@mmerterden/multi-agent-pipeline 20.20.0 → 20.21.0

package/manifest.json

@@ -1,15 +1,15 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "20.20.0",
-  "commit": "3eaded72b1509c7426dcba713df56fd72a0a2698",
-  "generatedAt": "2026-10-11T23:40:41.943Z",
+  "version": "20.21.0",
+  "commit": "e2d004d1ef1ce70ca42cd6083052d67ebff6c0c5",
+  "generatedAt": "2026-10-12T02:43:40.290Z",
   "algorithm": "sha256",
-  "fileCount": 1357,
+  "fileCount": 1360,
   "files": {
-    "CHANGELOG.md": "cf8a8131da43152e49483d7b7a9890a70f23e4df07c8c3e99f768ec632840e55",
+    "CHANGELOG.md": "2c2cac1fda619f849e9002de180cc0f02fbe0ad9ec15f7392cebd434b80ea56f",
     "LICENSE": "8d8c51aaf1e1538b180c69965fa038db71be86798cc3e26a143bebfefe16a43e",
-    "README.md": "a73f80dafda9ee106db1613bb359d56b02f53f9c3e16fb5691fef06719d2c2e9",
-    "README.tr.md": "7338743b34baa2128236775f8e11b7e7df486294e15f63268755e62d12e4fe4d",
+    "README.md": "4cb9fee0aed62bd1467bdc09954e011612b0de6e7895d663f297bc8778e00b2e",
+    "README.tr.md": "f30edbc26e51e311077fbb5b64234e70285db92340e6dadc259cfd673f104326",
     "SECURITY.md": "0eb89553ddcfc56bfe9712315b55a6630ee2f579631aaeccd6ad24f8ac769a0b",
     "docs/FIGMA_PIPELINE.md": "ea01f3ea5fef1a9cb316040a2d416fcf87dd4f2a14b5497aa00994a0b5dc7e6a",
     "docs/adr/0001-three-model-triage.md": "79a6f1025469f607a5859add21854052d7433bc213f4aceee2e159b613eeb6a1",
@@ -31,10 +31,10 @@
     "docs/adr/README.md": "6ff58bc97dde4f1d94df60e4e221396a46906682b429ef275fd813cd288956e1",
     "docs/architecture.md": "04fe9630d51646962bc5b660b4c82a8a8199984dc14d993aaf5c147c4c8f6968",
     "docs/best-practices.md": "f8b75b0d38b5896a6a852bb30a1edddeb24dab8b5b7b1d9313290e1241c72024",
-    "docs/ecosystem.md": "a1aa8134339f915749652814f4ee7291a37a926467fbb097109d5821f97aeeb8",
+    "docs/ecosystem.md": "44f7d2af1c3a655958bfc590d9d3ab10fcb2c9fe2f1558450f996dce0b45393a",
     "docs/engineering.md": "550528cd47c7d2c921729c68d0782a00ac8e77a4bdfec479f6749f9c3235d188",
-    "docs/facts.json": "3a12532eb8aab78df188985a05e593251ba248de79201ea6e5bba1ab696fbe8b",
-    "docs/features.md": "703435e309d1e37668c24bde3c2c0a7e4689a05d95449dcd394406fda1a19858",
+    "docs/facts.json": "8f1a90b5ece44ac36d2a8a58777e63038cddac208a044b092eefd709882524a4",
+    "docs/features.md": "17e9971ba14b940a562c99df727150fadc8688d793a8dda4b8204482d51c30a4",
     "docs/performance.md": "bbf2f3922c25dcba0c1a9e69ef420e3871a729af5b35009a49b48a5d3c5cd151",
     "docs/recovery-guide.md": "59a8f1b66b34cb9ff5507b3d54dac3b9915e184aa044d9c758d18cac818d510e",
     "docs/server-readiness.md": "ea21eee6a08c6fc0f2d1da8058acd5a50c556cea486d3acfe48fc0b23f4581fc",
@@ -52,7 +52,7 @@
     "install/_telemetry.mjs": "5433d753f909beed2c8789272bba05e245482c472f83d3444f58000c4c9a634b",
     "install/_unattended-profile.mjs": "e1ed82bde35d19105ee12c2a551eb778912b0e5c93ab227fd15c993098d98de0",
     "install/_xcode-skills.mjs": "1a7e20f1e6743324b941c5d3ecac9f94c65fff1534ffd9c63b39cbea4f8d101a",
-    "install/catalog-history.json": "9f8bd5ce3b6d5d49faec993a50111b4942be2a9402c4a5c38ba7ff6bdfde3e48",
+    "install/catalog-history.json": "39c2b310f9b7bd243141442aac55ab09d804ff085be794e0f4a43cce4ebb553c",
     "install/claude.mjs": "106ce353ebc19c8319d057ce342e1f989519510465c798399076b5f3d8727904",
     "install/codex.mjs": "08925fe9f3ecdf509b37f01105652c847475d20fcde2db0d679b9a7d663ca145",
     "install/copilot.mjs": "41dc394b8a3ae77cfd194ce0ca9bbcafce9bdce349f1f72eeb86569f993e15fe",
@@ -63,7 +63,7 @@
     "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": "6f50165ff1e18ae3f084464e171f7e710d106f37a96d77927b525509b5981de0",
+    "package.json": "72825278361b88c1b2742622d7ff2337a0f8c254467949052c6833793e3b1e89",
     "pipeline/agents/android-architect.md": "11fb74543cb0ebcf9525ca6654fe95d53da7229e0bf4a1149b31fd9005abc453",
     "pipeline/agents/backend-architect.md": "b02a606c301e4714131aed70ae6d16eeb77fbc819a001e2752cff2488d4246de",
     "pipeline/agents/bulk-reader.md": "6597052cd7d205bac2b1c7633f5232fe1a40730664a913b8eb77efd5a786dc25",
@@ -78,7 +78,7 @@
     "pipeline/commands/archive-guard.md": "16c5d3feaa91950402d62e66adc7fcf519a25d028a9303cb1e9c08af2765c04b",
     "pipeline/commands/deploy.md": "d20f95f3b1d2357c8c92f3047e8fe11eadf539ff13cab9b54f072f0ad697242a",
     "pipeline/commands/figma-to-swiftui.md": "cb198d279d36c6c34648ab9834433d00f81c9d427934cc1641c0e09f1878b0a6",
-    "pipeline/commands/multi-agent/SKILL.md": "accb6db9000040e519071f8414810063b8193ce9f3c310d1e935246685f58ab6",
+    "pipeline/commands/multi-agent/SKILL.md": "20e3d9af469af2e347700d1ff4a600e44a69a18f15f374ba107c011e52a1c31a",
     "pipeline/commands/multi-agent/analysis-jira/SKILL.md": "c08647b18a56f86690b7db7223e73194b6511f403796252ae8c17cb4265184cd",
     "pipeline/commands/multi-agent/analysis-resolve/SKILL.md": "48b72f59775ebfaab916afaeb2609e5694c0f7a3ce2bf2689cf25623d9755682",
     "pipeline/commands/multi-agent/analysis/SKILL.md": "8b92d8832f72e195408d6e8e137956df3a4920074ccc0a4a130f36995aa0f6d9",
@@ -119,8 +119,8 @@
     "pipeline/commands/multi-agent/review-jira/SKILL.md": "db8ecc7ec8c7040aac9c71dcf40dae194a76f146ab227833b909b45580b5347a",
     "pipeline/commands/multi-agent/review/SKILL.md": "dcbf4370351ed8b52e4cc9bc1167a1c385ef2cbb2a3a634e94b8c23d0e6e1f8d",
     "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",
+    "pipeline/commands/multi-agent/route-on/SKILL.md": "009668650f618daafe78db728f82ebac5b3af7fe34600283e18480b01ece572c",
+    "pipeline/commands/multi-agent/route-status/SKILL.md": "feeb453a21f56699df148ae944a6fa6c75dcb1a57061fef736e5c6a7273daf3c",
     "pipeline/commands/multi-agent/routines/SKILL.md": "570aa4c2349b0b4960d4a92ad94e1e63590a5e026032c2bb80155a89812a6cd3",
     "pipeline/commands/multi-agent/save/SKILL.md": "90c18995e4acd04564ee5041f72703426cee43aa940442e77d5e5d645ab1ad82",
     "pipeline/commands/multi-agent/scaffold/SKILL.md": "046d17dbf91719354fb7ba226996139b3a44a545fb9c956871b67ddfa795620a",
@@ -129,7 +129,7 @@
     "pipeline/commands/multi-agent/search/SKILL.md": "231f0dd266907423cc45feeadc4170852dc6fd45239e0bee3ee4e08d4d0f5958",
     "pipeline/commands/multi-agent/security-review/SKILL.md": "dfc2fad484c81169912062391f7ad97500ef113d95741902e5e18e7dd60b6da1",
     "pipeline/commands/multi-agent/serve/SKILL.md": "e931219d8be258a155a692d23c2b275c2e7e0a761b3f0354c943e26d2ce7b035",
-    "pipeline/commands/multi-agent/setup/SKILL.md": "b6b4af9eac2ec9454dda08d960ab9ed559421e167f6726915b451e86fbb3f058",
+    "pipeline/commands/multi-agent/setup/SKILL.md": "2f55f1ab3d3c2052584e4d189bb3cbaf11f7096da0f55d618b5c7c28df08a71a",
     "pipeline/commands/multi-agent/stack/SKILL.md": "26ecb48b28b61250330edb26fdfd014e401992e4f1329c572766ba4e2dc6e35d",
     "pipeline/commands/multi-agent/status/SKILL.md": "b08338841a5282f8ae2494751001aa31cbf4829146a58ed2c395b1c062b48443",
     "pipeline/commands/multi-agent/steer/SKILL.md": "07e738c228ba328f717f86e97e7af207df090b16433e28e613d430c3ff0aee3e",
@@ -203,11 +203,11 @@
