writes. `--integrity` repeats, one
 file per deterministic gate. Both gates always write their file, so a declared
 `--integrity` file that does not exist is unreadable (exit 3): the gate failed
 before writing. An empty one means no findings from that gate, and a missing or

package/pipeline/multi-agent-refs/features/valven.md

@@ -0,0 +1,83 @@
+# Valven delivery rules across the phases
+
+The `valven-rules` registry (`$HOME/.claude/skills/valven-rules/`) holds the rules; `valven-gate.mjs` measures them and `valven-split.mjs` turns an oversized branch into stacked pull requests. This file is the per-phase contract the phase docs point at.
+
+## Phase 1
+
+Work is built on one branch and shipped as small pull requests. Each task also gets an estimated line count (added + removed, tests included, generated output excluded), and the plan groups tasks into **PR slices** that each stay under the `VLV-SIZE-01` budget (`prefs.global.valven.thresholds`, default 250 lines and 25 files). Order the slices the way `valven-split.mjs` will cut them: renames and moves first, then data (models, services, repositories), then domain (view models, use cases), then UI, each slice carrying its own tests. Show the slice table in the plan (`slice`, `tasks`, `est. lines`) so the user approves the stack together with the plan. A plan whose total estimate exceeds the budget and shows no slices is incomplete. The estimate is advisory; Phase 4 Step 2.95 measures the real diff and splits by it.
+
+## Phase 2
+
+Gate 6 of the exit gate, after the secret scan:
+
+```bash
+node $HOME/.claude/scripts/valven-gate.mjs --mode dev --repo "$WORKTREE" --base "origin/$BASE_BRANCH" --worktree \
+  --out "$WORKTREE/.pipeline/valven-dev.json" >/dev/null
+```
+
+**Gate 6** (valven-rules, dev mode). Exit 2 blocks the phase: the rules could not be read or git failed. Exit 1: `VLV-TEST-01` (source changed, no test changed) and `VLV-TRACE-01` (no issue key in the branch) are fixed here before Review. `VLV-SIZE-01`, `VLV-SIZE-02` and `VLV-SCOPE-01` are not fixed by editing: keep building on this branch, set `state.valven.splitRequired = true`, and Phase 4 Step 2.95 splits it into stacked PRs. `VLV-REWORK-01` is reported to the user with the ratio and continues. Contract: `$HOME/.claude/skills/valven-rules/SKILL.md`.
+
+## Phase 3
+
+Step 1.762, after the owned-path gate. The PR body does not exist yet, so `VLV-PRDESC-01` reports `not-measured`; Phase 4 checks it.
+
+```bash
+VG_FILE="$WORKTREE/.pipeline/valven-gate.json"
+node $HOME/.claude/scripts/valven-gate.mjs --mode review --repo "$WORKTREE" --base "origin/$BASE_BRANCH" \
+  --out "$VG_FILE" >/dev/null
+VG_RC=$?
+[ "$VG_RC" = "2" ] && HALT "valven gate could not run  -  see stderr"
+$HOME/.claude/scripts/log-metric.sh "$TASK_ID" 3 review.valven \
+  findings="$(jq -r '.findings | length' "$VG_FILE")" split="$(jq -r '.splitRequired // false' "$VG_FILE")"
+```
+
+Exit 1 is findings, not an error: they merge at Step 3.0 with `tag: valven`, and `review-decision-gate.mjs` counts them as gate-backed, so a single-source one is not downgraded. Triage accepts a `criteriaSource: "valven-rules"` finding unless the task is exempt, never rejects it as style, and keeps its `line: 0`, which `post-pr-review.sh` posts as a top-level comment. When `splitRequired` is true the fix is never "edit the code"; Phase 4 Step 2.95 splits the branch. With `prefs.global.valven.enabled = false` the file still lands with `enabled: false` and no findings.
+
+## Phase 4
+
+```bash
+VG_COMMIT="$WORKTREE/.pipeline/valven-commit.json"
+node $HOME/.claude/scripts/valven-gate.mjs --mode commit --repo "$WORKTREE" --base "origin/$BASE_BRANCH" --out "$VG_COMMIT" >/dev/null
+VG_RC=$?
+```
+
+- Exit 2 halts: the gate could not measure, and pushing on an unmeasured branch is the silent pass this step exists to prevent.
+- Exit 1 without `splitRequired`: fix in place. `VLV-COMMIT-01` and `VLV-TRACE-02` are squash and reword of this branch's own commits (`git rebase -i` is not available; use `git reset --soft "$(git merge-base HEAD origin/$BASE_BRANCH)"` and re-commit with the step 6 convention). `VLV-TEST-01` and `VLV-TRACE-01` return to Phase 2. Re-run the gate.
