create-agdf 0.13.2 → 0.13.4

package/generated/plugins/agdf/skills/release-or/SKILL.md

@@ -20,6 +20,7 @@ It reports:
 - solution integrity
 - documentation impact
 - Context Graph impact
+- evaluated Parent reconciliation and programme aggregation from Delivery Map
 - open risks, blockers, retained fallbacks, and exit criteria
 - next permissible step
 - whether further quality follow-up or a separate delivery closeout is useful
@@ -53,6 +54,12 @@ Use the Runtime Contract definition of `Relevant Run` to decide whether OR is ma
 14. Reconcile Context Graph impact before clean closeout: report `context_graph_reconciliation: resolved | not_applicable | open_gap`.
 15. If Context Graph work remains unresolved, report it as an explicit open gap and do not describe the run as cleanly handoff-ready.
 16. After writing or updating `MASTER_BACKLOG.md`, run `doctor --json` (or the locally available equivalent) and resolve any `AGDF_BACKLOG_STATUS_UNKNOWN` or `AGDF_BACKLOG_ARTEFACT_LABEL_UNKNOWN` finding before closeout. See the AGDF control scaffold's `MASTER_BACKLOG.md` template Rules section for the canonical status/artefact label vocabulary.
+17. When Delivery Map exposes `parent_reconciliation`, report that evaluated object without
+    rediscovering or reclassifying the relationship. Keep Child completion and Parent coordination
+    visibly separate. An `open` result retains exactly one next action and does not invalidate Child
+    QA, UAT or OR completion.
+18. Report `programme_aggregation` only when applicable. Preserve `startable` and `final_ready` as
+    non-authorizing evidence values; never treat either as a gate or approval.
 
 ## When To Use
 - at the end of every relevant run
@@ -99,10 +106,12 @@ If information is missing, state the gap instead of guessing.
 7. Summarize tests and verification.
 8. Summarize documentation and Context Graph impact if relevant.
 9. Record Context Graph reconciliation as `resolved`, `not_applicable`, or `open_gap`.
-10. Name retained fallbacks and exit criteria.
-11. Set exactly one next permissible step.
-12. Set exactly one quality outlook.
-13. State whether `delivery-closeout` is the next operational handoff step when code changes exist and the delivery state allows it.
+10. Copy applicable evaluated Parent reconciliation and programme aggregation from Delivery Map into
+    the OR without mutating another run.
+11. Name retained fallbacks and exit criteria.
+12. Set exactly one next permissible step.
+13. Set exactly one quality outlook.
+14. State whether `delivery-closeout` is the next operational handoff step when code changes exist and the delivery state allows it.
 
 ## Output
 Use a compact structure:
@@ -135,3 +144,4 @@ This skill must not:
 - provide later-gate content while an earlier gate blocks
 - produce the operative commit/PR handoff owned by `delivery-closeout`
 - execute commit, push, or PR actions
+- infer Parentage, scan sibling runs independently or mutate a Parent

package/generated/plugins/agdf/submission/openai/availability.md

@@ -1,6 +1,6 @@
 # Availability Decision Record
 
-- release: `0.13.2`
+- release: `0.13.4`
 - decision_state: `pending`
 - decision_owner: verified publisher
 - countries: not selected

package/generated/plugins/agdf/submission/openai/capability-matrix.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "releaseVersion": "0.13.2",
+  "releaseVersion": "0.13.4",
   "evidenceStates": [
     "common",
     "codex-specific",
@@ -34,7 +34,7 @@
     {
       "id": "chatgpt-portable-skills",
       "state": "advisory",
-      "description": "Fit assessment, explanation, planning and review may use the portable skills core; repository enforcement requires direct host evidence.",
+      "description": "Fit assessment, explanation, planning and review use skills whose checked bundle satisfies AGDF's reviewed core-format profile and resolves declared shared resources within the plugin; standalone installation and host behavior remain unverified.",
       "evidenceClass": "unverified",
       "evidenceRef": "PPD-L03"
     },

package/generated/plugins/agdf/submission/openai/release-notes.md

@@ -1,4 +1,4 @@
-# AGDF 0.13.2 — Initial OpenAI Public Plugin Candidate
+# AGDF 0.13.4 — Initial OpenAI Public Plugin Candidate
 