     "pipeline/lib/jira-publish.sh": "a32e6a682ae730ddd9c6df64b9ece1fb73c797111c63f5c247d7e733668da6b7",
     "pipeline/lib/json-file-lock.mjs": "6ff8d8d7b890fc549e07287eca1e8261b69f930ec523d08fb73786677aa0a45a",
     "pipeline/lib/md2confluence-v3.py": "3677ca47931e4b3d0fd2ce3e11299fc5f6d24799eb8332e37dd60b6c3c4653a2",
-    "pipeline/lib/model-dispatch.sh": "7edd5c92d41ee3bf74972e0827ccbb671853d5410e7fb0af0b7cb020f95e05c5",
+    "pipeline/lib/model-dispatch.sh": "6500a5a7cb6a4c099cf1d01678bc9465a3d4eb1001e1f516dcc5eacd69577158",
     "pipeline/lib/model-rung.sh": "8cecb4d390f306270713bd162e311dee879995e393970405c9a8f9af11da1727",
     "pipeline/lib/multi-repo-pipeline.sh": "5cca6bcc4fb857448ddadb31add343952be89423a328267e56496c7b7cdc7710",
     "pipeline/lib/normalize-text.mjs": "c2eeed65ab85cdc27a12ecaadc45dfa00b49a7611250c9ad881b9e93882a51c1",
-    "pipeline/lib/outbound-gate.mjs": "1ebc840e975f19b0da4699b3a37361ecc8a2be1a7a558d2b2fb39b8b64244011",
+    "pipeline/lib/outbound-gate.mjs": "669194caf8f3c2b469e836866bcb5aa979cde870924f5f783be62ee8d11f615d",
     "pipeline/lib/owned-path-gate.mjs": "28e75cf021ee43bf8c6369f72d27f426c79e8f4a4ab5ef99a009ac6399669319",
     "pipeline/lib/parse-complaints.sh": "d787ce870f141cf7f881da80fab4320814044554065e82e94632f061675b4d12",
     "pipeline/lib/phase-schema.mjs": "8fc0c909f129341295cd8ef2ea9e93cecd0ac493c3a8d83e25879f7ff522f1ab",
@@ -223,12 +223,13 @@
     "pipeline/lib/repo-profile.mjs": "4da219c9f72f3d74cfe42d9ff8685d4f53a8426c347cef85f0c2a737ac275133",
     "pipeline/lib/require-jq.sh": "a137b4df202515c2b89d5b93c3e28b04c73c8bc2f7c42be9ca9a22926e042918",
     "pipeline/lib/review-watch.sh": "89a53f79aab902a39ab8301cabe6eb54c8dc854af4d97c024c6b3b1f3ab38a75",
-    "pipeline/lib/route-state.sh": "8d7555a79be96d824b533382214431436bb95f6d3d21c4f811800f4ab4963f86",
+    "pipeline/lib/route-state.sh": "be023c5d77dbbb46834475af3c772094cbfd73b9b2203c3ce7430b353a632c8a",
     "pipeline/lib/run-paths.sh": "2063a1d2f07d6caa391089c1e581fd870a4e9c3caa3b0c25a03f0b4fe4f6d070",
     "pipeline/lib/shadow-git.sh": "8a36d3942153c27c34762369f7c2716aadca489851e630d4a2a3f324af1e0b93",
     "pipeline/lib/stack-detect.sh": "53242b46482547f861625b9cbf44b65790849bce7e42be3bbd56abac67bc3489",
     "pipeline/lib/submodule-detector.sh": "e2c1a762876c5ae4756818e91f0f0fdd5897cac60decb979651124086e9cab97",
-    "pipeline/lib/unattended-profile-check.mjs": "80a9005a43ed66d7fded8335e73a22c24483854ea532a6d503480512386d0c6d",
+    "pipeline/lib/toolkit-llm.sh": "81b89279f42e2795472d4f1ea5fb89baa8bc9d330d4eedaf56f2c6ea0e5a98f7",
+    "pipeline/lib/unattended-profile-check.mjs": "942d5dba815e90a5b6b961b330c6b2f58e012cf9441e593767d7236bdb594d09",
     "pipeline/lib/unattended-settings-location.mjs": "8db0d143ae79a4c81318994f5201cb805547938208f75dad70357eeb1e2d8745",
     "pipeline/lib/unattended.mjs": "391231047478c60765a9ce05ed7134bad14f6caf79a91930c24276eb15dcd8bf",
     "pipeline/lib/unattended.sh": "6160d784bb36b9eaa71fcd097d5b34c093534ced02442bdf16778d66a794dac2",
@@ -246,7 +247,7 @@
     "pipeline/multi-agent-refs/_repo-picker.md": "c325e86d00fa5e26893eeafcfae8c809f62e34e2ec643b4b364ac4c6f9caca45",
     "pipeline/multi-agent-refs/analysis-template-corporate.md": "ffccd6ba4b8db4e1492c5b569dbd14f1953dd8da6a3aa5825e7563506b820779",
     "pipeline/multi-agent-refs/analysis-template.md": "7062312f153aa9219a1ced9f0b60ac3583b4a2034d9d205cf7144ac9bf70ef17",
-    "pipeline/multi-agent-refs/analysis/evidence.md": "1385d8c794018feec254831b2e325d11ba4fa697a7a987890047e735b34cce26",
+    "pipeline/multi-agent-refs/analysis/evidence.md": "cac132b0d11b7ebd754fa154678fe7d127ab0faf08decc5829086b8d3e538e4d",
     "pipeline/multi-agent-refs/analysis/intake.md": "f5fb9e16620acb63fa41d14165d04f0fa6f5f7e178250a6f2b5b6d921d176f53",
     "pipeline/multi-agent-refs/analysis/locked.md": "68c010154e57191075778dbaf81200e1085181acacefef160c76023e665bbe09",
     "pipeline/multi-agent-refs/analysis/redesign.md": "6314fc1e14e05166efbea4819d5b07adb838d0704bde61b4b69cef637f251d58",
@@ -271,7 +272,7 @@
     "pipeline/multi-agent-refs/component-dispatch.md": "2ab9094aa716397e4840cd48f736c3f4fc3e7c4f9ccc5c7c7c52f9e8b0a28fb5",
     "pipeline/multi-agent-refs/component-generation.md": "04fdb3fd0f1c129e1df8243184a3225cebd9c4f63511d6015eb356a92eda8891",
     "pipeline/multi-agent-refs/conventions-defaults.md": "608a05ec6332fc19ee12c0418fbf25165f80e6c06cfee9efed7f27fab185d97d",
-    "pipeline/multi-agent-refs/cross-cli-contract.md": "d7f6dc9e0d589077150c807ca2def54f78f5aa717d266941f70458e6480069b2",
+    "pipeline/multi-agent-refs/cross-cli-contract.md": "431d0a6e4f0021937af3cc8a7f994cc04f86136d37c473f12cf919e886e2852b",
     "pipeline/multi-agent-refs/design-check/build-launch.md": "0ac64d07ef7389e22f7443f79c70a0a4f8bb87dcff6dbc94c63e034febe194ea",
     "pipeline/multi-agent-refs/design-check/compare.md": "2a0a89542a8bfefcfeaf1068dd91edb6947392f911f23e8b4857e4ace8fd15d7",
     "pipeline/multi-agent-refs/design-check/drive-capture.md": "dee4cd6230a401bc9e9dc82fc08109803dd2630c872c5b77a43cf17db062b05f",
@@ -292,12 +293,13 @@
     "pipeline/multi-agent-refs/features/cost-analysis.md": "42f1b90b41ef454f29ccfd3f93c959920f0e74cbca65e140695e9a30d6d90b87",
     "pipeline/multi-agent-refs/features/design-conformance.md": "a88ca595827cafa0c87c2facfcf9190dac69485e0596e5c198c6fc1613880452",
     "pipeline/multi-agent-refs/features/dev-critic.md": "08e01edef04b5ac216f8f43332126966d33da7b95625e47a8a6cd8ac105b263f",
-    "pipeline/multi-agent-refs/features/doctor.md": "62ff75a085095b11818ffabb97bd76e62e58de6affd24f4eaf3d9f89f2fe1d66",
+    "pipeline/multi-agent-refs/features/doctor.md": "f5faeb062470e1e3b5777c1f9eb586b7b11cd923be149c0bdca12001aeae77a7",
     "pipeline/multi-agent-refs/features/exploratory-testing.md": "ac534fdb9e056b1a3782f9b9e38f0b8823f85e03cb85924513079179e318c45d",
     "pipeline/multi-agent-refs/features/external-context-injection.md": "be9a0e904efd52535fa18a254567c9d0c3fc2ed12fcbc7a116f7879048303df6",
+    "pipeline/multi-agent-refs/features/free-models.md": "64afaba7e7a77575f4ed6a10905a01330a83f573907fb1a5d5356ae6c80999a0",
     "pipeline/multi-agent-refs/features/jira-context.md": "7d14802ed9ad1747e1a06dec26f22ff9e8959e03c47d7a018af45b8274aea47c",
     "pipeline/multi-agent-refs/features/maturity-followup.md": "e663e5bcf0b3b4d4d2a67f4516dbb9fb12520dfbdedb47a9c5f57c13a9a0633e",
-    "pipeline/multi-agent-refs/features/model-fallback.md": "e6b9635124f3557013dfbfa71d414a9d9abe9ddc89f2228a5496086c8e3b0c72",
+    "pipeline/multi-agent-refs/features/model-fallback.md": "ba1eff2c9abc2b1fddbcac3c77bcdd6f5c2887ae5da4dfb862427256c107742a",
     "pipeline/multi-agent-refs/features/package-manager.md": "b9e52f798f5dcba43abff1fe5cad8d5d5374058c9a6847c993975c665acab05a",
     "pipeline/multi-agent-refs/features/phone-api.md": "817eeaffd3772b0a80811b0cd17dee3498f08f6eccf8fd7e56deb0bc24c1c434",
     "pipeline/multi-agent-refs/features/plan-critic.md": "d218c8599d893211480a412d46efdbba4aa48e3b18e8bb0ebfd66782f3b8ebc5",
