@receiz/ai-skills 122.0.0 → 124.0.0

package/README.md

@@ -1,8 +1,14 @@
 # Receiz AI Skills
 
-The `122.0.0` package is a registry-bound operating-contract distribution beneath Receiz proof authority. AI instructions, MCP confirmations, JSON objects, database rows, staging references, and receipts never become proof or runtime authority.
+The `124.0.0` package is a registry-bound operating-contract distribution beneath Receiz proof authority. AI instructions, MCP confirmations, OAuth/OIDC grants, JSON objects, database rows, staging references, and receipts never become proof or runtime authority.
 
-## V122 artifact authority chain
+## V124 — Reality Becomes Infrastructure
+
+**The Production Runtime for Verified Civilization.** V124 teaches every application to compose the canonical Kai clock, proof-authority challenges, server-custodied short-lived sessions, durable staged execution, exact recovery, verified replay/checkpoints, access-filtered private additions, atomic multi-domain mutations, privacy-safe recipient resolution, and evidence-based runtime qualification.
+
+The edge verifies and retains the sealed proof object. Exact authenticated subject, domain, namespace, access-key, and revocation heads bind every remote projection. Server and database state provide subordinate coordination, compare-and-swap, indexing, sync, and recovery. A response is rejected unless authenticated and bound to its request; method presence never means a production dependency is operational.
+
+## Established artifact authority chain
 
 V120 carries two established proof-object laws unchanged:
 `receiz.native_capture.v1` binds exact bytes from Receiz's dedicated camera
@@ -20,7 +26,7 @@ The single current MCP artifact inventory contains nine tools: `receiz_artifact_
 
 The same package carries 37 inherited living-subject MCP tools: subject resolve/state/history/memory/relationships/inventory; subject Twin profile/message/mind export/import planning; mandate get/plan/activate/pause/revoke; world additions/command plan/validate/execute/transaction plan/execute/receipt/replay; subject runtime enqueue/status/cancel; living-subject conformance; proof-brain head/search/resolve/stream; and bearer preview/issue/inspect/claim/cancel/status. Each generated skill map binds those exact names to SDK primitives, strict input/output types, source primitive, registry/reducer digests, zero-write failure, and the non-authority boundary.
 
-V122 adds 19 MCP operations for durable remote proof-object admission and authenticated subject state; edge-held proof bundles and append-only public access-key bindings; locally encrypted private/invited world commands; exact validation, execution, outcome recovery, and filtered additions; first-class mandate issue/state/revoke; atomic multi-world planning/execution; and explicit Phi Settlement/Reserve planning. The object remains authority. Remote storage coordinates append-only sync and recovery beneath edge-held proof. Private keys and private plaintext remain at the edge. Phi is the value unit, deterministic canonical price provides live USD display, and value moves on exactly two rails: Settlement and Reserve.
+The inherited v122 protocol adds 19 MCP operations for durable remote proof-object admission and authenticated subject state; edge-held proof bundles and append-only public access-key bindings; locally encrypted private/invited world commands; exact validation, execution, outcome recovery, and filtered additions; first-class mandate issue/state/revoke; atomic multi-world planning/execution; and explicit Phi Settlement/Reserve planning. Its stable v122 protocol identifiers remain intentionally unchanged in v123.
 
 `client.admission.browserStore` is durable admission coordination only: it stores no proof object or sealed artifact bytes and never blocks known-artifact first paint. V120 production reconciliation preserves the provider-neutral `client.coordination` rail and never exposes Supabase mechanics. Receiz-generated files retain declared ownership, while `receiz.extensions.ts` is developer-owned and must never be overwritten.
 
