@receiz/ai-skills 127.0.0 → 129.0.0

package/README.md

@@ -3,9 +3,9 @@
 Explore the [public capability directory](https://receiz.com/capabilities) for user outcomes, every public SDK callable, MCP tools, and AI skills. Agents can read the [machine-readable catalog](https://receiz.com/capabilities.json). An inventory entry grants no access and does not imply an MCP execution adapter.
 
 
-The `127.0.0` package at release coordinate `v127.0.0` 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.
+The `129.0.0` package at release coordinate `v129.0.0` 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.
 
-KKSv1.0 is the single temporal authority for proof. New proof coordinates are computed locally from Genesis and the canonical pulse frequency; existing coordinates are carried by the verified sealed object. `createdAt` is descriptive Chronos only and is never proof, ordering, or causal authority. The SDK, MCP tools, all 37 machine manifests, and the shared [KKSv1.0 temporal-authority contract](resources/kks-v1-temporal-authority.md) enforce the same boundary.
+KKSv1.0 is the single temporal authority for proof. New proof coordinates are computed locally from Genesis and the canonical pulse frequency; existing coordinates are carried by the verified sealed object. `createdAt` is descriptive Chronos only and is never proof, ordering, or causal authority. The SDK, MCP tools, all 37 machine manifests, and the shared [KKSv1.0 temporal-authority contract](https://unpkg.com/@receiz/ai-skills@129.0.0/resources/kks-v1-temporal-authority.md) enforce the same boundary.
 
 ## Highest Cash-Out Frame
 
@@ -15,23 +15,27 @@ Every AI skill is the reader layer beneath those authorities. The manifests
 forbid `reader-as-authority`; an agent may inspect, verify, and project, but it
 may not author, reorder, replace, or outrank the actual sealed proof object.
 
-## V127 — Reality-Grade Infrastructure
+## V129 — Reality-Grade Infrastructure
 
-V127 aligns the SDK, compiler, MCP and AI packages with complete source custody, first-seal ownership, deterministic coordinates and verified append continuity. The public function catalog covers 678 callable exports across the main, compiler, testing, React, offline sealing, local subject host and offline KaiSigil entry points. MCP capability reporting includes this catalog and the complete 425-method client inventory; 330 explicit tools retain their SDK authority boundaries.
+V129 preserves exact registered application IDs across the established SDK, compiler, full MCP and AI packages, with complete source custody, first-seal ownership, deterministic coordinates and verified append continuity. The public function catalog covers 704 callable exports across the main, compiler, testing, React, offline sealing, local subject host, offline KaiSigil and pure valuation entry points. MCP capability reporting includes this catalog and the complete 425-method client inventory; 356 explicit tools retain their SDK authority boundaries. Twenty-one new full-library adapters compose seven financial operations and eleven public-proof, World, sports, verification, and record operations plus three read-only offline valuation adapters without replacing proof or custody.
 
-V127 agents can create full KaiSigil proofs locally with packaged resources and use the [source-bound local subject runtime](../packages/receiz-sdk/docs/local-subject-runtime.md). Temporal execution admits complete causal coordinates; bare pulse values, model reports and copied plans cannot advance authority. [Offline file sealing](../packages/receiz-sdk/docs/offline-sealing.md) runs without network after explicit signer enrollment; KaiSigil proving requires no enrollment or network. Portable history retains exact V120 snapshots and full temporal evidence under the enclosing sealed source.
+The [SDK/MCP execution coverage guide](https://unpkg.com/@receiz/sdk@129.0.0/docs/capability-execution-coverage.md) distinguishes direct bounded MCP tools from SDK operations composed by a trusted host or device. Discovery describes all 425 client methods and 704 callable exports; execution follows the actual adapter, credentials, grants, confirmation, and custody requirements. Identity-signed public-store publication, offline Note/Reserve WebAuthn custody, and private account-Twin binary export/import require SDK host or device composition; subject-Twin has its own source-family adapters. Exact bytes, device keys, callbacks, and SDK-issued authority objects remain in their existing host or device runtime. The full library includes financial execution; the separate ChatGPT profile retains 195 restricted tools.
 
