Engineering
Architecture Rubric Refactor
Refactor against a written rubric, not taste fumes.
Use when
A refactor matters, but “make architecture better” is too vague.
Cadence
When architecture work has a defined scope
Verification
Scoped module meets the written rubric, tests pass, and unresolved objections are explicit.
Structured loop spec
| Field | Value |
|---|---|
| Name | Architecture Rubric Refactor |
| Category | Engineering |
| Trigger | When architecture work has a defined scope |
| Objective | Refactor against a written rubric, not taste fumes. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Define the exact scope, source of truth, and approval boundary.; Inspect current state and rank the highest-risk gap.; Make one small, reversible improvement.; Run the stated verification and record evidence.; Stop on success, budget, no progress, or approval required. |
| Verification | Scoped module meets the written rubric, tests pass, and unresolved objections are explicit. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Pull request, patch, report, or evidence log |
| Works with | Claude Code, OpenAI Codex, Cursor, Gemini CLI, any tool-using coding agent |
Steps
- Define the exact scope, source of truth, and approval boundary.
- Inspect current state and rank the highest-risk gap.
- Make one small, reversible improvement.
- Run the stated verification and record evidence.
- Stop on success, budget, no progress, or approval required.
Prompt
Run the Architecture Rubric Refactor loop. Use it when A refactor matters, but “make architecture better” is too vague. Work in bounded iterations: inspect current state, choose the highest-risk gap, make one reversible improvement, verify it, and record evidence. Stop when Scoped module meets the written rubric, tests pass, and unresolved objections are explicit. or when blocked, budget exhausted, or approval is required.Run in Claude Code
Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.
Run the "Architecture Rubric Refactor" loop from AI Loop Library (https://ailooplibrary.com/loops/architecture-rubric-refactor/) as a bounded loop.
Goal: Refactor against a written rubric, not taste fumes.
Rules: one change per round; run the same verification every round (Scoped module meets the written rubric, tests pass, and unresolved objections are explicit.); append each round to docs/loops/architecture-rubric-refactor/progress.md and update docs/loops/architecture-rubric-refactor/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.