+- `splitRequired: true`: plan the stack and show it.
+
+  ```bash
+  node $HOME/.claude/scripts/valven-split.mjs --repo "$WORKTREE" --base "origin/$BASE_BRANCH" --out "$WORKTREE/.pipeline/valven-split.json"
+  ```
+
+  Render one row per slice (branch, lines, layers, files, `oversized`) and ask (`question` / labels in `outputLanguage`, `header` English `"Split PR"`): option 1 "Split into N stacked PRs" (Recommended), option 2 "Ship as one PR" (the review will mark it NEEDS WORK), option 3 "Pause". Autopilot takes option 1. On option 1 re-run with `--apply`; exit 1 (the stack's top differs from the branch) halts with `drift[]` shown. Then build every slice branch with the Phase 2 Gate 1 command, in order; a slice that fails is folded into the next one: delete the `<branch>-p*` branches (`--apply` refuses to overwrite them), re-run with `--budget` raised to the two slices' combined lines, and build again. The original branch is never modified, so every re-run starts from the same tree. An `oversized` slice is one file larger than the budget: report it, it cannot be split by file.
+
+  After a split, steps 7 and 8 run once per slice in order: push `<branch>-pK`, open its PR with base `$BASE_BRANCH` for p1 and `<branch>-p(K-1)` for the rest, title suffix `(K/N)`, and a `## Stack` section in each body listing every slice PR with the current one marked. The original branch stays local. Record `state.valven.split = {sliceCount, branches[], prs[]}`.
+
+Log: `Phase 4 Step 2.95: valven {pass|fixed|split N|shipped-whole}`
+
+### PR body
+
+**Valven body check (required, every PR).** After the body is written to `/tmp/pr-body-$TASK_ID.md` and before the PR is created or updated:
+
+```bash
+node $HOME/.claude/scripts/valven-gate.mjs --mode review --repo "$WORKTREE" --base "origin/$BASE_BRANCH" \
+  --pr-body-file "/tmp/pr-body-$TASK_ID.md" --out "$WORKTREE/.pipeline/valven-body.json" >/dev/null
+jq -r '.findings[] | select(.ruleId == "VLV-PRDESC-01") | .issue' "$WORKTREE/.pipeline/valven-body.json"
+```
+
+Any `VLV-PRDESC-01` line blocks creation: add the missing why / how-to-verify text and re-run. Other findings here were already handled at Step 2.95.
+
+## Old work
+
+`VLV-AGE-01` (a commit older than 14 days, by author date so a rebase does not hide it), `VLV-BEHIND-01` (more than 50 commits behind the base, or a merge-base older than 14 days) and `VLV-TRACE-03` (commits carrying another issue's key) mean the branch carries old or foreign work. The answer is never a rebase of the old history: the change moves.
+
+```bash
+node $HOME/.claude/scripts/valven-port.mjs --repo "$WORKTREE" --base "origin/$BASE_BRANCH"            # plan
+node $HOME/.claude/scripts/valven-port.mjs --repo "$WORKTREE" --base "origin/$BASE_BRANCH" --apply    # move
+```
+
+`--apply` cuts `<branch>-v2` (next free `-vN`) from the current base tip, applies the net diff with `git apply --3way` as one commit, and returns to the original branch, which it never modifies. Exit 1 is a conflict: the new branch is deleted, `conflicts[]` names the paths, and they are resolved by hand on a fresh branch. `sharedWithBase[]` lists the paths the base also changed; those are the ones to re-test.
+
+- **Phase 0.** A task that resolves to an existing branch runs `valven-gate.mjs --mode dev` against it first. An old-work finding means work starts on the ported branch, not on the old one.
+- **Phase 4 Step 2.95.** Old-work findings are handled before the size check: port, re-run the gate on the new branch, then split if a size rule still fails. A `VLV-TRACE-03` commit is removed from the port (`--head` at the commit before it, or a cherry-pick of the rest) and gets its own branch.
+- **Review.** The finding's `fix` is concrete: the `valven-port.mjs` plan (new branch name, commits dropped, `sharedWithBase[]`), then "open the new PR from `<to>`, close this one with a link to it". For `VLV-TRACE-03` it lists the foreign commits. Accepted findings make the review NEEDS WORK.

