code-review-context
Model visible context
Install
npx skillscat add openai/codex/code-review-context Install via the SkillsCat registry.
About this skill
The skill builds an incremental, bounded message context sent to the model, preventing cache misses and enforcing size limits while flagging large fragments for manual review. It is appropriate when an agent requires a stable, size‑constrained conversation history for inference.
SKILL.md
Codex maintains a context (history of messages) that is sent to the model in inference requests.
- No history rewrite - the context must be built up incrementally.
- Avoid frequent changes to context that cause cache misses.
- No unbounded items - everything injected in the model context must have a bounded size and a hard cap.
- No items larger than 10K tokens.
- Highlight new individual items that can cross >1k tokens as P0. These need an additional manual review.
- All injected fragments must be defined as structs in
core/contextand implement ContextualUserFragment trait