---
name: deonmenezes-code-review-context
description: "Model visible context"
license: "Apache-2.0"
metadata:
  decimalai-skill-id: "dd0bb2c2-6e94-454a-85f9-db419cfa6820"
  decimalai-version-id: "83f5cd1e-bd79-40f3-b322-c3f37a21c77f"
  decimalai-version: "1"
  decimalai-body-sha256: "bdc1c638042c4df9bf6d97d495097cf29e8522da3cb015f4586cbabae5e26cf7"
  decimalai-name: "deonmenezes/code-review-context"
  decimalai-format: "1"
  decimalai-invocation: "model"
  decimalai-category: "agent-tooling"
  decimalai-source: "https://app.decimal.ai/s/deonmenezes-code-review-context@1/SKILL.md"
---
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.
6. All injected fragments must be defined as structs in `core/context` and implement ContextualUserFragment trait