-Capability inventory is not a claim that every historical HTTP route exists. Of the 81 newly mapped JSON SDK adapters, 12 compose current routes and 69 require explicit historical HTTP compatibility; older `media.upload`, `media.transform`, and `proof.query` also require that transport. Default calls fail before requests or mutation previews. Agents must follow [historical HTTP compatibility](../packages/receiz-sdk/docs/historical-http.md) and the separate historical subject transport boundary in the local runtime guide. Neither compatibility configuration nor credentials become proof authority.
+The current `receiz_connect_record` adapter requires `receiz:record`, exact single-use record/save/visibility consent, and the complete PNG from `connect.record`. Set `body.save` explicitly: the route defaults it to true. `vis: "public"` selects showcase, `"private"` selects private visibility, and `"hidden"` or an omitted `vis` hides the record from showcase. It verifies the enclosing canonical proof before private exact-byte output. Save, visibility, and showcase response headers describe server effects beneath that proof. A remote save may precede a failed delivery or verification; resolve the unknown outcome before retry and never infer zero remote writes.
+
+V127 agents can create full KaiSigil proofs locally with packaged resources and use the [source-bound local subject runtime](https://unpkg.com/@receiz/sdk@129.0.0/docs/local-subject-runtime.md). Temporal execution admits complete causal coordinates; bare pulse values, model reports and copied plans cannot advance authority. [Offline file sealing](https://unpkg.com/@receiz/sdk@129.0.0/docs/offline-sealing.md) runs without network after explicit signer enrollment; KaiSigil proving requires no enrollment or network. Portable history retains exact V120 snapshots and full temporal evidence under the enclosing sealed source.
+
+Capability inventory is not a claim that every historical HTTP route exists. Of the 86 JSON SDK adapters, 17 compose current routes and 69 require explicit historical HTTP compatibility; two additional financial artifact adapters preserve private exact-byte custody rather than a JSON result. Older `media.upload`, `media.transform`, and `proof.query` also require historical transport. Historical default calls fail before requests or mutation previews. Agents must follow [historical HTTP compatibility](https://unpkg.com/@receiz/sdk@129.0.0/docs/historical-http.md) and the separate historical subject transport boundary in the local runtime guide. Neither compatibility configuration nor credentials become proof authority.
 
 ### Preserved V125 economy contracts
 
 **Sealed Reality Becomes Spendable Value. Economic authority follows proof, not institution.** V125 teaches agents to register a sealed lawful-action law, submit a separately sealed completed action whose causal claims are derived from a reverified portable execution-authority transition, and request deterministic current-Kai Settlement projection without inventing value. The exact micro-Phi law is `(completionKai - startKai + 1) * (valuationKai - completionKai + 1)`. No AI, developer, government, institution, server, database, or model may supply a completion verdict, amount, multiplier, bonus, backfill, or proof exemption.
 
-The current 330-tool MCP registry preserves the 169-tool v124.1 runtime inventory, 39 trust adapters, and thirteen v125 economy adapters alongside the new v127 tools. The thirteen economy adapters comprise three lawful-action operations plus the complete ten-operation sender/receiver edge lifecycle for planning, inspection, transition-set verification, commit preparation, recovery packaging, Settlement send/receive, and Reserve send/receive. Exact proof, plan, transition, commit, and recovery materials stay in trusted-host or same-runtime custody behind opaque references. The enclosing sealed artifact is verified before payload extraction. One admitted membership belongs to the current owner; transfer moves it without cloning Settlement value or erasing provenance. Reserve remains the legacy funding rail.
+The current 356-tool MCP registry preserves the 169-tool v124.1 runtime inventory, 39 trust adapters, and thirteen v125 economy adapters alongside the v127 tools and twenty-one current adapters. The thirteen economy adapters comprise three lawful-action operations plus the complete ten-operation sender/receiver edge lifecycle for planning, inspection, transition-set verification, commit preparation, recovery packaging, Settlement send/receive, and Reserve send/receive. Exact proof, plan, transition, commit, and recovery materials stay in trusted-host or same-runtime custody behind opaque references. The enclosing sealed artifact is verified before payload extraction. One admitted membership belongs to the current owner; transfer moves it without cloning Settlement value or erasing provenance. Reserve remains the legacy funding rail.
 