@@ -318,7 +320,7 @@
     "pipeline/multi-agent-refs/features/stack-adapters.md": "71e23385da872ceed35263f4838f154800aa2da55bb6688ccca74726b70a3ef5",
     "pipeline/multi-agent-refs/features/stack-skill-routing.md": "1989f7f64be6c5ee0a42d8e9962aead7cd7472d795915ab953d89d9382f317e6",
     "pipeline/multi-agent-refs/features/unattended-gates.md": "46b516cac81a4eacf5d58bc3b1613e2266c26f1559be8dac060d1dc6b7d7ca01",
-    "pipeline/multi-agent-refs/features/unattended-security.md": "24235b0479342e4a9f0edb88d387619dd5f222ea82769b99acbc703392769005",
+    "pipeline/multi-agent-refs/features/unattended-security.md": "f0f05ed17bbf26a50fa0f88d890f7ac3ccb8f78f169b9f759e997299fdeb5cac",
     "pipeline/multi-agent-refs/features/url-enrichment.md": "72e01a799d9fa54b56c762ba404a9f9236adbbf98320e395a96f6b0f5917e76b",
     "pipeline/multi-agent-refs/features/usage-reporting.md": "bd8643e804a70d86679e431368e2fff7a8fbe7b121837340e745b1dd221a428d",
     "pipeline/multi-agent-refs/features/valven.md": "13b1fb8a3815330f6f970181506ac117e0d1c42761e5a83454edbd0b383ee1a7",
@@ -365,6 +367,7 @@
     "pipeline/multi-agent-refs/setup/discovery.md": "ebf6365102b336beba9904f0d01a6fadc0e734b2988919860ea9313908116a19",
     "pipeline/multi-agent-refs/setup/figma.md": "95405e7303c34c9f640fdea7e4aa84388ad57dd31ed5d0d19b0b1cb4f1a3572d",
     "pipeline/multi-agent-refs/setup/firebase.md": "a82031c67993762303a7ecd222e2574fbbf8d65dcc6b17e051a8dd53a9e31474",
+    "pipeline/multi-agent-refs/setup/free-models.md": "57b374a9732a98eea443103ac8de53ec614050c9bfb055aba1f02c32ade34b4a",
     "pipeline/multi-agent-refs/setup/google-play.md": "c60117fb8b13c709da93d379064aa0d56869bfde88fc5d5737996b7c1fc02ff7",
     "pipeline/multi-agent-refs/setup/identity-routing.md": "299870880a1d4f27986d09ce912288472d35cc333382301536ea25bc13289c70",
     "pipeline/multi-agent-refs/setup/repo-discovery.md": "06944e7b7677d998b6d169fbf5bebcac08c0f5eab808f9f1f3e5b6b2dc6a1f55",
@@ -384,7 +387,7 @@
     "pipeline/multi-agent-refs/web-guide.md": "714cba0d92fa45bf71fbff21bb2f09c88534ebf785b3a2ea96d18037e2e7f7f9",
     "pipeline/multi-agent-refs/website-deploy.md": "ce819c8b1ef8e8ec3257611379aaf0ab4678e08e0b58bd88c936e98cb8ead609",
     "pipeline/multi-agent-refs/wiki-capture.md": "bfd33cf097b966e61f80c9235d98c8139e4c9ede2e47c14b920a5b910cdc76d8",
-    "pipeline/preferences-template.json": "8c74c0fa9f182a6c474aa7d4d2cfe6d67635ec0917c847f19ddae3095e6af944",
+    "pipeline/preferences-template.json": "f7e57c9fd4d776168a192d270f7ef68a71d0351df311b15d389dcffa4a98ca47",
     "pipeline/rules/app-store-guidelines.md": "cdfa4f8a2e0e642460bb72517f9f430638d6f09eb4a37898747cb8d55df03405",
     "pipeline/rules/code-review.md": "b18eec5cec31710fe76cdae6f03b53e7403d4f0406274691ab38a4771505a1c5",
     "pipeline/rules/code-style.md": "cd7d8fa872d1d640d143a573a0bdeeb7a9095f62a4d69741a11b4f0cee9d5a48",
@@ -452,7 +455,7 @@
     "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": "d603707539234845e4390cb33e4bfe9a116d7c6485dfcd3207caf786db36ccdc",
+    "pipeline/schemas/prefs.schema.json": "6beee7dbb67168528cb3d677cf4215c34c48fd97b5354017ef6f23de8662c482",
     "pipeline/schemas/repo-profile.schema.json": "1a74ef8330da9a26a5a70955f6f9cbb20eda54a8615efaf86c7993d420a7f04e",
     "pipeline/schemas/repos.schema.json": "a9bf56f25c66201c170912e3389bd73e4a3f61922410f83e31a6c6ba47aee861",
     "pipeline/schemas/research-output.schema.json": "54e3ba1b04fdc20fbaa84333b943a8ab95d1395c7b0e0aedc67929184cb49523",
@@ -460,14 +463,14 @@
     "pipeline/schemas/review-file-exclusions.json": "2e8c44b45d21d2c82fc95aa2bf76ad3fbf2d5c68180c7b2ebf89c4a926688d77",
     "pipeline/schemas/review-file-exclusions.schema.json": "d7310b4328ae14673f0971c9f823a697d3cafe054062a680ef0f020be1867ea3",
     "pipeline/schemas/reviewer-output.schema.json": "57512ef7ebeee39575937bfff266651685568ee17b326bbb8e1d9113296b4e46",
-    "pipeline/schemas/route-config.schema.json": "6f606926c257b7ad3d2972e53d0b772714774140c473b9cb8c7cd9e52731020f",
+    "pipeline/schemas/route-config.schema.json": "cb6bd03a38956ad2fa1a7245d633918756f2b3d9be10abf0bdd929cd2328517f",
     "pipeline/schemas/run-log.schema.json": "3ac10faf0aafb05a8ae89e027b7923aee604cb4bf8daebdbbf4da8c31bc97a1d",
     "pipeline/schemas/run-questions.json": "7928448ac408b8e90df2e24070c7d433691fe861315adb80ea754c7d21db7688",
     "pipeline/schemas/run-questions.schema.json": "d4b5b4c3e297164182dac7e86ba05e350f41085a7f024c6c7adefb0be42c4a8e",
     "pipeline/schemas/runs-index.schema.json": "ad7d598f39a599031f89339a955fc939624fc127a635c70f5cc4667b9395124f",
     "pipeline/schemas/scaffold-manifest.schema.json": "4ee8dfacf646a96c62438234bedab9d286d80d1a6d3d4984361d91a7411ce171",
     "pipeline/schemas/scope-check.schema.json": "f96973c59372b36b7d68b9ac4b03490e7da8d54acf29a35947f5f610e82b98ea",
-    "pipeline/schemas/secret-patterns.json": "d9a7bec7b2ba704b73f2302c3498874c6298cde69bde0f181932c282d3fe0b0e",
+    "pipeline/schemas/secret-patterns.json": "4ae313b7f2529252b71be8b1cbee9bfd954cad6a9d0f30248a2593d1212a4c08",
     "pipeline/schemas/secret-patterns.schema.json": "faf32274ca4999217bb725d7b16f455143f1775fa72768a02ba87783fbec3d27",
     "pipeline/schemas/security-finding.schema.json": "623d965edf2de8ab0f2a49c33fa5be507d479d5bc3067ccd72cdf90a480b498a",
     "pipeline/schemas/skill-observation.schema.json": "05f16c6e5055ef99a102b12b578ba841251267d41dd7343f8ab66cd8070180ff",
@@ -527,7 +530,7 @@
     "pipeline/scripts/build-references.mjs": "724fe25d9d1bd9d2a0f53abd7c0e13e9bced22126cb5562d0d285f63ff5eeecb",
     "pipeline/scripts/build-skills-index.mjs": "35b7ae8299db6a554064096ea34b476cb231b5f15bbf0dd86dd3b128399e9390",
     "pipeline/scripts/build-stack-plugins.mjs": "bd7b7f9a3983d4daaf5e4468abc79c0f195877a02a390dcccfb529d79e8c39c7",
-    "pipeline/scripts/bulk-read.sh": "f5f55e229b00b849a84e6b6015e3bba1f0cb59dba5fb011857d1ceaafe7ad614",
+    "pipeline/scripts/bulk-read.sh": "eb13ef378768e98a7624dc14c83e0cdc83ac01476567bcca16e390368f5706d0",
     "pipeline/scripts/capture-evidence.sh": "2f7657786e07c17c302b76d4ea6bafe391b65be3dd891901b78019af3a7e38e1",
     "pipeline/scripts/capture-flush.sh": "291da92a3a708bf2e8e0884d1d6e0a676da83650ee723f7a499a6549e6cd2adc",
     "pipeline/scripts/capture-resume.sh": "4934ff7961e2b8eabcd154ca06dd53c1d4aab03986a39dff287b8c16f5cea7ee",
@@ -547,12 +550,12 @@
     "pipeline/scripts/cost-analyze.mjs": "ba6f402bd7b08359b8eb502b6502d3c86a70dcf50b4a8f5829bd771cade5cd43",
     "pipeline/scripts/cost-budget-check.mjs": "0edc96feccc3fe07f36eefe3b52b611e43ef94178fd257f0f4537a024e2754cd",
     "pipeline/scripts/cost-lib.sh": "64eeb1d4515b802cc9136ef520f93b7a81aa9cc1c1065e81fe522fccf7fd2cb5",
-    "pipeline/scripts/cost-table.json": "cc9f762cf9d1e7ddf1f233c9346bacf2e3b72475b6567d7ef4217a69efdd24f9",
+    "pipeline/scripts/cost-table.json": "934fcf2682f5998587f6d5337219be1c836aa68bd51fc5fda95e4306465ddfe8",
     "pipeline/scripts/council-view.mjs": "f904aa3a71fe31f7b02a00c603186e251f66a652950d285e934b591571db56cc",