 This candidate packages the canonical AGDF workflow skills for public discovery in ChatGPT and
 Codex. It helps users assess delivery fit, preserve explicit human approvals, inspect existing-system

package/generated/plugins/agdf/submission/openai/reviewer-cases.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "releaseVersion": "0.13.2",
+  "releaseVersion": "0.13.4",
   "cases": [
     {
       "id": "positive-proportional-fit",

package/generated/submissions/openai/agdf/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agdf",
-  "version": "0.13.2",
+  "version": "0.13.4",
   "description": "Control layer for governed AI-assisted delivery.",
   "author": {
     "name": "Arndt Gold",

package/generated/submissions/openai/agdf/meta/agdf-interaction-locales.json

@@ -45,8 +45,7 @@
         "value": "Value",
         "classification": "Classification",
         "mode": {
-          "quick_task": "Quick Task",
-          "verified_change": "Verified Change"
+          "quick_task": "Quick Task"
         },
         "boundary": {
           "inside": "Trivial change boundary satisfied",
@@ -296,8 +295,7 @@
         "value": "Wert",
         "classification": "Klassifizierung",
         "mode": {
-          "quick_task": "Quick Task",
-          "verified_change": "Verified Change"
+          "quick_task": "Quick Task"
         },
         "boundary": {
           "inside": "Trivial-Change-Boundary erfüllt",

package/generated/submissions/openai/agdf/meta/agdf-plugin.definition.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
   "id": "agdf",
-  "version": "0.13.2",
+  "version": "0.13.4",
   "displayName": "AI Governance & Delivery Framework",
   "developerName": "Arndt Gold",
   "description": "Control layer for governed AI-assisted delivery.",

package/generated/submissions/openai/agdf/meta/agent-skills-conformance.json

@@ -0,0 +1,86 @@
+{
+  "schemaVersion": 1,
+  "policyVersion": "2026-08-19",
+  "baseline": {
+    "id": "agent-skills-core-format",
+    "specificationUrl": "https://agentskills.io/specification",
+    "reviewedAt": "2026-08-19"
+  },
+  "classifications": [
+    "standard_strict",
+    "upstream_advisory",
+    "agdf_policy"
+  ],
+  "frontmatterProfile": {
+    "requiredFields": [
+      "name",
+      "description"
+    ],
+    "allowedFields": [
+      "name",
+      "description"
+    ],
+    "scalarStyles": [
+      "plain",
+      "single_quoted",
+      "double_quoted"
+    ]
+  },
+  "strictRules": {
+    "nameMaxCodePoints": 64,
+    "descriptionMaxCodePoints": 1024,
+    "namePattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
+    "nameMustMatchParent": true
+  },
+  "advisoryRules": {
+    "skillMdMaxLines": 500
+  },
+  "agdfRules": {
+    "descriptionStartsWith": "Use this skill",
+    "requiresRuntimeContractResource": true
+  },
+  "surfaces": {
+    "source": {
+      "skillsRoot": "skills",
+      "sharedResourceRoots": [
+        "meta/contracts"
+      ],
+      "skillPrefixOwner": "codex",
+      "ignoredSkillEntries": []
+    },
+    "plugin": {
+      "skillsRoot": "skills",
+      "sharedResourceRoots": [
+        "meta/contracts"
+      ],
+      "skillPrefixOwner": "codex",
+      "ignoredSkillEntries": []
+    },
+    "copilot": {
+      "skillsRoot": ".",
+      "sharedResourceRoots": [
+        "contracts"
+      ],
+      "skillPrefixOwner": "copilot",
+      "ignoredSkillEntries": [
+        "contracts"
+      ]
+    },
+    "opencode": {
+      "skillsRoot": "skills",
+      "sharedResourceRoots": [
+        "contracts"
+      ],
+      "skillPrefixOwner": "opencode",
+      "ignoredSkillEntries": []
+    },
+    "public_candidate": {
+      "skillsRoot": "skills",
+      "sharedResourceRoots": [
+        "meta/contracts"
+      ],
+      "skillPrefixOwner": "codex",
+      "ignoredSkillEntries": []
+    }
+  }
+}

package/generated/submissions/openai/agdf/meta/contracts/closeout.md

@@ -21,6 +21,55 @@ selected-run ceremony even when it is otherwise a relevant run. If a selected ca
 section or any other existing line.
 