-`skills.json` also binds all 425 callable methods on the public `createReceizClient()` surface by exact ordered inventory and digest. The union of the 37 machine manifests must contain every method and all 330 MCP tools; generation and validation fail if either distribution surface drifts. Three retained artifact-recovery methods are explicitly classified under `historicalSdkOperations`, remain callable, and are not mislabeled as v125 defaults. `receiz_capabilities` exposes the same SDK inventory, exact MCP tool inventory, and v125 capability families without turning capability description into proof or transaction authority.
+`skills.json` also binds all 425 callable methods on the public `createReceizClient()` surface by exact ordered inventory and digest. The union of the 37 machine manifests must contain every method and all 356 MCP tools; generation and validation fail if either distribution surface drifts. Three retained artifact-recovery methods are explicitly classified under `historicalSdkOperations`, remain callable, and are not mislabeled as v125 defaults. `receiz_capabilities` exposes the same SDK inventory, exact MCP tool inventory, and v125 capability families without turning capability description into proof or transaction authority.
 
-All 37 current manifests use package/ruleset `127.0.0`, SDK/MCP range `>=127.0.0 <128.0.0`, registry digest `8d0b5b839d02d9efbd4306cc99410595a183705c2670b76d2567eaaaade99065`, and operation-matrix digest `eadd171a45fcc51e275a1c57de1eb8e67614757a5723d141793641edf7207a10`.
+All 37 current manifests use package `129.0.0` and inherited ruleset `127.0.0`, SDK/MCP range `>=129.0.0 <130.0.0`, registry digest `8d0b5b839d02d9efbd4306cc99410595a183705c2670b76d2567eaaaade99065`, and operation-matrix digest `c4e0cff348b62f31db2bb2ffdeec533a92ca3a6d476757bb9b559ac58a7875e1`.
 
 ## Historical V124 — Reality Becomes Infrastructure
 
@@ -59,7 +63,7 @@ The same package carries 37 inherited living-subject MCP tools: subject resolve/
 
 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.
 
-V124 introduced 22 universal production-runtime MCP adapters for live Kai, canonical proof-authority challenges, durable atomic execution, authority-session lifecycle, operational qualification, verified public/private additions and replay/checkpoints, unsealed replay-candidate export followed by canonical seal and sealed restore, namespace resolution, privacy-safe recipient resolution, and sealed-source publication. V124.1 added four source-carried adapters, producing the retained exact 26-tool family. The exact names, SDK methods, fixed/conditional scopes, input/output references, process-local handles, and trusted-host custody rules are published in the [V124 runtime tool map](receiz-mcp-agent-skill/resources/v124-runtime-tool-map.md).
+V124 introduced 22 universal production-runtime MCP adapters for live Kai, canonical proof-authority challenges, durable atomic execution, authority-session lifecycle, operational qualification, verified public/private additions and replay/checkpoints, unsealed replay-candidate export followed by canonical seal and sealed restore, namespace resolution, privacy-safe recipient resolution, and sealed-source publication. V124.1 added four source-carried adapters, producing the retained exact 26-tool family. The exact names, SDK methods, fixed/conditional scopes, input/output references, process-local handles, and trusted-host custody rules are published in the [V124 runtime tool map](https://unpkg.com/@receiz/ai-skills@129.0.0/receiz-mcp-agent-skill/resources/v124-runtime-tool-map.md).
 
 `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.
 
@@ -70,7 +74,7 @@ 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 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. `receiz-value-execution` governs exact live Phi execution and retry recovery; `receiz-proof-authority` governs edge verification, explicit consent, and minimum-scope embedded authority. The v124 coordinates remain immutable historical evidence; the v127 manifest coordinates above are current.
+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. The v124 coordinates remain immutable historical evidence; the v129 manifest coordinates above are current.
 
 This package teaches AI agents how to understand, verify, build with, and operate Receiz from the existing repository surfaces.
 