@@ -29,13 +35,13 @@ Receiz applications. Fifteen focused constitutional skills supply architecture,
 domain, law, command, authority, replay, offline, causal, artifact, migration,
 performance, observability, testing, and release contracts. The earlier nine
 domain skill names remain packaged for compatibility. Seven operation skill names first introduced in obsolete-versioned now
-describe current v122 outcomes for identity profiles, portable continuity, bearer ownership, offline transport,
+describe current outcomes for identity profiles, portable continuity, bearer ownership, offline transport,
 proof media, cross-app state, and admission evidence. Their retired obsolete-versioned mechanisms are not active defaults.
-One dedicated `receiz-global-reconciliation` skill governs accepted-head resolution, verified offline reconciliation, structural divergence, first paint, indeterminate recovery, and effects. The `receiz-value-rails` skill governs the two lawful value rails and deterministic USD display. Every current manifest uses package version `122.0.0`, requires SDK/MCP `>=122.0.0 <123.0.0`, and binds ruleset `122.0.0` to registry digest `ed65956a16dd5f0d76d04db2f4a651fc43eb0a71cef64afd53576aa782dc9896` and operation-matrix digest `bd1d7ccf1543e2484df68e3025c7376f8ae37cafe1ca0d7c9cd9f52f6342b325` from SDK source.
+One dedicated `receiz-global-reconciliation` skill governs accepted-head resolution, verified offline reconciliation, structural divergence, first paint, indeterminate recovery, and effects. `receiz-value-execution` governs exact live Phi execution and retry recovery; `receiz-proof-authority` governs edge verification, explicit consent, and minimum-scope embedded authority. Every current manifest uses package version `124.0.0`, requires SDK/MCP `>=124.0.0 <125.0.0`, and binds ruleset `124.0.0` to registry digest `d02429151b0bcebdaeb89485792e377afc55130f9a25e07982c1c88221314247` and operation-matrix digest `540d1c1bf39f1b288b257c79a6e020bdcc5e587fc9b7dbf6b7aaa5d082e20ad5` from SDK source.
 
 This package teaches AI agents how to understand, verify, build with, and operate Receiz from the existing repository surfaces.
 
-It is published as `@receiz/ai-skills` and is an exact-version dependency of both `@receiz/sdk` and `@receiz/mcp-server`. Installing either package places all 40 skills under `node_modules/@receiz/ai-skills`: 34 manifests and 31 OpenAI agent prompts are included for explicit loading by an agent host.
+It is published as `@receiz/ai-skills` and is an exact-version dependency of both `@receiz/sdk` and `@receiz/mcp-server`. Installing either package places all 42 skills under `node_modules/@receiz/ai-skills`: 36 manifests and 33 OpenAI agent prompts are included for explicit loading by an agent host.
 
 Receiz is a proof-native artifact system. Sealed proof/object truth is strongest: a Receiz object is not a database row, but a proof-carrying artifact whose witnessed history is the truth boundary. The proof object carries continuity; SDK and MCP may verify, extract, append, or project beneath that carried truth. Receiz.com reference behavior comes before SDK, MCP, AI, and other developer rails. Server state, database state, UI state, marketplace state, and model memory are projections only. Old witnessed truth is not stale. If a projection is wrong, rebuild it from object history. If truth is missing, append new truth. Never mutate witnessed truth.
 
@@ -44,14 +50,14 @@ A verified proof object is not limited to the platform that created it. Any lawf
 ## SDK, MCP, And Skills
 
 - SDK: `@receiz/sdk` is the universal runtime; `@receiz/sdk/react` is React-only; `@receiz/sdk/compiler` is Node-only; `@receiz/sdk/testing` is browser-safe sandbox and conformance support.
-- MCP: `@receiz/mcp-server` is for agent tool access. Its current nine artifact tools, 37 inherited living-subject tools, and 19 v122 tools expose transition, reconciliation, proof-brain, Twin, mandate, runtime, world, memory, social, inventory, bearer, remote admission, edge-held access keys, private envelope, outcome recovery, multi-world, and Phi value-rail contracts through the same SDK authority types. Diagnostics, public reads, app-state/public-store actions, previews, and delegated writes remain beneath proof truth.
+- MCP: `@receiz/mcp-server` is for agent tool access. Its current nine artifact tools, 37 inherited living-subject tools, 19 stable v122 protocol tools, and eight v123 completion tools expose transition, reconciliation, proof-brain, Twin, mandate, runtime, world, memory, social, inventory, bearer, remote admission, canonical planning, embedded authority, exact-head namespaces, exact recovery, and live Phi execution through the same SDK authority types.
 - Skills: this package is operating doctrine. It tells an AI which Receiz primitive is active, which source of truth wins, which SDK or MCP rail to use, and what must never be assumed.
 