 
+## Parent Reconciliation Handoff
+
+Parent reconciliation is an optional closeout coordination projection. It never grants, revokes or
+blocks Child gates, QA, UAT, OR completion or an otherwise valid delivery handoff.
+
+It activates only when the Child `Artefact Chain` contains exactly one evidenced row with:
+
+- `From`: `OR`
+- `Relationship`: `reconciles_with`
+- `To`: `parent_run:<run_id>` using the canonical run-id grammar
+
+Names, directories, branches, backlog proximity, chat history and evidence prose do not establish
+Parentage. Delivery Map is the single deterministic evaluator. It compares the Child row with one
+evidenced reciprocal Parent row `Aggregate | includes | child_run:<run_id>` and returns exactly one
+outcome:
+
+- `resolved`: the named Parent has exactly one evidenced reciprocal Child relationship;
+- `not_applicable`: the Child declares no qualifying Parent relationship; or
+- `open`: the explicit relationship is invalid, ambiguous, unavailable, stale or lacks reciprocal
+  evidence.
+
+An open outcome contains concrete evidence or missing evidence and exactly one next action. Optional
+Child handling input is limited to `action_required | accepted_open`. `accepted_open` keeps the
+outcome open and visible while allowing independently valid Child delivery to continue; it never
+asserts Parent reconciliation. Evaluation is read-only and must never mutate a Parent.
+
+`release-or` reports the evaluated result in the Child OR. `delivery-closeout` consumes that OR
+projection only; it must not search sibling runs, infer a relationship, reevaluate evidence or repair
+a Parent. Unresolved explicit reconciliation is warning-level coordination evidence, not a Child
+gate failure. Legacy runs without the optional relationship remain unchanged and add no routine
+visible ceremony.
+
+
+## Programme Aggregation Readiness
+
+An explicit Parent/programme run may project two independent evidence values:
+
+- `startable: true` requires at least one evidenced `Aggregate | includes | child_run:<run_id>` row
+  whose Child has a completed OR;
+- `final_ready: true` additionally requires one valid declared acceptance artefact beneath
+  `.agdf/control/artefacts/`, concrete aggregation evidence and
+  `programme_aggregation_missing_evidence: none`.
+
+`final_ready: true` always implies `startable: true`. Failed prerequisites stay false with explicit
+missing evidence and one next action; they are never silently promoted. These values are evidence
+projections only. They do not approve QA/UAT, create a gate or define the programme-specific
+acceptance criteria, which remain owned by the referenced programme artefact.
+
+
 ## Do Not Duplicate
 
 The explanatory framework lives in `docs/`.

package/generated/submissions/openai/agdf/meta/contracts/control-scaffold.md

@@ -108,6 +108,8 @@ It must expose:
 - multi-scope ambiguity and branch/workspace evidence limits when present
 - memory persistence target, reason and references when present
 - Context Graph impact and gate effect
+- optional evaluated Parent reconciliation and programme aggregation readiness from the Closeout
+  Contract, without changing Child gate authority
 - the Run Status Card as a compact projection of current gate, next step and quality outlook
 - findings that explain why the delivery picture is `pass | warn | revise | block`
 

package/generated/submissions/openai/agdf/meta/contracts/interaction.md

@@ -7,7 +7,7 @@ It must not introduce a second gate model or override `gate-check`, `delivery-ma
 
 - `mode`: `quick_task | verified_change | structured_delivery | unknown`
 - `run_id`: the exactly selected canonical run
-- `presentation_language`: the resolved complete locale-pack tag; absent, unsupported or incomplete packs resolve to the registry's deterministic `en` fallback
+- `presentation_language`: the resolved complete locale-pack tag; absent or unsupported requested locale tags resolve to the registry's deterministic `en` fallback, while an incomplete or invalid registry fails closed
 - `status`: `open | blocked | pass | warn | revise | block | in_progress`
 - `current_gate`: current user gate or internal step
 - `mode_slice_decision`: `undecided | quick_task | verified_change | structured_slice | structured_delivery | block`
@@ -206,8 +206,8 @@ Use this compact composition:
 
 Resolve all AGDF-owned explanatory text through the canonical Interaction
 Locale Registry. `en` and `de` are initial reviewed packs, not a closed locale
-list. English is the deterministic fallback for absent, unsupported or
-incomplete packs. Gate identifiers, `run_id`, canonical paths and exact
+list. English is the deterministic fallback for absent or unsupported requested locale tags; an
+incomplete or invalid registry fails closed. Gate identifiers, `run_id`, canonical paths and exact
 approval values are never translated. The visible gate title is localized;
 for example, the German title may be `Lösungsdesign` while the authorization
 value remains `Approval: SD`. Meaning, ordering and authority boundaries are
@@ -362,20 +362,30 @@ skill-local target-orientation template.
 