@@ -83,13 +87,21 @@ 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 330-tool registry preserves the 169-tool v124.1 inventory, thirteen v125 lawful-action and edge-value tools, and 39 trust adapters alongside the v127 tools. The four V124.1 source-carried adapters remain unchanged and expose replay-family opening, Receiz-ID conversation-family opening, bounded private epoch-grant planning, and held material-family inspection while exact sources, secrets, locators, and large bytes remain in trusted-host custody.
+- MCP: `@receiz/mcp-server` is for agent tool access. Its current 356-tool registry preserves the 169-tool v124.1 inventory, thirteen v125 lawful-action and edge-value tools, and 39 trust adapters alongside the v127 tools and twenty-one current adapters. The four V124.1 source-carried adapters remain unchanged and expose replay-family opening, Receiz-ID conversation-family opening, bounded private epoch-grant planning, and held material-family inspection while exact sources, secrets, locators, and large bytes remain in trusted-host custody.
 
 `skills.json` carries the canonical `v124_1CapabilityInventory`, and each relevant manifest carries its exact `v124_1CapabilityIds`. This binds source-carried replay, unlimited invited-member conversation, exact large-material reconstruction, progressive verified playback, proof-derived memory/Twin response, and portable account continuity across SDK, MCP, and AI instructions without allowing the model layer to invent or outrank proof.
 - 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.
 
+## Registered native application setup
+
+For registered native APIs, set `RECEIZ_APPLICATION_ID` and SDK `applicationId` to the exact registered OIDC client ID returned by Receiz. Keep its bytes/case and `rc_` prefix; never replace it with a subject Receiz ID, username, normalized slug, alias, or client secret. Keep client secrets server-side. Syntax compatibility for existing native slugs does not authorize an unregistered client.
+
+The [registered native session example](https://unpkg.com/@receiz/ai-skills@129.0.0/receiz-proof-authority/examples/registered-native-session.md) binds genuine device-held consent, minimum scopes, grant exchange, current complete subject-source publication, authority-session opening, and qualification to the same exact application/audience. It names actual full SDK methods and MCP adapters; restricted ChatGPT Marketplace profiles retain their own constraints. Qualify every called operation and its deployed dependencies, then record live integration results separately from fixture/config evidence.
+
+The [commerce example](https://unpkg.com/@receiz/ai-skills@129.0.0/receiz-commerce-skill/examples/create-no-db-store.md) separates wallet funding, payment, seller proceeds, complete bearer artifact delivery, claim, custody, and purchased asset use. Card checkout success alone establishes no asset purchase or ownership transfer. Release the compatible libraries, server, and forward database migration together; explicitly mark every untested live stage.
+
 ## 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 v127 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.
@@ -138,3 +150,11 @@ When SDK or MCP changes:
 Every living-subject skill carries its SDK map, MCP map, authority rules, examples, tests, manifest, OpenAI metadata, and the exact current v127 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.
+
+## V129 coordinated distribution target
+
+The [v129 release record](https://docs.receiz.com/releases/v129.0.0) describes the coordinated `129.0.0` SDK, full MCP library, and AI-skills source/package target. The admitted constitutional ruleset remains `127.0.0` with its exact canonical registry bytes and retained v124/v125 protocols. V129 preserves registered application bytes through existing proof-authority, source publication, sessions, replay, and execution without an alias or replacement authority.
+
+**Source + law + sequence + object + evidence. And the reader underneath them.** The enclosing proof object remains terminal authority through time. SDK/MCP responses, OIDC grants, sessions, rows, public projections, configuration, and agent statements remain readers or execution mechanics beneath it. The full MCP library supports financial workflows; the ChatGPT Marketplace plugin has a separate restricted nonfinancial profile.
+
+The generated catalogs bind the exact callable methods, actual tools, and skill manifests. Qualification must cover actual used operations and deployed dependencies. Funding, wallet credit, payment, seller proceeds, complete bearer delivery, claim, custody, and asset use remain distinct live evidence stages. Current package publication, server/database deployment, and fresh-client seller/buyer acceptance are recorded separately in the [v129 conformance source](https://github.com/kojibai/receiz/blob/main/docs/releases/v129.0.0-conformance.md); this prepared target does not claim those stages passed. V128 acceptance remains historical evidence at its original frozen coordinates.