     "pipeline/scripts/crush-json.mjs": "303382670f8f170c8c6710202853a2de2915625813cd157185f9be4e2b27258e",
     "pipeline/scripts/diff-explain.mjs": "194d0635639607cb1af3de064453162e01c0d59dc0c2e187d21d45bae3bc559c",
     "pipeline/scripts/diff-risk-score.mjs": "b3e8da42fea1258162e40f4eb7809074831339b7563874527f7e825f7aa795ca",
-    "pipeline/scripts/doctor.mjs": "a86a39b3eab13158166f44133c1fdc1fda3d4cc7ad0122f3dc47e3cfae2f5ad1",
+    "pipeline/scripts/doctor.mjs": "4905cedb5a71e9890f6b9994d6097d840fccc4afcff2b4fbdc69aefb8017a2cb",
     "pipeline/scripts/estimate.mjs": "9847e412dd74ac19a5c3b84bed343f79d25f256022b2df98e3eb1296db45ed3a",
     "pipeline/scripts/evidence-gate.mjs": "347a8d3fa1d17d996de345585c216bd7071f4c1d687999daf6e48881720ea5df",
     "pipeline/scripts/explore-findings.mjs": "997cca3ef42a170ff51ee2c382263eff8653affd6bb675877b94b8bba782e717",
@@ -610,7 +613,7 @@
     "pipeline/scripts/plugin-refresh.sh": "687a33199ad963616ab537e32210ec8c967e76ecc42f494ee8a1dc9fe947fc30",
     "pipeline/scripts/pr-request.mjs": "e6f4ded2366c6599bb345b3011ecc771e13b8a1561afa4c9a50bca4edff17456",
     "pipeline/scripts/pr-timeline.mjs": "6a12df12a72f3440796569d3264edb0b3e105be6e4f2e26e958a5a0da340d05c",
-    "pipeline/scripts/pre-commit-check.sh": "08f72728c6ca5266aac1c91f12af1dccf898ae315549511611657e7b034efc96",
+    "pipeline/scripts/pre-commit-check.sh": "46081c47891c46e4aa96d7df58222d06d95087bce98bb2f543fb15a63322a52a",
     "pipeline/scripts/pre-push-check.sh": "4a1554a625df4745a829c0df294db7ce450fbe44fe624e562008e9912be78925",
     "pipeline/scripts/probe-evidence-capability.sh": "ac74252eed6b773fdbc7ec475a63606925f1ba7b5e7c6f911329f46fd920eae7",
     "pipeline/scripts/probe-store-key.mjs": "b46dfcf444c95d0bb61de36823314945dacaaacb8f35841d153dcfcde8e4df1a",
@@ -662,7 +665,7 @@
     "pipeline/scripts/token-budget-report.mjs": "508bbc659df478c535c0ecdd3f8611372af8fef0b0932c7b19a247af2b2b9265",
     "pipeline/scripts/triage-memory.mjs": "2d8541145f1749593ae5728fb4c9eb3001484edb5e4d37be473aeec34d1dbe7c",
     "pipeline/scripts/ui-tree-dumper.swift": "a09e42ef069eafa08c05afd8333e05b754ef6a7d8b9687712039b0f2c9801273",
-    "pipeline/scripts/unattended_policy.py": "e2ac82b4a969fdd230e3c3f390cb31cde1e2178c4caa57574ad63a3d786f8379",
+    "pipeline/scripts/unattended_policy.py": "851f3982bf8a5d12415caf724146184c50801f9ee2e3654ba2ded593351f71af",
     "pipeline/scripts/uninstall.mjs": "ba11803733cf3bfcc966f0d4aa2cc5fbed000cb37a251005f067ce0289306233",
     "pipeline/scripts/update-check.sh": "9c00647e7ca4249414b2e5af08f61705ab5bd2106b6f66ae8ebce8aa143dc957",
     "pipeline/scripts/update-issue-progress.sh": "ccfef87743e91272e009e396ac07461d2784b2fa84a06c802a582526eeeb9ed9",
@@ -691,7 +694,7 @@
     "pipeline/scripts/worktrees.mjs": "90dfd09b70fffe9b56c331a4ae2692cc248f4898f4ee6aee4239ef0b20888a90",
     "pipeline/scripts/write-state.mjs": "e1198bf970eace07d3eff22b394808a526e473df65d3d58aa2d5a12cfdac8b49",
     "pipeline/scripts/write-store-config.mjs": "b994a061f6febb2ca3d396074d8b51d2c1c1f991d3072d321703380da3639a56",
-    "pipeline/skills/.skill-manifest.json": "93cf5b7a3d7011a6be1e1c7601892039775051ff34ad80dc172ea4c44c82fc20",
+    "pipeline/skills/.skill-manifest.json": "7bc20de35075819d6c43d5bf84376ccfe2b0db1dd06a9efe1d307780ebef01ba",
     "pipeline/skills/.skills-index.json": "b2917fa44e273b939549f1c3ab3dd81c26ba8168772bc7644c9fa076116d8a4c",
     "pipeline/skills/shared/README.md": "928fe4292be729c3b7d7d0898cade8be0dfa868f208e0c6d1fe7b2c6bd6223c5",
     "pipeline/skills/shared/core/apple-archive-compliance/SKILL.md": "7239fef717ea45b79276bfcc2c3903acd57950b6e00dd6a2a66399c4b09cbd51",
@@ -738,8 +741,8 @@
     "pipeline/skills/shared/core/multi-agent-review-jira/SKILL.md": "a17a1f11fcf6c75640452e53ddddaaf906ff9e3ebfeda73e333f44db02515352",
     "pipeline/skills/shared/core/multi-agent-review/SKILL.md": "2b6934d6086a467bdf145b326061ab4b83d5479bfb1a2fb36420ff8012a02e5d",
     "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",
+    "pipeline/skills/shared/core/multi-agent-route-on/SKILL.md": "97c76d711454e6bc9edfd47344bbeab7f73cf72c116cca92cffacdcda7fe96b1",
+    "pipeline/skills/shared/core/multi-agent-route-status/SKILL.md": "869689dbf84edece67168a892a61b51459ff6c15cbf7dafe40c2b774f875b9f0",
     "pipeline/skills/shared/core/multi-agent-routines/SKILL.md": "564f06a2754e8ad2ddab9996133680c1a91bf7ecba5bd860ee5afcdde12ca0a5",
     "pipeline/skills/shared/core/multi-agent-save/SKILL.md": "6da2cb991c3a15e538f2d618383a23389183756be402a995d58f813667a2f986",
     "pipeline/skills/shared/core/multi-agent-scaffold/SKILL.md": "892415937ed2094d470f297f742e35e2684ad58ef262028873d8535210065dc0",
@@ -748,7 +751,7 @@
     "pipeline/skills/shared/core/multi-agent-search/SKILL.md": "5f5177cd28cbb13583441fb98402cfa251c78e69de693540584e9a1dcc7692cb",
     "pipeline/skills/shared/core/multi-agent-security-review/SKILL.md": "3c483d5942f2c2b81c0537d4db0b36804c13cabd66fd7fae2972d07a8f239f69",
     "pipeline/skills/shared/core/multi-agent-serve/SKILL.md": "90e4dd7225e10e670118ed05d0c8a9e346112c4bbbdb24a7fe7c5c334a83e848",
-    "pipeline/skills/shared/core/multi-agent-setup/SKILL.md": "427df811e5130da1ab6e23ff78202eb9134fb76bcd601924fba5668cbd630158",
+    "pipeline/skills/shared/core/multi-agent-setup/SKILL.md": "e3523960d5d178125302e5ceeb865902d7b12ea5d615670cddeb4d542fa48035",
     "pipeline/skills/shared/core/multi-agent-stack/SKILL.md": "ac964cd00dd6ed06512530489d867efbc51d7d7614265f9aa022679325d5defe",
     "pipeline/skills/shared/core/multi-agent-status/SKILL.md": "444c3773b52e6786e40bc67c8833ea6aecadbcd4459b01127b4aff152157040a",
     "pipeline/skills/shared/core/multi-agent-steer/SKILL.md": "20f332bd2fe2745da5341f8d8187211fc47c06b4b5f5031e217affee0282ddb5",
@@ -762,7 +765,7 @@
     "pipeline/skills/shared/core/multi-agent-testflight-validation/SKILL.md": "6bfd1569117bfbacb485d831c0b7f262ebb3a2f9471f6177a646f5ce32c06a25",
     "pipeline/skills/shared/core/multi-agent-uninstall/SKILL.md": "9dccf78ffc2fb014d83f67d683d395f56f4fad8b5a36b9aa84e6cbd075b58818",
     "pipeline/skills/shared/core/multi-agent-update/SKILL.md": "013317432263490a01d081b657928b977012afb78f75a64d278d94d2daa8e894",
-    "pipeline/skills/shared/core/multi-agent/SKILL.md": "3dd44ccc00e41c09e59ad223900a391f80158bd3f69e45d67c684285bc42418d",
+    "pipeline/skills/shared/core/multi-agent/SKILL.md": "a39f712426638e7955db9171c950be720f11c861621884e628c81a0b6a49de5d",
     "pipeline/skills/shared/external/NOTICE-avdlee-swiftui-agent-skill.md": "400842e4653f038fad22509fe3f3d152151120758f5f9b170e6dba59afaf4a48",
     "pipeline/skills/shared/external/NOTICE-dimillian-skills.md": "f9c3d783fd3563418c18291b90899251e890fd3fa8ee353c8c1fbbe61078526e",
     "pipeline/skills/shared/external/NOTICE-paul-hudson-skills.md": "bca5fe8779df70fb0f234483d65ff3562c67521e719b69b22aac260803b75244",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "20.20.0",
+  "version": "20.21.0",
   "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/SKILL.md

