docs(agents): add operating principles

Inspired by https://github.com/forrestchang/andrej-karpathy-skills.
2026-08-03 07:41:04 +02:00 · 2026-04-28 15:24:35 +07:00
parent ae62b9dbf1
commit f82e5f04b9
1 changed files with 8 additions and 0 deletions
@@ -22,6 +22,14 @@ Only record items that are repo-specific, likely to recur, and have a concrete m
 - **SHOULD** rules are strong defaults unless task context requires a different choice.
 - If guidance conflicts, prefer: user request > MUST > SHOULD > playbooks.

+## Agent Operating Principles
+
+- Before editing, state important assumptions when the task is ambiguous. Ask instead of silently choosing between materially different interpretations.
+- Prefer the smallest implementation that solves the requested problem. Do not add speculative abstractions, configurability, or features.
+- Keep diffs surgical. Do not refactor, reformat, rename, or "improve" adjacent code unless it is necessary for the task.
+- Clean up only artifacts created by the current change, such as newly unused imports or dead helper code.
+- For non-trivial work, define success criteria and verify them with the narrowest reliable checks before marking the task complete.
+
 ## Task Router (Read First)

 | Situation | Required action |