docs: streamline AGENTS.md per prompting best practices (#5246)

docs: add autonomy and approval boundaries to AGENTS.md
This commit is contained in:
Zhengchao An
2026-07-26 05:34:45 +08:00
committed by GitHub
parent 258b7d6f06
commit 6da69180d8
+6
View File
@@ -21,6 +21,12 @@ If repo-level instructions conflict, follow the nearest file and keep behavior a
- Avoid redundant file reads, repeated commands, and unnecessary exploratory work once enough context is available. - Avoid redundant file reads, repeated commands, and unnecessary exploratory work once enough context is available.
- A good result is a minimal diff with clear assumptions, no over-engineering, and independent verification that survives Adversarial Validation (below). - A good result is a minimal diff with clear assumptions, no over-engineering, and independent verification that survives Adversarial Validation (below).
## Autonomy and Approval Boundaries
- Inquiry tasks (answer, explain, review, diagnose, plan): report findings; do not change files unless a fix is explicitly requested.
- Action tasks (change, build, fix): make in-scope local changes without asking for approval.
- Ask for confirmation before destructive or hard-to-reverse operations (force-pushes, history rewrites, deleting data or branches), merging a PR (reviewer approval required), or any material expansion of the requested scope.
## Communication and Language ## Communication and Language
- Respond in the same language used by the requester. - Respond in the same language used by the requester.