 Agents may acquire scoped delegated access through the official Receiz Connect/OIDC Authorization Code + PKCE flow or through the MCP delegated-agent setup path exposed by `receiz_mcp_login`. That acquired access is permission to call scoped SDK/MCP rails after user consent. It is not proof authority and must never outrank artifact truth.
 
 ## How Agents Should Use This Package
 
-Start with `receiz-build-production-system` when work spans multiple constitutional domains and `receiz-global-reconciliation` for named-domain coordination. Machine-readable manifests require the exact active canonical v122 registry and operation-matrix digests, command-only mutation, independent verification, MCP conformance, and a passing release lock. Use a focused operation skill for SDK/MCP implementation and a constitutional skill for broader system law. Stable obsolete-versioned wire schemas remain available only through the explicit historical `@receiz/sdk/obsolete-versioned` package entry; current skills never teach their key, head, receipt, reconcile, or signed-command mechanics as a current outcome.
+Start with `receiz-build-production-system` when work spans multiple constitutional domains and `receiz-global-reconciliation` for named-domain coordination. Machine-readable manifests require the exact active canonical v124 registry and operation-matrix digests, command-only mutation, independent verification, MCP conformance, and a passing release lock. Use a focused operation skill for SDK/MCP implementation and a constitutional skill for broader system law. Stable obsolete-versioned wire schemas remain available only through the explicit historical `@receiz/sdk/obsolete-versioned` package entry; current skills never teach their key, head, receipt, reconcile, or signed-command mechanics as a current outcome.
 
 The current operation skills are executable contracts. Current profile work uses the neutral authenticated same-UID profile operation. Current bearer ownership accepts a complete verified artifact, derives prior ownership from carried proof, and returns a native Record -> Seal artifact. Proof media uses the same native artifact custody and projects only a verified URL beneath it. These outcomes have no active identity-key, caller-head, claim-key, or receipt prerequisite. MCP calls the same SDK outcomes and never creates a parallel authority.
 
@@ -83,7 +89,7 @@ When SDK or MCP changes:
 - Generated apps must preserve Receiz proof semantics.
 - Generated apps should not require a traditional database unless the user explicitly asks for one.
 
-## v122 living-subject skills
+## Established living-subject skills
 
 - `receiz-living-subject` governs immutable subject identity, byte-preserved namespaces, ownership continuity, state, history, additions, and portable proof artifacts.
 - `receiz-subject-twin` governs subject-scoped profile, exact-head messaging, complete proof-brain retrieval, portable mind export/import, memory summaries, and the separation between speech, intentions, facts, memories, and performance.
@@ -93,6 +99,6 @@ When SDK or MCP changes:
 - `receiz-event-derived-memory` governs factual memories with admitted event citations and rebuildable AI summaries/projections.
 - `receiz-live-proof-character` governs streamed reply, audio, viseme, gaze, blink, breath, emotion, gesture, proposed intention, and completion events as non-authoritative performance over exact proof context.
 
-Every living-subject skill carries its SDK map, MCP map, authority rules, examples, tests, manifest, OpenAI metadata, and the exact v122 registry and operation-matrix digests. The skills teach the same sequence as the implementation: canonical head → entire proof history → compact indexes → relevant references → exact primary proof objects → reasoning → cited answer. They never authorize a world event, transfer, mandate, or release claim by prose.
+Every living-subject skill carries its SDK map, MCP map, authority rules, examples, tests, manifest, OpenAI metadata, and the exact current v124 registry and operation-matrix digests. The skills teach the same sequence as the implementation: canonical head → entire proof history → compact indexes → relevant references → exact primary proof objects → reasoning → cited answer. They never authorize a world event, transfer, mandate, or release claim by prose.
 
 The updated constitutional skills bind living-subject behavior into app building, command construction, deterministic replay, causal sync, global reconciliation, portable continuity, authority/security, MCP operation, testing, release, constitutional law, and offline-first operation. Their examples cover exact proof-memory speech, absent-owner exploration, mutual relationship formation, bounded trade, atomic battle, cross-device restoration, mandate revocation during a queued action, partition convergence, rejection of an AI-invented event, and cross-application subject continuity.

package/SKILLS.md

@@ -1,52 +1,41 @@
-# Receiz AI Skills v120
+# Receiz AI Skills v124
 
-V120 preserves sealed proof/object authority and adds
-`receiz.native_capture.v1` plus
-`receiz.pbi.proof-object-authorship.v1`. Native Capture binds dedicated camera
-ceremony bytes. PBI authorship requires canonical predecessor verification,
-appends ordered history, settles locally before optional publication, and does
-not transfer ownership.
+## Reality Becomes Infrastructure
 