package/SKILLS.md

@@ -1,68 +1,33 @@
-# Receiz AI Skills v125
+# Receiz AI Skills v129.0.0
 
-## Reality Becomes the Economy
+## Reality-Grade Infrastructure
 
-**Sealed Reality Becomes Spendable Value. Economic authority follows proof, not institution.** The v125 distribution teaches agents to derive Settlement from sealed lawful actions and to move explicit Settlement or Reserve between sender and receiver edges while servers and databases perform additive global sync only.
+**The source carries authority. Every experience carries it forward.** Receiz is a proof-native artifact system. Source + law + sequence + object + evidence remain authority; every reader operates beneath them. Sealed reality carries Settlement, Reserve, identity, ownership, and verified continuity through permitted experiences.
 
-This package ships 43 skills, 37 machine-readable manifests, and 34 OpenAI agent prompts. Every current manifest binds ruleset `126.0.0`, SDK/MCP range `>=126.0.0 <127.0.0`, registry digest `80137c2e6f294050ef36ff75e4daac15c7790b7f04d9a91fab9d1970fa3c0b09`, and operation-matrix digest `42c7f0924df91b4ba11c1b891fee2b92abb509430a86b030735c23d055e67949`.
+This package ships 43 skills, 37 machine-readable manifests, and 34 OpenAI agent prompts. Current manifests bind SDK/MCP range `>=129.0.0 <130.0.0`, canonical ruleset `127.0.0`, registry digest `8d0b5b839d02d9efbd4306cc99410595a183705c2670b76d2567eaaaade99065`, and operation-matrix digest `c4e0cff348b62f31db2bb2ffdeec533a92ca3a6d476757bb9b559ac58a7875e1`. The canonical ruleset retains its own version independently of the distribution version.
 
-Every manifest also carries the identical KKSv1.0 temporal-authority contract and forbids `created-at-as-proof-authority`. New proof coordinates come from the local Genesis/frequency computation; existing proof coordinates come from verified sealed objects; Chronos timestamps are descriptive projection only. Read the shared [KKSv1.0 contract](resources/kks-v1-temporal-authority.md).
+Every manifest carries the identical KKSv1.0 temporal-authority contract and forbids `created-at-as-proof-authority`. New proof coordinates come from the local Genesis/frequency computation; existing proof coordinates come from verified sealed objects; Chronos timestamps are descriptive projection only. Read the shared [KKSv1.0 contract](resources/kks-v1-temporal-authority.md).
 
-## Highest Cash-Out Frame
+## Complete capability synchronization
 
-**source + law + sequence + object + evidence. And the reader underneath them.**
+The machine index carries 704 callable SDK exports, all 425 public SDK client methods, and the exact 356-tool full MCP inventory. The union of the manifests binds every public SDK client method and every MCP tool. Three retained artifact-recovery methods remain explicitly historical.
 
-Every skill is a reader beneath these authorities and forbids
-`reader-as-authority`.
+SDK exports, SDK client methods, MCP tools, and AI skills are distinct interfaces. Listing a function grants no access and creates no adapter. Use the [execution coverage and host composition map](resources/capability-execution-coverage.md) for direct MCP adapters, SDK composition, device interaction, historical hosts, and disabled routes. Identity custody, private epoch secrets, and WebAuthn remain in their existing trusted host or device boundaries. The restricted ChatGPT distribution retains its separate permitted tool inventory.
 
-## V125 complete capability synchronization
+## Financial execution
 
-The machine index carries all 421 callable methods on the public SDK client, their exact digest, the complete capability families, and the exact 221-tool MCP inventory. The union of the manifests binds every public SDK client method and every MCP tool. Three retained artifact-recovery methods remain in the explicit historical field instead of being relabeled current. The ten v125 edge-value tools mirror every `client.value.edge` method; `receiz_v124_execution_execute` also returns a recovery reference when the canonical SDK outcome carries committed transition custody. MCP references remain custody mechanics, never authority.
+The full MCP supports the SDK financial routes under existing proof admission, delegated scopes, exact arguments, and explicit confirmation. Read the [full financial tool map](receiz-mcp-agent-skill/resources/full-financial-tool-map.md). A paid card checkout credits only its verified bound principal idempotently; a later purchase or transfer still requires its own authorization. Settlement and Reserve remain distinct rails. Committed, zero-write, and unknown outcomes govern lookup before retry.
 
