habitat-blueprint-packet-frame
Mental model for one Habitat rule packet as one reviewable policy claim with one qualified verification mechanism.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Mental model for one Habitat rule packet as one reviewable policy claim with one qualified verification mechanism.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Mental model for a sealed service whose context and authorship narrow toward operation handlers.
Mental model for locating work in RAWR's blueprint kinds while keeping semantic direction, ownership, and structural proof distinct.
Mental model for Nx as the repository graph and scheduler while project owners retain their qualified build and verification work.
Mental model for one conventional installed Oclif application that owns CLI identity while commands retain qualified capability boundaries.
Mental model for a first-party Oclif command plugin as one host-composed terminal projection on public package boundaries.
Mental model for an application as the concrete selection and realization boundary of the product chain.
| name | habitat-blueprint-packet-frame |
| description | Mental model for one Habitat rule packet as one reviewable policy claim with one qualified verification mechanism. |
Activation: None. This lowercase
skill.mdis an unregistered design seed and does not participate in Habitat discovery.
A blueprint packet is one durable policy claim packaged with the evidence needed to evaluate it. The packet is smaller than the architectural kind and smaller than the product behavior. Its job is to make one monotonic constraint inspectable, executable, and reviewable without acquiring broader ownership.
rule.json names the claim, its owner, scope, reason, and remediation.
structure.toml owns positive filesystem topology. pattern.md owns source
relationships. baseline.json records admitted findings during convergence;
it is not a source of truth and does not turn debt into design.
The strongest packet removes a class of invalid possibilities while leaving valid implementation choice open. It describes a relation shared by every member of a kind, not today's product inventory, a list of retired filenames, or one migration's temporary state.
One packet should have one natural evaluator. Mixing topology, source semantics, behavior, and process orchestration in the same mechanism makes the claim ambiguous. Native Habitat capabilities remain the ordinary substrate. An executable escape hatch represents an admitted evaluator gap, not a preferred policy language or a place for architecture.
The packet closes structure around meaningful work. TypeScript and runtime tests still verify the behavior inside that structure.