package/pipeline/multi-agent-refs/phases/phase-0-init.md

@@ -419,6 +419,7 @@ Branch name is deterministic  -  no user confirmation needed.
   # 0 = ref exists (collision) · 2 = no matching ref (authoritative "free")
   # anything else = the probe itself failed; REMOTE_ERR holds why
   ```
+- Old work is not reused (`features/valven.md`).
 - `REMOTE_RC` is 0 or 2 → treat as authoritative
 - `REMOTE_RC` is anything else → the remote answer is **unknown**, not "free". Log
   `Remote collision probe failed: <REMOTE_ERR>`, fall back to the local check only,

package/pipeline/multi-agent-refs/phases/phase-1-plan.md

@@ -326,6 +326,8 @@ For each identified change area:
 
 Create tasks using TaskCreate with imperative subject, description (what/which files/expected behavior), and `addBlockedBy` for dependencies.
 
+**PR slices (required):** `features/valven.md`.
+
 ##### Analysis citation requirement (every UI task)
 
 Every UI-touching task in the plan MUST cite:

package/pipeline/multi-agent-refs/phases/phase-2-dev.md

@@ -349,7 +349,6 @@ bash $HOME/.claude/scripts/phase-tracker.sh tokens 2 <input_count> <output_count
 
 Contract and rationale: `progress-contract.md` -> Token telemetry forwarding.
 
-
 #### Generated trees are not yours to edit
 
 Many repos generate part of their source: a service client from an OpenAPI spec, mock
@@ -399,8 +398,6 @@ reach Review at all.
 
 #### Step 1  -  Deterministic Gates (run BEFORE AI review)
 
-If any gate fails → fix first, don't waste AI tokens reviewing broken code.
-
 ```bash
 # Gate 0: Owned paths (repo profile), before the build
 node $HOME/.claude/scripts/owned-path-gate.mjs --repo "$WORKTREE" --base "origin/$BASE_BRANCH" --state "$STATE_FILE"
@@ -411,6 +408,7 @@ node $HOME/.claude/scripts/owned-path-gate.mjs --repo "$WORKTREE" --base "origin
 <test-command> 2>&1 | tee "{worktreePath}/.test.log"
 # Gate 4: Secrets  -  run the scanner against the staged diff
 bash $HOME/.claude/scripts/pre-commit-check.sh
+# Gate 6: features/valven.md
 ```
 
 **Gate 0** exit 1 blocks the phase: move each change where its `fix` points, revert the owned path, re-run. Exit 2 is a call error, never a pass: an unknown `--base` ref means fetch the base branch. Exit 0 with `skipped: true` gives its reason in `note`; log it. Contract: `features/repo-profile.md`, "Owned-path gate".
@@ -442,7 +440,7 @@ The subtraction never widens: match on identifier only, and when identifiers can
 **Gate results:**
 
 - All pass (including the evidence gate) -> proceed to AI review
-- Any fail -> fix immediately, re-run gates (no AI review until clean)
+- Any fail -> fix, re-run gates (no AI review until clean)
   Log: "Phase 3: Gates  -  owned:{ok/fail} build:{pass/fail} lint:{pass/fail} test:{pass/fail/inherited-red} secrets:{clean/found} evidence:{ok/unverified}"
 
 ##### Gate 5  -  Fortify SSC findings (runs when `state.contextLinks[]` contains a `fortify` entry, or when `prefs.global.fortify.alwaysCheck === true`)

package/pipeline/multi-agent-refs/phases/phase-3-review.md

@@ -145,7 +145,7 @@ node $HOME/.claude/scripts/owned-path-gate.mjs --repo "$WORKTREE" --base "origin
   --state "$STATE_FILE" --out "$OP_FILE"
 ```
 