-This package ships 39 skills, 33 machine-readable manifests, and 30 OpenAI agent prompts. Every current manifest binds registry digest `29a793a5bcc0195ab41d30614d37ac51df66023af354fa4335460764eb0af413` and application-operation-matrix digest `208553829ba78a5536524b864577ce59989e2d0a994fad9598d39ae3d557c4f5` from the v120 SDK source.
+**The Production Runtime for Verified Civilization.** The v124 distribution teaches agents to bind live Kai, explicit consent, exact heads, durable plans, one compare-and-swap execution, authenticated replay/checkpoints, private-access filtering, and exact recovery beneath the sealed proof object.
 
-## Current MCP artifact inventory: nine tools
+This package ships 42 skills, 36 machine-readable manifests, and 33 OpenAI agent prompts. Every current manifest binds ruleset `124.0.0`, SDK/MCP range `>=124.0.0 <125.0.0`, registry digest `d02429151b0bcebdaeb89485792e377afc55130f9a25e07982c1c88221314247`, and operation-matrix digest `540d1c1bf39f1b288b257c79a6e020bdcc5e587fc9b7dbf6b7aaa5d082e20ad5`.
 
-The single current inventory is:
+## V124 production-runtime composition
 
-1. `receiz_artifact_verify`
-2. `receiz_artifact_admit`
-3. `receiz_artifact_append_plan`
-4. `receiz_artifact_transition_seal_and_stage`
-5. `receiz_artifact_transition_commit`
-6. `receiz_artifact_global_resolve`
-7. `receiz_artifact_reconcile_plan`
-8. `receiz_artifact_reconcile_stage`
-9. `receiz_artifact_reconcile_commit`
+The current 53-operation matrix adds live Kai projection, canonical challenge creation, authority-session lifecycle, operational qualification, verified additions/replay/checkpoint admission, private additions, persisted-plan execution and recovery, atomic mutation planning, and privacy-safe public-recipient resolution. These operations are universal and introduce no application or principal admission path.
 
-The first five tools are also the historical v112 compatibility inventory. That historical label preserves the v112 contract; it does not define a second current surface.
+## Stable V123 completion skills
 
-## Current MCP living-subject inventory: 37 tools
+- `receiz-value-execution`: live Phi execution on exactly one Settlement or Reserve rail; USD is display-only; exact heads, idempotency, receipts, and lookup-before-retry are mandatory.
+- `receiz-proof-authority`: embedded proof-to-authority exchange after independent edge verification and explicit consent, without redirecting the person to receiz.com; grants are short-lived, non-refreshable, minimum-scope mechanics beneath the identity artifact.
+- `receiz-world-event-runtime`: SDK-owned v122 public planners remain stable protocol identifiers used by the current distribution to generate canonical command and transaction bytes.
+- `receiz-living-subject`: resolves named namespaces at one exact authenticated head with pinned registry and reducer digests.
 
-The exact v121 living-subject inventory covers `receiz_subject_resolve`, `receiz_subject_state`, `receiz_subject_history`, `receiz_subject_memory_query`, `receiz_subject_relationships`, `receiz_subject_inventory`, `receiz_subject_twin_profile`, `receiz_subject_twin_message`, `receiz_subject_twin_mind_export`, `receiz_subject_twin_mind_import_plan`, `receiz_subject_mandate_get`, `receiz_subject_mandate_plan`, `receiz_subject_mandate_activate`, `receiz_subject_mandate_pause`, `receiz_subject_mandate_revoke`, `receiz_world_additions`, `receiz_world_command_plan`, `receiz_world_command_validate`, `receiz_world_command_execute`, `receiz_world_transaction_plan`, `receiz_world_transaction_execute`, `receiz_world_receipt`, `receiz_world_replay`, `receiz_subject_runtime_enqueue`, `receiz_subject_runtime_status`, `receiz_subject_runtime_cancel`, `receiz_living_subject_conformance`, `receiz_subject_brain_head`, `receiz_subject_brain_search`, `receiz_subject_brain_resolve`, `receiz_subject_brain_stream`, `receiz_bearer_transfer_preview`, `receiz_bearer_instrument_issue`, `receiz_bearer_instrument_inspect`, `receiz_bearer_instrument_claim`, `receiz_bearer_transfer_cancel`, and `receiz_bearer_transfer_status`.
+## Current MCP inventories
 
