Engineering Loop

Engineering Loop

Own the change from a verified starting point to a reviewed result. Use one agent and this skill alone unless a specialist changes a material decision.

Establish the baseline

1. Read applicable AGENTS.md files and repository documentation.
2. Record the requested behavior, constraints, and observable done conditions.
3. Inspect the branch and working tree; preserve unrelated user-owned changes.
4. Identify repository-native validation and run the smallest safe baseline that separates pre-existing failures from task regressions.

For a long, cross-stack, or high-risk change, use the templates and failure rules in references/loop-contract.md. When a task is expected to need repeated autonomous iterations or has an explicit retry, time, token, or cost limit, also use references/loop-policy.md. When a defect is intermittent, performance-related, difficult to reproduce, or resists the first evidence-driven pass, use references/hard-debugging.md.

Run the loop

1. Reproduce the defect, or capture the current behavior for a feature.
2. Choose the smallest coherent change and the evidence that will prove it.
3. Add a failing regression test first when practical.
4. Implement one bounded change and run the narrowest relevant check.
5. Pause before expanding into an unplanned subsystem, public contract, migration, or external system. Record why the original scope is insufficient and obtain any authority the expansion requires.
6. Classify failures as product, test, environment, or assumption failures; fix the cause and rerun the affected check.
7. Run repository-required broader checks after focused checks pass.
8. Review the complete diff first for task-contract compliance, then for code quality, regressions, security, and maintainability.
9. Fix consequential findings and rerun checks affected by those fixes.

Keep a compact ledger of confirmed facts, changed files, commands, outcomes, and the next decision. Return concise diagnostics instead of full logs.