-`--out` drops the old file; exit 2 writes none. A missing `$OP_FILE` is a gate error, never "no findings" (`review-decision-gate.mjs` exit 3 under the gates). Findings merge at Step 3.0. Contract: `features/repo-profile.md`.
+`--out` drops the old file; exit 2 writes none. A missing `$OP_FILE` is a gate error, never "no findings" (`review-decision-gate.mjs` exit 3 under the gates). Findings merge at Step 3.0. Contract: `features/repo-profile.md`. Step 1.762: `features/valven.md`.
 
 #### Step 1.77  -  Reviewer scope (cost gate)
 
@@ -377,15 +377,15 @@ ANON=$(jq -n --argjson r "$REVIEWERS_JSON" --arg t "$TASK_ID" --argjson i "$ITER
 
 `$REVIEWERS_JSON` is `state.reviewIterations[i].reviewers`. Findings come back with `foundBy: "Source A|B|C"` and every identity key removed. Persist the map to `state.reviewIterations[i].anonymizationMap` for Phase 5 per-reviewer telemetry, and **never put the map in a prompt**.
 
-Then append the Step 1.76 test-integrity, 1.761 owned-path and 2.7 security-audit findings, so they are adjudicated:
+Then append the deterministic findings (Steps 1.76, 1.761, 1.762, 2.7):
 
 ```bash
 SA_FILE="$WORKTREE/.pipeline/security-audit-$ITERATION.json"
-MERGED=$(printf '%s' "$ANON" | cat - "$TI_FILE" "$OP_FILE" "$SA_FILE" 2>/dev/null \
+MERGED=$(printf '%s' "$ANON" | cat - "$TI_FILE" "$OP_FILE" "$VG_FILE" "$SA_FILE" 2>/dev/null \
   | jq -s '.[0] + ([.[1:][] | .findings // []] | add // [])')
 ```
 
-Deterministic findings keep their `tag` (`test_integrity`, `owned_path`) and no `foundBy`: a reviewer finding may hallucinate, a gate finding is a fact. Security-audit findings carry their `security` envelope and `foundBy: "security-auditor"`; no audit file contributes nothing.
+Deterministic findings keep their `tag` (`test_integrity`, `owned_path`, `valven`) and no `foundBy`: a reviewer finding may hallucinate, a gate finding is a fact. Security-audit findings carry their `security` envelope and `foundBy: "security-auditor"`; no audit file contributes nothing.
 
 ##### 3.1 Short-circuit: no findings
 
@@ -550,7 +550,7 @@ A triage verdict is judgment; a failing repro test is proof. Runs only when `pre
 
 Compressed flow: dispatch ONE verifier agent (model `verifyByTest.model`, default `sonnet`) for up to `maxFindings` (default 3) accepted blocking findings. Per finding it writes ONE minimal repro test and runs ONLY that test (Phase 2 single-test invocation, build lock, log tee'd to `$WORKTREE/.pipeline/verify-<i>.test.log`). Outcomes: test FAILS as predicted -> `confirmed`, finding stays blocking and the test is KEPT in `redTests[]` as the Phase 2 rework RED test; test PASSES on every one of `verifyByTest.repeatCount` runs (default 3) -> `not-reproduced` ONLY if `evidence-gate.mjs --claim test --status passed` exits 0 on each log; a run that disagrees with the others -> `inconclusive` with `flaky: passed k/N`, finding moves to `deferred[]`, test deleted; compile error / timeout / not unit-testable -> `inconclusive`, judgment verdict stands. Stamp findings with `verification` (schema v3.2.0), persist `state.reviewIterations[-1].verifyByTest = {attempted, confirmed, downgraded, inconclusive, redTests[]}`, recompute `approved`, re-run `validate-triage.mjs` under the 3.2.1 gate. Whole step bounded by `stepTimeoutSec` (default 600); on breach or crash remaining findings keep judgment verdicts  -  never blocks. Telemetry per 3.4: `review.verify_by_test attempted= confirmed= downgraded= inconclusive= duration_ms=`.
 
