Kdna Creator

---
name: kdna-creator
description: Author and revise KDNA assets from authorized materials, review their substantive content and field coverage, and use the Host-selected native CLI or the explicitly matched Studio creation session.
---

# KDNA Creator

Choose the creation route from the Host's exact installed contract. For native authored assets with `create`, `source-open` and `source-pack`, read [native asset authoring and content review](references/native-asset-authoring.md). That route includes an executable field inventory, task-specific content review, official no-loss reading and versioned revision. A successful save does not approve the work's content. Do not require Studio or Work as a prerequisite for that native route.

For the explicitly matched Studio session, follow the remaining instructions and [the terminal adapter](references/terminal-session.md). Core owns component interpretation and Studio owns materialization and the one-use lifecycle. Exact archive content and a Host-approved installation are required; no global binary, latest package, alternate checkout or old-Core fallback. The matched Studio route creates container 0.5 assets with Read 0.6.4; the native CLI route creates container 0.6 assets with Read 0.7. A shared Core/Read package version does not make the two container routes interchangeable. Keep each workflow on its declared reader and source-revision route. To reopen and revise protected Studio output, use the separate [local protection Host](references/studio-protected-host.md) with independently supplied permission and credential channels.

Start from the user's natural language and reuse the existing authorization. Establish the intended judgment, scope, explicit materials and new private output directory. Ask only for a material ambiguity or genuinely unsupported boundary. Do not ask people to author protocol IDs, carriers, hash fields or review tickets. No material path means no directory scan. Read only named UTF-8 text files or interview through the selected live channel. If verified-local processing is required and the Host cannot attest it, stop before reading; a local executable does not prove where the Agent processes content.

Draft at least two substantive alternatives for each intended judgment. Explain evidence, applicability, uncertainty and tradeoffs. Preserve the actual source and license/notice obligations. New comparisons are new editorial work, not retrospectively proven producer loss. Do not manufacture extra judgments, taxonomy, diagnostic structure or prerequisites to fill a template. The current Studio exporter requires an explicitly complete method and rejects method absence with `CREATION_METHOD_REQUIRED`; do not invent a method to bypass that restriction. Use one of the frozen supported component forms only when it expresses the actual judgment. Keep candidate-specific conditions with that candidate, never AND them into overall conditions; an explicitly empty overall condition set may be correct.

Obtain actual selection and fresh final adoption of the full current preview. Use a separate human channel for human-declared review. When the user or authorized supervisor has expressly delegated editorial adoption to an Agent, use the separate Agent adoption channel and record that existing authority. Represent the actor as an Agent, never as a human. A synthetic callback executing is a test, not an actual editorial decision. Do not invent a missing reply or replay an old content decision into a new context.

The Agent interprets actual reviewer language; role, message/review coordinates and final context are bound by the live Host. Neither channel proves identity. Keep stdin/stdout private because it contains material bodies, alternatives, replies and evidence. After any revision, select current alternatives again, show a new preview and obtain fresh final adoption. EOF/error/abort terminates the workspace; do not reconstruct a live capability from JSON.

Deliver the exclusive private bundle only after the CLI saves, reads back and completes the actual bytes. A live `accepted_with_live_context` result is limited to that creation and saved-byte check. Static reopening keeps `creation_accepted:not_evaluated`, `live_context:unavailable`, `identity:not_verified` and `action_authorization:not_evaluated`. Actual editorial acceptance, editorial fitness, identity, action authorization and publication are separate evidence. Read still requires explicit permission and grants no action authority.

Current format2 and its exact graph are required. Historical format1/format-absent artifacts keep their original accepted release and UNKNOWN missing pins; never infer from version, relabel evidence, replace an external expected binding or silently import a prior workspace. See [the typed input guide](references/component-creation-draft.md) for the current authoring surface.