@@ -157,7 +157,7 @@ This command uses lazy loading for token efficiency. Read the relevant sub-file
 - `$HOME/.claude/agents/backend-architect.md`  -  Backend/API architecture review (`preferredModel: fable`)
 - `$HOME/.claude/agents/security-auditor.md`  -  Security audit (`preferredModel: opus`)
 
-**Per-persona model routing:** Before each Agent dispatch, the orchestrator reads `preferredModel` from the persona file and exports `CLAUDE_CODE_SUBAGENT_MODEL` (Claude Code) / passes `--model` (Copilot CLI). Precedence: per-dispatch `PHASE_MODEL_OVERRIDE` > a matching `prefs.global.modelRouting` rule (v19.0.0+, consulted only when the phase named no model, and only inside the Anthropic ladder because subagent dispatch belongs to the host) > persona `preferredModel` > `fable` (falls back per `$HOME/.claude/multi-agent-refs/features/model-fallback.md`). Full contract: `skills/shared/core/multi-agent/SKILL.md#agent-dispatch--per-persona-model-routing-v610`.
+**Per-persona model routing:** Before each Agent dispatch, the orchestrator reads `preferredModel` from the persona file and exports `CLAUDE_CODE_SUBAGENT_MODEL` (Claude Code) / passes `--model` (Copilot CLI). Precedence: per-dispatch `PHASE_MODEL_OVERRIDE` > a matching `prefs.global.modelRouting` rule (v19.0.0+, consulted only when the phase named no model, and only inside the Anthropic ladder because subagent dispatch belongs to the host) > persona `preferredModel` > `fable` (falls back per `$HOME/.claude/multi-agent-refs/features/model-fallback.md`). Full contract: `skills/shared/core/multi-agent/SKILL.md#agent-dispatch--per-persona-model-routing-v610`. Simple text tasks (summaries, extraction, labels, drafts) ask `model-dispatch.sh delegate --default host` first and use `llm_delegate` on `free`: `$HOME/.claude/multi-agent-refs/features/free-models.md`.
 