 ### Scope Classification Card
 
-When `gate-check` classifies a fresh scope as ungated (Quick Task or Trivial Change Boundary),
+When `gate-check` classifies a fresh scope as an ungated `quick_task` with a resolved Trivial
+Change Boundary result,
 the agent consumes the canonical `scope_classification.markdown` verbatim from
 `renderScopeClassificationCard` in `create-agdf/lib/interaction-presentation.js`. The card is a
 compact, localized, non-authorizing projection of the classification: mode, boundary result,
 UR-trigger evaluation, one currently-allowed line, one remains-forbidden line, escalation triggers
 and the challenge path. It carries `authorizes: false` and never renders approval controls.
 
-The card renders exactly once per fresh-scope ungated classification, before work proceeds. It must
-not appear for gated scopes, internal steps of a selected run, or as a substitute for the two-card
-approval envelope. Read-only requests keep the single read-only orientation sentence above; the
-scope classification card and the read-only orientation are mutually exclusive for the same request.
-
-If the classification input is missing, unknown, contradictory or the locale section is incomplete,
-the renderer returns `null` and the agent fails closed to the existing ceremony — never
+The card renders exactly once per valid fresh-scope Quick Task classification, before work proceeds.
+It must not appear for Verified Change, Structured Delivery, gated, ambiguous, unknown or selected-
+run states, internal steps of a selected run, or as a substitute for the two-card approval envelope.
+Read-only requests keep the single read-only orientation sentence above; the scope classification
+card and the read-only orientation are mutually exclusive for the same request.
+
+Every dynamic scalar and escalation-trigger item is a non-empty, single-line plain-text string of at
+most 240 Unicode code points. Markdown control tokens and line-leading heading, blockquote, list or
+ordered-list syntax are invalid. The escalation list contains 1–3 valid, distinct normalized items.
+The renderer rejects the complete input on any violation; it never coerces, truncates, sanitizes or
+partially retains invalid values.
+
+An unsupported requested locale resolves through the complete deterministic English fallback pack.
+A present incomplete or otherwise invalid registry is an invalid presentation source, not an
+unsupported locale: the renderer returns `null`. Missing, unknown or contradictory classification
+input likewise returns `null`, and the agent fails closed to the existing ceremony — never
 model-reconstructed Markdown. The card introduces no gate, no approval value, no persistence and no
 second presentation owner. `gate-check` must not maintain a skill-local card template.
 
@@ -390,7 +400,8 @@ fallback and human CLI output use the configured project chat language from
 
 - resolve an exact complete pack, then its language subtag, then deterministic English fallback;
 - `en` and `de` are the initial complete packs; additional reviewed complete packs are supported without changing runtime logic;
-- an incomplete pack is unsupported and must fail to English as a unit;
+- an unsupported requested locale must fail to English as a complete unit; an incomplete or invalid
+  registry is not an unsupported locale and must fail closed without presentation;
 - one interaction must not mix presentation languages, including labels and descriptions;
 - durable artefacts, runtime rules, task identifiers and machine-facing approval values remain English;
 - the exact approval value remains `Approval: <GateName>` in every locale;

package/generated/submissions/openai/agdf/skills/delivery-closeout/SKILL.md

@@ -57,6 +57,7 @@ Use what is available:
 - rollout or migration notes
 - open technical risks or documentation gaps
 - Context Graph impact from OR/QA/review
+- Parent reconciliation projection already reported by OR
 
 If code-change status is unclear, do not claim a commit handoff.
 
@@ -87,6 +88,11 @@ If code-change status is unclear, do not claim a commit handoff.
    - monitoring/runtime verification
    - Context Graph reconciliation
 7. If `Approval: UAT` exists, code changes were delivered, and no Context Graph gap remains, actively offer the commit but do not run it.
+8. If OR reports an `open` Parent reconciliation, retain its named Parent and one next action in the
+   handoff while preserving an otherwise valid commit offer. This coordination warning is not a
+   Child gate failure.
+9. Consume Parent reconciliation from the OR only. Do not inspect sibling runs, infer Parentage,
+   reevaluate evidence or mutate a Parent.
 
