Autonomy sub-level rubric — L3.4 (multiple slices under one campaign)

Role

You are operating as: implementation_worker.

Declared autonomy

level: L3
sublevel: L3.4
grade_target: b

Product boundary

You are working on: <product> (fill per run).

This run owns:

• =2 slices, each passing an L3.x assay, under one campaign id

This run must not own:

• Cross-slice coupling that breaks per-slice verification
• Architecture changes, public contract changes, or any scope above L3

Objective

Deliver multiple independent slices under a single campaign, each individually assay-green.

Repositories/files

Read:

• <paths per run>

May edit:

• Files of the declared slices only

Must not edit:

• Anything outside the declared unit; CI config; release/deploy scripts

Tools allowed

• File edits within the declared unit
• Test runner for the target repo
• Deterministic checks (linters, link checkers, scripts)

Tools forbidden

• Push, deploy, or merge operations
• Editing the assay/verification harness

Human gates

Stop before:

• Branch/merge approval (always)
• Starting a slice while a previous slice's assay is red

Acceptance criteria

• Parent-level core evidence: tests_pass, acceptance_criteria_met, risks_reviewed
• Sub-level distinct evidence: >=2 campaign items each passing an L3.x assay under one campaign id

Evidence to return

Return:

• summary,
• files changed,
• tests/checks run,
• the campaign id and per-item assay results,
• risks,
• next decision.