-## Historical V124 production-runtime composition
+## Historical protocol composition
 
-The inherited 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.
+Existing v123, v124, v124.1, and v125 protocol identifiers preserve their exact wire identities beneath the current distribution. They are implemented primitives, not new authority layers. The [universal V124 runtime tool map](receiz-mcp-agent-skill/resources/v124-runtime-tool-map.md) binds SDK methods, delegated scopes, and custody. The machine-readable capability inventories bind the declared families to the exact SDK methods, MCP tools, and AI skills.
 
-## Stable V123 completion skills
-
-- `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.
-
-## Current MCP inventories
-
-The package maps the complete 221-tool registry—including nine artifact tools, 37 living-subject tools, 19 stable v122 protocol tools, eight v123 completion tools, 26 V124 production-runtime tools, thirteen v125 economy tools, and 39 trust tools—to the canonical SDK. The exact V124 tool/SDK/scope/custody contract remains in the [universal V124 runtime tool map](receiz-mcp-agent-skill/resources/v124-runtime-tool-map.md). The machine-readable `v124_1CapabilityInventory` and `v125CapabilityInventory` bind every declared capability family to the exact SDK methods, MCP tools, and AI skills that teach it.
-
-The V124 adapters cover:
-
-- canonical live Kai and proof-authority challenge creation;
-- atomic plan, stage, execute, resolve, idempotency recovery, and cancel;
-- authority-session open, refresh, close, and runtime qualification;
-- verified additions, replay, checkpoint, trusted-host private additions, unsealed replay-candidate export, canonical sealing, and sealed restore;
-- subject namespace resolution, privacy-safe recipient resolution, and sealed-source publication.
-
-The stable v123 tools are:
-
-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`
-
-MCP confirms mutations, redacts bearer material, and never becomes proof, identity, ownership, or settlement authority.
+The V124 adapters cover canonical Kai projection and proof-authority challenge creation; atomic plan, stage, execute, resolve, recovery, and cancel; authority-session lifecycle; verified additions, replay and checkpoint admission; trusted-host private additions; canonical sealed restore; subject namespace and privacy-safe recipient resolution; and sealed-source publication.
 
 ## 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 coordination, `receiz-value-execution` for live Phi movement, or `receiz-proof-authority` for embedded consent and scopes.
-
-All current skills forbid last-write-wins, timestamp-as-head authority, created-at-as-proof 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.
-
-Historical protocol and schema identifiers remain documented only where current compatibility requires them. They do not define a second current authority surface.
+The canonical machine-readable index is [skills.json](skills.json). Start with `receiz-build-production-system` for multi-domain work, `receiz-global-reconciliation` for coordination, `receiz-value-execution` for Phi movement, or `receiz-proof-authority` for embedded consent and scopes.
 
-## v126 complete SDK reference
+All current skills forbid last-write-wins, timestamp-as-head authority, created-at-as-proof 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. MCP references select custody; they never become proof, identity, ownership, or Settlement authority.
 
-Read [all public SDK function signatures](resources/sdk-public-functions.json) and [the entry-point index](resources/sdk-public-functions.md), including compiler, testing, and React exports. Client capabilities and executable MCP adapters remain separately identified; inventory membership never substitutes for an implemented adapter or SDK proof admission.
+Read [all public SDK function signatures](resources/sdk-public-functions.json) and [the entry-point index](resources/sdk-public-functions.md), including compiler, testing, and React exports. Historical protocol and schema identifiers remain documented where current compatibility requires them.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@receiz/ai-skills",
-  "version": "127.0.0",
+  "version": "129.0.0",
   "description": "Registry-bound Receiz AI operating contracts beneath proof authority for SDK and MCP agents.",
   "type": "module",
   "files": [
@@ -68,6 +68,6 @@
     "access": "public"
   },
   "scripts": {
-    "test": "node scripts/validate-skills.mjs"
+    "test": "node scripts/validate-skills.mjs && node scripts/test-registered-application-docs.mjs"
   }
 }