 ## Output
 For code-changing runs:
@@ -116,3 +122,4 @@ This skill must not:
 - execute commit, push, or PR
 - invent a commit handoff for non-code runs
 - imply new gate approvals
+- rediscover, reclassify or repair Parent reconciliation outside the OR

package/generated/submissions/openai/agdf/skills/release-or/SKILL.md

@@ -20,6 +20,7 @@ It reports:
 - solution integrity
 - documentation impact
 - Context Graph impact
+- evaluated Parent reconciliation and programme aggregation from Delivery Map
 - open risks, blockers, retained fallbacks, and exit criteria
 - next permissible step
 - whether further quality follow-up or a separate delivery closeout is useful
@@ -53,6 +54,12 @@ Use the Runtime Contract definition of `Relevant Run` to decide whether OR is ma
 14. Reconcile Context Graph impact before clean closeout: report `context_graph_reconciliation: resolved | not_applicable | open_gap`.
 15. If Context Graph work remains unresolved, report it as an explicit open gap and do not describe the run as cleanly handoff-ready.
 16. After writing or updating `MASTER_BACKLOG.md`, run `doctor --json` (or the locally available equivalent) and resolve any `AGDF_BACKLOG_STATUS_UNKNOWN` or `AGDF_BACKLOG_ARTEFACT_LABEL_UNKNOWN` finding before closeout. See the AGDF control scaffold's `MASTER_BACKLOG.md` template Rules section for the canonical status/artefact label vocabulary.
+17. When Delivery Map exposes `parent_reconciliation`, report that evaluated object without
+    rediscovering or reclassifying the relationship. Keep Child completion and Parent coordination
+    visibly separate. An `open` result retains exactly one next action and does not invalidate Child
+    QA, UAT or OR completion.
+18. Report `programme_aggregation` only when applicable. Preserve `startable` and `final_ready` as
+    non-authorizing evidence values; never treat either as a gate or approval.
 
 ## When To Use
 - at the end of every relevant run
@@ -99,10 +106,12 @@ If information is missing, state the gap instead of guessing.
 7. Summarize tests and verification.
 8. Summarize documentation and Context Graph impact if relevant.
 9. Record Context Graph reconciliation as `resolved`, `not_applicable`, or `open_gap`.
-10. Name retained fallbacks and exit criteria.
-11. Set exactly one next permissible step.
-12. Set exactly one quality outlook.
-13. State whether `delivery-closeout` is the next operational handoff step when code changes exist and the delivery state allows it.
+10. Copy applicable evaluated Parent reconciliation and programme aggregation from Delivery Map into
+    the OR without mutating another run.
+11. Name retained fallbacks and exit criteria.
+12. Set exactly one next permissible step.
+13. Set exactly one quality outlook.
+14. State whether `delivery-closeout` is the next operational handoff step when code changes exist and the delivery state allows it.
 
 ## Output
 Use a compact structure:
@@ -135,3 +144,4 @@ This skill must not:
 - provide later-gate content while an earlier gate blocks
 - produce the operative commit/PR handoff owned by `delivery-closeout`
 - execute commit, push, or PR actions
+- infer Parentage, scan sibling runs independently or mutate a Parent

package/generated/submissions/openai/agdf/submission/openai/availability.md

@@ -1,6 +1,6 @@
 # Availability Decision Record
 
-- release: `0.13.2`
+- release: `0.13.4`
 - decision_state: `pending`
 - decision_owner: verified publisher
 - countries: not selected

package/generated/submissions/openai/agdf/submission/openai/capability-matrix.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "releaseVersion": "0.13.2",
+  "releaseVersion": "0.13.4",
   "evidenceStates": [
     "common",
     "codex-specific",
@@ -34,7 +34,7 @@
     {
       "id": "chatgpt-portable-skills",
       "state": "advisory",
-      "description": "Fit assessment, explanation, planning and review may use the portable skills core; repository enforcement requires direct host evidence.",
+      "description": "Fit assessment, explanation, planning and review use skills whose checked bundle satisfies AGDF's reviewed core-format profile and resolves declared shared resources within the plugin; standalone installation and host behavior remain unverified.",
       "evidenceClass": "unverified",
       "evidenceRef": "PPD-L03"
     },