-Every tool calls the SDK primitive named by its skill map, returns the source primitive and v120 registry/reducer digests, requires exact plan/permit/instrument confirmation for writes, resolves exact bytes before commit, and returns structured zero-write failure. MCP and skill prose never become authority.
+The package maps the nine artifact tools, 37 living-subject tools, 19 stable v122 protocol tools, and eight v123 completion tools to the canonical SDK. The v123 tools are:
 
-## Skill inventory
-
-The canonical machine-readable index is [skills.json](skills.json). Start with `receiz-build-production-system` for multi-domain work, `receiz-global-reconciliation` for named-domain head resolution and offline reconciliation, or a focused primitive skill for narrower work.
+1. `receiz_v123_world_plan_command_v122`
+2. `receiz_v123_world_plan_transaction_v122`
+3. `receiz_v123_value_execute_settlement`
+4. `receiz_v123_value_execute_reserve`
+5. `receiz_v123_value_execution_by_idempotency`
+6. `receiz_v123_subject_resolve_namespaces`
+7. `receiz_v123_identity_exchange_proof_authority`
+8. `receiz_v123_auth_granted_scopes`
 
-## Forbidden AI operations
+MCP confirms mutations, redacts bearer material, and never becomes proof, identity, ownership, or settlement authority.
 
-All current skills forbid: `last-write-wins`, `timestamp-as-head-authority`, `connect-token-as-proof-authority`, `local-receipt-as-global-authority`, `projection-as-current-owner`, `silent-divergence-resolution`, `remote-reconciliation-before-first-paint`, `unverified-server-artifact-render`, `environment-player-token-fallback`, `accepted-means-effects-delivered`, and `indeterminate-means-failed`.
+## Skill inventory
 
-These instructions remain beneath exact sealed artifact bytes, independently verified history, verified identity evidence, plan-bound capability authority, and atomic named-domain acceptance.
+The canonical machine-readable index is [skills.json](skills.json). Start with `receiz-build-production-system` for multi-domain work, `receiz-global-reconciliation` for named-domain coordination, `receiz-value-execution` for live Phi movement, or `receiz-proof-authority` for embedded consent and scopes.
 
-## v121 living-subject skills
+All current skills forbid last-write-wins, timestamp-as-head authority, connect-token-as-proof authority, projection-as-current-owner, silent divergence resolution, remote reconciliation before first paint, unverified server artifacts, retry-before-lookup, rail collapse, and USD-as-moved-value.
 
-- `receiz-living-subject`: immutable identity, byte-preserved namespaces, ownership continuity, state, history, additions, and portable artifacts.
-- `receiz-subject-twin`: complete exact-head proof retrieval, speech/intention/fact/memory separation, subject mind portability, and provenance.
-- `receiz-autonomous-mandate`: owner-confirmed digest scope, runtime re-verification, expiration, pause, and revocation.
-- `receiz-world-event-runtime`: typed command admission, deterministic receipts, durable ticks, retries, replay, and zero-write failure.
-- `receiz-multi-subject-transaction`: atomic meetings, relationships, battles, gifts, inventory, and trades.
-- `receiz-event-derived-memory`: admitted-event citations and rebuildable projections.
-- `receiz-live-proof-character`: streamed voice and performance cues that never become canonical fact.
+Historical protocol and schema identifiers remain documented only where current compatibility requires them. They do not define a second current authority surface.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@receiz/ai-skills",
-  "version": "122.0.0",
+  "version": "124.0.0",
   "description": "Registry-bound Receiz AI operating contracts beneath proof authority for SDK and MCP agents.",
   "type": "module",
   "files": [
@@ -47,7 +47,9 @@
     "receiz-multi-subject-transaction",
     "receiz-event-derived-memory",
     "receiz-live-proof-character",
-    "receiz-value-rails"
+    "receiz-value-rails",
+    "receiz-value-execution",
+    "receiz-proof-authority"
   ],
   "keywords": [
     "receiz",