Skill
code-review-context
Model visible context
Install
git clone https://github.com/openai/codex /tmp/codex && ln -s /tmp/codex/.codex/skills/code-review-context ~/.claude/skills/code-review-contextFrom README
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/context and implement ContextualUserFragment trait