 ---
 

package/pipeline/commands/multi-agent/route-on/SKILL.md

@@ -1,8 +1,8 @@
 ---
 description: "Enable policy-driven model routing: pick a strategy, a scope, and the rules that say which rung a call lands on. Use when asked to turn model routing on."
 description-tr: "Politika güdümlü model yönlendirmesini açar: strateji, kapsam ve hangi çağrının hangi basamağa düşeceğini söyleyen kuralları sorar."
-argument-hint: "[--strategy=manual|task-fit|cost-ceiling] [--scope=subagent,bulk-read,research]"
-parameters: [{"name":"--strategy","kind":"enum","enum":["manual","task-fit","cost-ceiling"]},{"name":"--scope","kind":"enum","repeat":true,"enum":["subagent","bulk-read","research"]}]
+argument-hint: "[--free [--allow-training] | --no-free] [--strategy=manual|task-fit|cost-ceiling] [--scope=subagent,bulk-read,delegate,research]"
+parameters: [{"name":"--free","kind":"flag"},{"name":"--allow-training","kind":"flag"},{"name":"--no-free","kind":"flag"},{"name":"--strategy","kind":"enum","enum":["manual","task-fit","cost-ceiling"]},{"name":"--scope","kind":"enum","repeat":true,"enum":["subagent","bulk-read","delegate","research"]}]
 gui: form
 destructive: false
 confirm: none
@@ -25,7 +25,8 @@ Routing ships **off**. This is the command that turns it on, and it writes to
 ```
 
 Ordered, first match wins. `when` matches on `persona`, `phase` (0..5) or
-`taskKind`; `prefer` lists rungs in descending preference.
+`taskKind`; `prefer` lists rungs in descending preference. `free` is a rung too,
+honoured only at `bulk-read` and `delegate` and only while `--free` is on.
 
 **Rung names are the contract; model ids are not.** `opus` is a rung here and a
 model id in `cost-table.json`, and the second can change without anyone editing
@@ -38,18 +39,41 @@ Set rules with:
 bash "$HOME/.claude/lib/route-state.sh" set-rules path/to/rules.json
 ```
 
