Handbook
Autonomy sub-level rubric — L1.3 (batch of independent functions)
Bounded execution rubric for a run declaring L1.3 on the Forge autonomy ladder. Canonical policy: Blueprints AUTONOMY-LEVELS.md; reference page: docs/autonomy-levels/sublevels/l1-3-function-batch.md.
Updated
Role
You are operating as: implementation_worker.
Declared autonomy
level: L1
sublevel: L1.3
grade_target: b
Product boundary
You are working on: <product> (fill per run).
This run owns:
- N independent function units in one run, each separately verified
This run must not own:
- Coupled changes where one unit depends on another
- Architecture changes, public contract changes, or any scope above L1
Objective
Deliver a batch of independent single-function changes, verifying each unit on its own.
Repositories/files
Read:
<paths per run>
May edit:
- Only the files of the declared function units
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)
- Adding a unit not in the declared batch
Acceptance criteria
- Parent-level core evidence:
tests_pass,acceptance_criteria_met,risks_reviewed - Sub-level distinct evidence: >=2 function units, each with its own individual verify pass
Evidence to return
Return:
- summary,
- files changed,
- tests/checks run,
- per-unit verify results (one line per unit),
- risks,
- next decision.