-**Autopilot decision rule (every round, after 3.7):** run the call in `$HOME/.claude/multi-agent-refs/features/review-decision.md` (Wiring: `--integrity "$TI_FILE" --integrity "$OP_FILE" --source "$SA_FILE"`), merge its JSON into `state.reviewIterations[-1].reviewDecision`, repeat the `cp`. A blocker backed by neither two reviewers nor a failing test becomes important; on exit 1 or 3 run `gate-ledger.mjs park --outcome verification-failed --gate review-decision`.
+**Autopilot decision rule (every round, after 3.7):** run the call in `$HOME/.claude/multi-agent-refs/features/review-decision.md` (Wiring: one `--integrity` per gate file, `--source "$SA_FILE"`), merge its JSON into `state.reviewIterations[-1].reviewDecision`, repeat the `cp`. A blocker backed by neither two reviewers nor a failing test becomes important; on exit 1 or 3 run `gate-ledger.mjs park --outcome verification-failed --gate review-decision`.
 
 ##### 3.8 Cross-round delta + circuit-breaker trigger 2 (iteration >= 2)
 

package/pipeline/multi-agent-refs/phases/phase-4-commit.md

@@ -110,6 +110,7 @@ Branch **deterministically**, no implicit fallback. Read `agent-state.json` and
    - For EACH submodule with changes: stage, commit, push separately
    - Commit message uses same convention but scope reflects submodule: `{type}({submodule-scope}): {description} [{jiraId}]`
 6. Commit with convention: `{type}({scope}): {description} [{jiraId}]` or `[#{shortId}]`. When `node $HOME/.claude/scripts/repo-profile.mjs resolve commit.format --repo "$PROJECT_ROOT"` returns `use: true`, its `ticketPosition` places the ticket (`prefix` first, `suffix` last; `none` keeps this default unless confirmed or manual), `ticketStyle` its form and `scopeRequired` the scope. A profile hook with `amends-commit` or `writes-files` rewrites the commit: re-read the SHA after committing ([`features/repo-profile.md`]($HOME/.claude/multi-agent-refs/features/repo-profile.md)). **Local-only repos** (`projects[i].provider == "local"`) have no ticket, and that wins over any profile placement: the subject keeps the conventional prefix with no ticket, and the taskId (`LOCAL-...`) goes in the body footer: `Local-Task: {taskId}`.
+6a. **Valven (required):** `features/valven.md`.
 7. Push to remote  -  **skip per-repo when `projects[i].provider == "local"`** (no `git push`, no upstream config). Log `Phase 4: local-only commit {sha} (no push)` for that repo.
 8. Ask: "Want to open a Pull Request?"
    - **Skip the prompt entirely when `state.offlineOnly == true`** (all repos local  -  no PR target exists). Proceed to Phase 5 with `pr.status = "skipped-offline"` for each project.

package/pipeline/schemas/agent-state.schema.json

@@ -1476,6 +1476,22 @@
         }
       }
     },
+    "valven": {
+      "type": "object",
+      "additionalProperties": true,
+      "description": "valven-rules delivery gate. Phase 2 Gate 6 sets splitRequired when a size or scope rule fails; Phase 4 Step 2.95 records the stacked PRs it opened.",
+      "properties": {
+        "splitRequired": { "type": "boolean" },
+        "split": {
+          "type": "object",
+          "properties": {
+            "sliceCount": { "type": "integer", "minimum": 1 },
+            "branches": { "type": "array", "items": { "type": "string" } },
+            "prs": { "type": "array", "items": { "type": "string" } }
+          }
+        }
+      }
+    },
     "diffRisk": {
       "type": "object",
       "additionalProperties": true,