+## Free models: `--free`
+
+```bash
+bash "$HOME/.claude/lib/route-state.sh" on --free
+```
+
+Layer 2. Simple text work the pipeline does itself - a large-file read, a log or
+document summary, field extraction, a label, a translation or commit-body draft -
+goes to the multi-agent-toolkit's verified free-model chain first. Every answer
+is checked against its source before it is used; when none passes, Claude does
+the task as before. Decisions, plans, code, reviews and triage never leave Claude.
+
+`--free` turns on `modelRouting.free`, adds `bulk-read` and `delegate` to the
+scope, and lists which providers are usable. With none, it says exactly which key
+to add: one free Groq key is enough. `--allow-training` also admits free tiers
+that may train on prompts; leave it off for corporate code and tickets.
+`--no-free` turns only the free chain off. Full contract, the task list for
+development and analysis, and unattended behaviour:
+`$HOME/.claude/multi-agent-refs/features/free-models.md`.
+
 ## Strategies
 
 | Strategy | What it does |
 |---|---|
 | `manual` | only the explicit rules apply, nothing is inferred. The default, because a router that guesses is a router nobody can predict |
-| `task-fit` | a rule may match on `taskKind`, and the cheapest rung clearing it is chosen |
-| `cost-ceiling` | rungs downgrade as the run approaches `budgetCeilingUsd` |
+| `task-fit` | the matched rule's rungs are tried cheapest first (cost-table prices, `free` first) |
+| `cost-ceiling` | the rule's order holds until the run reaches the warn threshold of `budgetCeilingUsd`, then the cheapest rung is tried first |
+
+`set-rules` checks every rule against the schema and the cost table and writes
+nothing if one fails: an unknown rung, a phase outside 0-5, an unknown key.
 
 ## Scope, and the value that is not in it
 
 `scope` names the call sites routing may act on: `subagent`, `bulk-read`,
-`research`. Every one of them is a call **this pipeline makes itself**.
+`delegate`, `research`. Every one of them is a call **this pipeline makes itself**.
 
 There is no `host-session` value, and that absence is enforced by that schema
 rather than written as advice. Routing a host session means rewriting the CLI's
@@ -62,8 +86,8 @@ Passing `--scope=host-session` is refused with that reason, not ignored.
 
 On Claude Code a subagent cannot be dispatched to a non-Anthropic model: subagent
 dispatch belongs to the host, not to us. So Phase 1, 2 and 3 personas stay inside
-the Anthropic ladder no matter what the rules say, and external providers apply
-only at `bulk-read` and `research`, where the pipeline makes the HTTP call.
+the Anthropic ladder no matter what the rules say, and the `free` rung applies
+only at `bulk-read` and `delegate`, where the pipeline makes the call itself.
 
 This is printed by `route-status` on every invocation instead of living in a doc,
 because the question it answers - "routing is on, why is the reviewer still on

package/pipeline/commands/multi-agent/route-status/SKILL.md

@@ -28,13 +28,23 @@ A disabled router with rules is deliberately not reported as "off" alone: that
 reads as "unconfigured" and sends the user through `route-on`'s questions a
 second time.
 
+## Free models and what they saved
+
+With `route-on --free`, status also prints `free: true` with its data policy,
+where the free chain answers first (`bulk-read`, `delegate`), and the last seven
+days from the toolkit's usage log: tasks answered free and verified, answers
+served from cache, tasks handed back to Claude, and the input and output tokens
+kept off Claude with an estimated saving at haiku rates. The estimate is labelled
+as one: it prices the tokens at the rung the task would otherwise have used.
+
 ## The limit, printed every time
 
 On Claude Code a subagent cannot be sent to a non-Anthropic model. Subagent
 dispatch belongs to the host; the pipeline asks for a persona and the host
 decides what answers. So Phase 1, 2 and 3 personas stay inside the Anthropic
-ladder whatever the rules say, and an external provider is only reachable where
-the pipeline makes the HTTP call itself - `bulk-read.sh` and `research_ask`.
+ladder whatever the rules say, and a free model answers only where the pipeline
+makes the call itself - `bulk-read.sh` and the `delegate` call site - and only
+after the toolkit verified its answer against the source.
 
 This paragraph is output, not documentation, because the alternative is the
 question arriving later as "routing is on but the reviewer is still on Opus, is

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

@@ -209,6 +209,7 @@ The Step 2 discovery summary is never the end of setup. Immediately after showin
 10. `jenkins`
 11. App Store Connect block (Step 3b; only when the target repo is iOS)
 12. Google Play block (Step 3d; only when the target repo is Android)
+13. Free-model keys `llm-<id>` (only after `route-on --free`): `$HOME/.claude/multi-agent-refs/setup/free-models.md`
 
 Loop rules:
 
@@ -377,7 +378,7 @@ Standard key names are a convention for NEW tokens; discovery may find existing
 
