Agent skills for OpenAI Agents SDK

Create and install Codex multi-agent roles and configs with safe minimal-change updates.

Delegates complex coding, browser research, and code review tasks to independent Codex CLI sessions for enhanced multi-tasking.

Diagnose GitHub bug reports in openai/codex.

Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including…

Code review via Codex CLI with full disk access.

Code review using Codex MCP. Use when: PR review, code audit, second opinion on changes. Not for: doc review (use doc-review), security…

Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.

Coordinate GitHub Issue dependency graphs specifically for Codex delivery across independent Codex sessions and session-local Codex…

Codex debugging: codex-rs core/tui/exec/cli/app-server/config.

Diagnose OpenAI Codex CLI, Desktop, IDE, skill, plugin, MCP, session, configuration, authentication, network, storage, and performance…

Claude Code-only work routing: delegate implementation, fixing, exploratory subagents, rebasing, and PR merging/landing to Codex CLI while…

Navigates Codex specifications and validates execution policies using official documentation and live command testing.

Monitor already-submitted long-running Slurm jobs from Codex with a detached deterministic read-only supervisor, optional event-driven…

Codex 1M context: direct OpenAI Responses API inference, safe Sol/Terra/Luna input headroom, Keychain delivery, and Mac fleet rollout.

Implement features via Codex exec. Use when: writing new code from specs, implementing features, Codex-driven development. Not for: code…

Ask Codex CLI (gpt-5.6-sol) to implement scoped code changes in the current repository, then have Claude inspect the resulting diff and…

Run a GitHub issue digest for openai/codex by feature-area labels, all areas, and configurable time windows.

Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default.

Monitor long-running commands, asynchronous artifacts, callbacks, dispatched Codex work, and Slurm jobs with detached deterministic…

Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.

Orchestrate implementation, orchestration complete: route work among the Codex primary task, disposable in-thread subagents, and…