package/pipeline/schemas/prefs.schema.json

@@ -1500,6 +1500,27 @@
           "default": true,
           "description": "v8.3+ - Phase 3 Step 1.75 advisory diff risk scoring. When enabled, `pipeline/scripts/diff-risk-score.mjs` runs before reviewer dispatch and the top-N risk-ranked files are injected into each reviewer's prompt as a priority hint (security paths, public API surfaces, untested source changes, schema migrations). Heuristic, deterministic, no LLM cost. Default ON - the run is sub-second and never gates the pipeline. Flip to false to skip the script and the prompt injection entirely."
         },
+        "valven": {
+          "type": "object",
+          "additionalProperties": false,
+          "description": "valven-rules delivery gate (skills/valven-rules). Runs at Phase 2 exit (Gate 6), Phase 4 Step 2.95 before push, Phase 3 Step 1.762 and every /multi-agent:review. Findings carry tag `valven`; an accepted important or blocking one sets NEEDS WORK, and an oversized branch is split into stacked PRs by valven-split.mjs.",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "default": true,
+              "description": "false turns the gate off everywhere; each run then logs `valven: disabled by prefs` so a skipped check is never read as a pass."
+            },
+            "thresholds": {
+              "type": "object",
+              "description": "Per-rule overrides of the `gate_rules` defaults in rules.yml, keyed by rule ID, e.g. {\"VLV-SIZE-01\": {\"important_over\": 300}}. Only keys the rule already declares are applied.",
+              "propertyNames": { "pattern": "^VLV-[A-Z]+-[0-9]{2}$" },
+              "additionalProperties": {
+                "type": "object",
+                "additionalProperties": { "type": ["number", "string", "array"] }
+              }
+            }
+          }
+        },
         "reviewScopeGate": {
           "type": "boolean",
           "default": true,

package/pipeline/scripts/gen-skills-index.mjs

@@ -31,7 +31,8 @@ function categorize(name) {
   if (
     name.startsWith("multi-agent") ||
     name === "apple-archive-compliance" ||
-    name === "google-play-compliance"
+    name === "google-play-compliance" ||
+    name === "valven-rules"
   )
     return "pipeline";
   if (

package/pipeline/scripts/phase-tracker.sh

@@ -162,6 +162,14 @@ usage_live_ping() {
   # Smoke runs exercise this script's state handling, never the live dashboard -
   # a test gate must not leave phantom "running" rows on the timeline.
   [ -n "${MULTI_AGENT_SMOKE:-}" ] && return 0
+  # A tracker file supplied through TRACKER_FILE is a fixture unless it sits
+  # under a run root; only real runs reach the dashboard.
+  if [ "$TRACKER_FILE_FROM_ENV" = "1" ]; then
+    case "$TRACKER_FILE" in
+      "${LOGS_ROOT:-$HOME/.claude/logs/multi-agent}"/* | "$HOME/.multi-agent-unattended/"*) ;;
+      *) return 0 ;;
+    esac
+  fi
   local task="$1" phase="$2"
   # The emitter ships into whichever host tree installed it; a Copilot- or
   # Codex-only install has no ~/.claude/scripts, so resolve across all three

package/pipeline/scripts/pre-push-check.sh

@@ -53,7 +53,9 @@
 
 set -uo pipefail
 
-REPO_ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
+# Git runs the hook from the top of the worktree being pushed; the script itself
+# may live in a different checkout of the same repository. Measure the former.
+REPO_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || (cd "$(dirname "$0")/../.." && pwd))"
 cd "$REPO_ROOT" || { echo "FAIL: can't cd to repo root" >&2; exit 2; }
 
 if ! command -v node >/dev/null 2>&1; then

package/pipeline/scripts/review-decision-gate.mjs

@@ -176,7 +176,7 @@ export function rebuttalRecorded(reviewers) {
 }
 
 /** Tags of findings a deterministic gate produced, and the basis each one records. */
-const GATE_BASIS = { test_integrity: "test-integrity", owned_path: "owned-path" };
+const GATE_BASIS = { test_integrity: "test-integrity", owned_path: "owned-path", valven: "valven" };
 
 /**
  * Apply the decision rule. Pure: the input is not mutated.