Community코딩 & 개발github.com

코드 리뷰 컨텍스트

모델이 추론 요청 시 사용하는 컨텍스트(메시지 기록)를 관리하는 방법에 대한 가이드라인

코드 리뷰 컨텍스트란 무엇인가요?

이 스킬은 Codex AI 에이전트가 추론 요청 시 모델에 전송되는 컨텍스트(메시지 기록)를 관리하는 원칙을 정의합니다. 컨텍스트는 증분 방식으로 구축되어야 하며, 이전 기록을 다시 작성할 수 없습니다. 컨텍스트를 자주 변경하면 캐시 미스가 발생할 수 있으므로 피해야 합니다. 모델 컨텍스트에 주입되는 모든 항목은 크기가 제한되어야 하며 하드 캡이 있어야 하고, 10K 토큰을 초과할 수 없습니다. 1K 토큰을 초과하는 개별 항목은 P0으로 표시되어 추가 수동 검토가 필요합니다. 모든 주입된 조각은 `core/context`에 구조체로 정의되고 `ContextualUserFragment` 트레이트를 구현해야 합니다. 이 가이드라인은 Codex 플랫폼에서 모델 컨텍스트의 효율성과 신뢰성을 보장합니다.

지원 대상~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/openai/codex/tree/main/.codex/skills/code-review-context

Installed? Explore more 코딩 & 개발 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

Codex는 모델에 대한 추론 요청 시 전송되는 컨텍스트(메시지 기록)를 유지합니다.

  1. 기록 재작성 금지 - 컨텍스트는 증분 방식으로 구축되어야 합니다.
  2. 캐시 미스를 유발하는 컨텍스트의 빈번한 변경을 피하십시오.
  3. 무제한 항목 금지 - 모델 컨텍스트에 주입되는 모든 항목은 크기가 제한되어야 하며 하드 캡이 있어야 합니다.
  4. 10K 토큰보다 큰 항목은 없어야 합니다.
  5. 1K 토큰을 초과하는 새로운 개별 항목을 P0으로 강조 표시하십시오. 이러한 항목은 추가 수동 검토가 필요합니다.
  6. 모든 주입된 조각은 core/context에 구조체로 정의되고 ContextualUserFragment 트레이트를 구현해야 합니다.

Individual skills in this repo

This repo contains 19 individual skills — each has its own dedicated page.

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

code-review

Run a final code review on a pull request

code-review-change-size

Change size guidance (800 lines)

code-review-testing

Test authoring guidance

codex-bug

Diagnose GitHub bug reports in openai/codex. Use when given a GitHub issue URL from openai/codex and asked to decide next steps such as verifying against the repo, requesting more info, or explaining why it is not a bug; follow any additional user-provided instructions.

codex-issue-digest

Run a GitHub issue digest for openai/codex by feature-area labels, all areas, and configurable time windows. Use when asked to summarize recent Codex bug reports or enhancement requests, especially for owner-specific labels such as tui, exec, app, or similar areas.

codex-pr-body

Update the title and body of one or more pull requests.

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

openai/babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

openai-docs

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

openai/test-tui

Guide for testing Codex TUI interactively

path-types

Choose Rust types for operating system paths across the Codex repository. Use when defining new path-bearing types or explicitly migrating existing ones.

plugin-creator

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.

pushing-ci-changes

Pushing GitHub Actions changes, resolving push rejection, requesting upload exceptions.

remote-tests

Testing against remote executors in integration tests.

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

skill-installer

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

test-tui

Guide for testing Codex TUI interactively

update-v8-version

Update Codex's pinned `v8` / `rusty_v8` versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update `rusty_v8` artifacts, prepare or validate a V8 release candidate, check `v8-canary`, or diagnose why a V8 version update no longer builds.

관련 스킬