 ### Inline Token Save Pattern
 
-All tokens go through `~/.claude/lib/credential-store.sh`, which auto-delegates to the deterministic Python helper (`~/.claude/scripts/keychain.py`). The Python path writes both `-l` (label) and `-s` (service) attributes so existing manually-added entries with either convention remain findable.
+All tokens go through `~/.claude/lib/credential-store.sh` (Python helper and label/service attributes: see "Setup" above).
 
 ```bash
 # PAT / API Key / JSON contents (from clipboard)

package/pipeline/lib/model-dispatch.sh

@@ -9,11 +9,11 @@
 #   model-dispatch.sh <call-site> [--persona P] [--phase N] [--task-kind K]
 #                                 [--default RUNG] [--task-id ID]
 #
-# <call-site> is one of the `scope` members: subagent | bulk-read | research.
-# stdout is a single rung NAME. Rung names are the contract; the model id behind
-# one lives in cost-table.json and moves without a config edit.
+# <call-site> is one of the `scope` members: subagent | bulk-read | delegate |
+# research. stdout is a single rung NAME. Rung names are the contract; the model
+# id behind one lives in cost-table.json and moves without a config edit.
 #
-# Exit is always 0 and stdout is always a usable rung. A router that can fail
+# Exit is always 0 and stdout is always a usable answer. A router that can fail
 # turns every call site into a place the run can die, for a feature that ships
 # disabled; when anything is missing, unparseable or out of scope, the caller's
 # default comes back unchanged.
@@ -22,16 +22,18 @@
 #
 #   Layer 1  an Anthropic rung. Reachable from every call site, because it
 #            writes to a seam that already exists and opens no new network path.
-#   Layer 2  a non-Anthropic rung. NO call site can dispatch to one today, and
-#            the router refuses it rather than returning a rung its caller will
-#            hand to a CLI that does not know the name:
-#              - a subagent is dispatched by the HOST;
-#              - bulk-read shells out to `claude -p --model <rung>`;
-#              - research_ask runs in the MCP server and picks its own model.
-#            `provider` in cost-table.json is what makes this checkable, and it
-#            is the seam a future call site would use. Until one exists, the
-#            refusal is the honest answer: an allowed rung nothing can honour is
-#            a rule the user believes worked.
+#   Layer 2  the `free` rung: the multi-agent-toolkit's verified free-model
+#            chain. Reachable only where the pipeline makes the call itself -
+#            bulk-read and delegate - and only with modelRouting.free.enabled.
+#            Its caller must keep its default as the fallback, because the chain
+#            answers ESCALATE_TO_CLAUDE whenever no free answer survives
+#            verification. A subagent is dispatched by the HOST, so `free` and
+#            every other non-Anthropic rung is refused there and the rule's next
+#            rung answers instead.
+#
+# Strategies: manual keeps the rule's order; task-fit tries the cheapest rung
+# first; cost-ceiling keeps the order until cost-budget-check.mjs reports the run
+# at its warn threshold of budgetCeilingUsd, then tries the cheapest first.
 
 set -uo pipefail
 
@@ -74,7 +76,7 @@ fi
 [ "$DEFAULT_RUNG" = "fable" ] && [ "$FABLE_ON" != "true" ] && DEFAULT_RUNG="opus"
 
 case "$CALL_SITE" in
-  subagent|bulk-read|research) ;;
+  subagent|bulk-read|delegate|research) ;;
   *) emit "$DEFAULT_RUNG" ;;
 esac
 
@@ -103,11 +105,45 @@ MATCH=$(jq -r \
          and ((.when.taskKind // null) as $k | $k == null or $k == $kind)
        )
    ] | first | (.prefer // []) | join(" ")' "$PREFS" 2>/dev/null) || emit "$DEFAULT_RUNG"
-[ -n "$MATCH" ] && [ "$MATCH" != "null" ] || emit "$DEFAULT_RUNG"
+[ "$MATCH" = "null" ] && MATCH=""
+
+FREE_ON=$(jq -r '.global.modelRouting.free.enabled // false' "$PREFS" 2>/dev/null)
+CANDIDATES="$MATCH"
+case "$CALL_SITE" in
+  bulk-read|delegate) [ "$FREE_ON" = "true" ] && CANDIDATES="free $MATCH" ;;
+esac
+[ -n "${CANDIDATES// /}" ] || emit "$DEFAULT_RUNG"
 
 HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 COST_TABLE="$HERE/../scripts/cost-table.json"
 
+STRATEGY=$(jq -r '.global.modelRouting.strategy // "manual"' "$PREFS" 2>/dev/null)
+CHEAPEST_FIRST=false
+STRATEGY_NOTE=""
+case "$STRATEGY" in
+  task-fit) CHEAPEST_FIRST=true; STRATEGY_NOTE="task-fit" ;;
+  cost-ceiling)
+    CEILING=$(jq -r '.global.modelRouting.budgetCeilingUsd // empty' "$PREFS" 2>/dev/null)
+    if [ -n "$CEILING" ] && [ "$TASK_ID" != "unknown" ] && command -v node >/dev/null 2>&1 \
+       && [ -f "$HERE/../scripts/cost-budget-check.mjs" ]; then
+      node "$HERE/../scripts/cost-budget-check.mjs" --task-id "$TASK_ID" --max-usd "$CEILING" --enabled >/dev/null 2>&1
+      case $? in
+        10|11) CHEAPEST_FIRST=true; STRATEGY_NOTE="cost-ceiling reached" ;;
+      esac
+    fi
+    ;;
+esac
+
+if [ "$CHEAPEST_FIRST" = "true" ] && [ -f "$COST_TABLE" ]; then
+  CANDIDATES=$(
+    jq -r --arg c "$CANDIDATES" '
+      .prices as $p
+    | ($c | split(" ") | map(select(length > 0)))
+    | to_entries
+    | sort_by([($p[.value].inPerMtok // 1e9), .key])
+    | map(.value) | join(" ")' "$COST_TABLE" 2>/dev/null || printf '%s' "$CANDIDATES")
+fi
+
 # The fable rung answers only when the fable switch is on (FABLE_ON, read
 # above). Routing is a policy over what is available; it is not a second way to
 # turn a rung on, or `/multi-agent:model off` would stop meaning anything the
@@ -116,13 +152,13 @@ COST_TABLE="$HERE/../scripts/cost-table.json"
 record() {
   [ -x "$HERE/../scripts/log-metric.sh" ] || return 0
   local rec
-  rec=$(jq -r '.global.modelRouting.recordDecisions // true' "$PREFS" 2>/dev/null)
+  rec=$(jq -r 'if .global.modelRouting.recordDecisions == false then "false" else "true" end' "$PREFS" 2>/dev/null)
   [ "$rec" = "false" ] && return 0
   "$HERE/../scripts/log-metric.sh" "$TASK_ID" "${PHASE:-0}" model_routing.decision \
     call_site="$CALL_SITE" rung="$1" reason="$2" >/dev/null 2>&1 || true
 }
 
-for rung in $MATCH; do
+for rung in $CANDIDATES; do
   if [ ! -f "$COST_TABLE" ]; then
     record "$rung" "no cost table; rung taken on trust"
     emit "$rung"
@@ -139,15 +175,27 @@ for rung in $MATCH; do
     echo "model-dispatch: rule prefers 'fable' but modelFallback.fableEnabled is false; skipping it" >&2
     continue
   fi
+  if [ "$PROVIDER" = "free-chain" ]; then
+    if [ "$FREE_ON" != "true" ]; then
+      echo "model-dispatch: rule prefers 'free' but modelRouting.free.enabled is false (route-on --free); skipping it" >&2
+      continue
+    fi
+    case "$CALL_SITE" in
+      bulk-read|delegate)
+        record "$rung" "free chain${STRATEGY_NOTE:+, $STRATEGY_NOTE}"
+        emit "$rung" ;;
+    esac
+    echo "model-dispatch: rung 'free' is reachable only at bulk-read and delegate; a $CALL_SITE is dispatched by the host, skipping it" >&2
+    continue
+  fi
   if [ "$PROVIDER" != "anthropic" ]; then
-    # The honest limit, said out loud at the moment it bites. Every call site
-    # that asks here hands the rung to something that only speaks the Anthropic
-    # ladder, so returning an external rung would produce a failed call rather
-    # than a cheaper one.
-    echo "model-dispatch: rung '$rung' is $PROVIDER and no call site can dispatch to one yet; skipping it" >&2
+    # Every call site that asks here hands any other rung to something that
+    # speaks the Anthropic ladder or the free chain, so returning an external
+    # rung would produce a failed call rather than a cheaper one.
+    echo "model-dispatch: rung '$rung' is $PROVIDER and no call site dispatches to it; skipping it" >&2
     continue
   fi
-  record "$rung" "rule matched"
+  record "$rung" "rule matched${STRATEGY_NOTE:+, $STRATEGY_NOTE}"
   emit "$rung"
 done
 

package/pipeline/lib/outbound-gate.mjs

@@ -82,6 +82,8 @@ export const RULES = [
   { name: "stripe-key", certain: true, re: /\b[sr]k_live_[A-Za-z0-9]{20,}\b/g },
   { name: "perplexity-key", certain: true, re: /\bpplx-[A-Za-z0-9]{32,}\b/g },
   { name: "huggingface-token", certain: true, re: /\bhf_[A-Za-z0-9]{30,}\b/g },
+  { name: "groq-key", certain: true, re: /\bgsk_[A-Za-z0-9]{40,}\b/g },
+  { name: "openrouter-key", certain: true, re: /\bsk-or-v1-[A-Za-z0-9]{40,}\b/g },
   {
     name: "service-account-json",
     certain: true,