package/generated/submissions/openai/agdf/submission/openai/inventory.json

@@ -1,11 +1,11 @@
 {
   "schemaVersion": 1,
-  "releaseVersion": "0.13.2",
-  "digest": "39e413c04f3a9ed00a929059c811517122595db1ca996160014ab28e40d4343b",
+  "releaseVersion": "0.13.4",
+  "digest": "0c035d175a08c123e2fcfee394c2ce740836c2cfb9031f1f993d9a910cb21c4c",
   "files": [
     {
       "path": ".codex-plugin/plugin.json",
-      "sha256": "7c312e36df469557f1a8b4c9ce3c58cdcfa15e9f4203d2daea7fa2cc03eefe9f"
+      "sha256": "bd6a373939140ffd65cda9da1889fd28ca8890229bd550f25e1074c3838ea342"
     },
     {
       "path": "assets/agdf-icon.svg",
@@ -25,11 +25,11 @@
     },
     {
       "path": "meta/agdf-interaction-locales.json",
-      "sha256": "ff155ca9e87cf852ddae579dbb63878ece65e38e9d27f4ca3b69daec6ecbae9e"
+      "sha256": "c2be4146bbf3972861697128ecb880369867360ea8a0efe61bee9ca9eae63266"
     },
     {
       "path": "meta/agdf-plugin.definition.json",
-      "sha256": "825d2e15df0a4cff0c3821f1f03c97dbf6310a3a58ff75e93becce5e68c43b3d"
+      "sha256": "2807ca0b148f2ec04e237e0ea7c30eda7c9093f58e5e92f23fe46a725101c7b8"
     },
     {
       "path": "meta/agdf-runtime-contract.md",
@@ -39,9 +39,13 @@
       "path": "meta/agdf-tenets.md",
       "sha256": "1166f11d08f46f7770ae69e79d99340ed1ead35cc5d79e80855b40420979c311"
     },
+    {
+      "path": "meta/agent-skills-conformance.json",
+      "sha256": "9d0c69fa87c267d258ce6ead8940449623718cbe59ee14b4ba4a45ff251f2b0a"
+    },
     {
       "path": "meta/contracts/closeout.md",
-      "sha256": "aef6bd3951c97f4e7dc37287a784abecdf7539fe3b93feabf6e0b45acc97aa7c"
+      "sha256": "e5b1ac18efe7309d46cc974d1938e3e66f532af96bc1fc01d6e0eb865feea473"
     },
     {
       "path": "meta/contracts/context-graph.md",
@@ -49,7 +53,7 @@
     },
     {
       "path": "meta/contracts/control-scaffold.md",
-      "sha256": "ffcbd1ff2aa67e196e46c37f57bf0f35760266c683dfcba8c3157ae041217a9d"
+      "sha256": "bf5773ec22013d3332cf4900d59880ebdfbaab7dee227c66b1721d0fd05aeac2"
     },
     {
       "path": "meta/contracts/gate-transition.md",
@@ -57,7 +61,7 @@
     },
     {
       "path": "meta/contracts/interaction.md",
-      "sha256": "5da4c305181da484883f1df47c3225b167414f77d9043a6c592b082cb531b5c1"
+      "sha256": "799ff1d27f16004844775f2802a94d6d336d9130b08a6484c5f325d7ea6b0df8"
     },
     {
       "path": "meta/contracts/modes.md",
@@ -97,7 +101,7 @@
     },
     {
       "path": "skills/delivery-closeout/SKILL.md",
-      "sha256": "5dc5fb82a229ab9259446cca35bfe6723d08ca17084d35436f10bb40a368506d"
+      "sha256": "00c836b400ad5a3df5021e33904f125b2c46328585ee2b48291d8439543224bf"
     },
     {
       "path": "skills/delivery-closeout/help.md",
@@ -129,7 +133,7 @@
     },
     {
       "path": "skills/release-or/SKILL.md",
-      "sha256": "5abc9124ce31b3e04b28a27c9a779b97d3e75e234f54bee80e18510babe0ae7d"
+      "sha256": "28a35c3b6ca1d392bb2bb9e404bb0f5c7783c755c133333252b8cf21b767e742"
     },
     {
       "path": "skills/release-or/help.md",
@@ -153,23 +157,23 @@
     },
     {
       "path": "submission/openai/availability.md",
-      "sha256": "e4c8f423e8f34f451bea859b22bbe957f763edf193ee64e5b70a9493dab70d22"
+      "sha256": "3dc16160e0e46dca41281374a1b581fe52447d6b9e30eaf1cbbb4aaeffe2bd17"
     },
     {
       "path": "submission/openai/capability-matrix.json",
-      "sha256": "139a02d1da98ff87e190a611d2aaf65d14bdf186afa65eb3687100d401473704"
+      "sha256": "4345d732af70f5ae5874f6d3f665d2e862b9f87877bf548e77dc67026fe775f2"
     },
     {
       "path": "submission/openai/listing.json",
-      "sha256": "bc8f674e2ca9134da8e283943123613fee4a40cc5f45ba9caa6e26d459255daf"
+      "sha256": "d50e6baed2d101f9d56f9748b2d9b97451ff4a2d71a1ca12ca4b46271f69f045"
     },
     {
       "path": "submission/openai/release-notes.md",
-      "sha256": "8dde4b6ba3fa6b8a5075e749a5b5cdad0ca86e07130e03df395a0698e3187ec3"
+      "sha256": "e89c1319affc34c06fa27b6ac87c0f8dd86c63258fb2e8db14d7f4c8a4e5de2b"
     },
     {
       "path": "submission/openai/reviewer-cases.json",
-      "sha256": "ffd89e71028ca29031fd283c8a7980006f4d16026eb2c6d09e401b788caf83ed"
+      "sha256": "c3ea5365465b9c1022e2c54ed1c3611657afda85ba1f0627743c64075d30c773"
     }
   ]
 }

