mirror of
https://github.com/openai/codex.git
synced 2026-05-03 10:56:37 +00:00
Add Code Review skill (#18746)
Adds a skill that centralizes rules used during code review for codex.
This commit is contained in:
12
.codex/skills/code-review-context/SKILL.md
Normal file
12
.codex/skills/code-review-context/SKILL.md
Normal file
@@ -0,0 +1,12 @@
|
||||
---
|
||||
name: code-review-context
|
||||
description: Model visible context
|
||||
---
|
||||
|
||||
Codex maintains a context (history of messages) that is sent to the model in inference requests.
|
||||
|
||||
1. No history rewrite - the context must be built up incrementally.
|
||||
2. Avoid frequent changes to context that cause cache misses.
|
||||
3. No unbounded items - everything injected in the model context must have a bounded size and a hard cap.
|
||||
4. No items larger than 10K tokens.
|
||||
5. Highlight new individual items that can cross >1k tokens as P0. These need an additional manual review.
|
||||
Reference in New Issue
Block a user