package/generated/submissions/openai/agdf/submission/openai/listing.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "releaseVersion": "0.13.2",
+  "releaseVersion": "0.13.4",
   "submissionType": "skills",
   "identity": {
     "technicalId": "agdf",

package/generated/submissions/openai/agdf/submission/openai/readiness.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "releaseVersion": "0.13.2",
+  "releaseVersion": "0.13.4",
   "candidateState": "repository_ready",
   "submissionReady": false,
   "submissionBlockers": [
@@ -16,7 +16,7 @@
     },
     "bundle": {
       "state": "pass",
-      "detail": "42 inventoried files; inventory digest 39e413c04f3a9ed00a929059c811517122595db1ca996160014ab28e40d4343b"
+      "detail": "43 inventoried files; inventory digest 0c035d175a08c123e2fcfee394c2ce740836c2cfb9031f1f993d9a910cb21c4c"
     },
     "installed_host": {
       "state": "unverified",

package/generated/submissions/openai/agdf/submission/openai/readiness.md

@@ -1,6 +1,6 @@
 # AGDF Public Plugin Readiness
 
-- release: `0.13.2`
+- release: `0.13.4`
 - candidate_state: `repository_ready`
 - submission_ready: `false`
 
@@ -9,7 +9,7 @@
 | Class | State | Detail |
 |---|---|---|
 | repository | pass | canonical contract and deterministic source checks |
-| bundle | pass | 42 inventoried files; inventory digest 39e413c04f3a9ed00a929059c811517122595db1ca996160014ab28e40d4343b |
+| bundle | pass | 43 inventoried files; inventory digest 0c035d175a08c123e2fcfee394c2ce740836c2cfb9031f1f993d9a910cb21c4c |
 | installed_host | unverified | PPD-L02 and PPD-L03 not performed |
 | portal | unverified | unverified |
 | post_publication | unverified | not published |

package/generated/submissions/openai/agdf/submission/openai/release-notes.md

@@ -1,4 +1,4 @@
-# AGDF 0.13.2 — Initial OpenAI Public Plugin Candidate
+# AGDF 0.13.4 — Initial OpenAI Public Plugin Candidate
 
 This candidate packages the canonical AGDF workflow skills for public discovery in ChatGPT and
 Codex. It helps users assess delivery fit, preserve explicit human approvals, inspect existing-system

package/generated/submissions/openai/agdf/submission/openai/reviewer-cases.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "releaseVersion": "0.13.2",
+  "releaseVersion": "0.13.4",
   "cases": [
     {
       "id": "positive-proportional-fit",