$ loading_
Migrate instruction files, skills, agents, and MCP configs into Codex files.
The material indicates this is essentially a prompt/instruction skill for migrating to Codex, with no required secrets, no declared remote endpoints, and an auditable open-source source with strong community adoption, so overall risk is low. The main caveat is that its README encourages high-autonomy modification of target configs and generated files, so practical impact depends on what file access the host agent is granted.
The material explicitly states there are no required secrets or environment variables, and the README does not ask for API keys, tokens, or other sensitive credentials. No credential collection, storage, or forwarding behavior is described, so exposure in this dimension is low.
Both the system checks and the material show no remote host endpoints, and the skill is prompt-only. While the README mentions possibly refreshing Codex docs, it does not declare fixed third-party egress endpoints or describe sending user data to external services.
As a prompt-based skill, it does not contain executable code, install scripts, or its own process-launching logic. Phrases such as 'run the migrator' and 're-run checks' are instructions to the host agent, not evidence that the skill itself has standalone code-execution capability.
The documented scope focuses on migration-related paths such as `AGENTS.md`, `.codex/`, `.agents/`, and `~/.codex/`, and it explicitly says not to edit `.claude/`, secrets, or unrelated code. As a skill artifact, it only defines intended file scope and does not itself grant read/write access or request excessive permissions.
The source is the open-source `openai/skills` repository on GitHub, with system-labeled open-source status and strong community adoption (~22k stars), providing good auditability and source credibility. The undeclared license and unknown maintenance state are minor uncertainties, but not enough on their own to raise this to high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "migrate-to-codex" skill from askskill: 1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/migrate-to-codex/SKILL.md 2. Save it as ~/.claude/skills/migrate-to-codex/SKILL.md 3. Reload skills and tell me it's ready
Keep going until the selected migration is completely done: run the migrator, inspect the report, fix migrated Codex instructions/skills/agents/MCP config, and re-run checks without stopping to ask for confirmation of the next step. If the user has selected a target, do not ask before creating, editing, replacing, or deleting generated Codex artifacts in that target (AGENTS.md, .codex/, .agents/, or ~/.codex/). Preserve unrelated existing Codex config entries in .codex/config.toml or ~/.codex/config.toml, such as notify, projects, marketplaces, or unrelated MCP servers; do not ask about them unless they fail validation or directly conflict with the migration. Do not edit source Claude Code files (.claude/, ~/.claude/, .mcp.json, or .claude.json), unrelated project code, secrets, or another repository.
Run the migration in this order for each selected global or project source:
Start by using Codex's built-in TODO/task list tool. Do not create MIGRATION_TODOS.md or any TODO file unless the user explicitly asks. The TODO list input has a plan array whose items each have step and status; use statuses pending, in_progress, and completed. Make the TODOs specific to the selected artifacts. Before finishing, update the TODO list so every finished step is marked completed and no step remains in_progress. Use literal source → Codex target labels, for example:
.claude/commands → Codex skills/prompts.claude/agents → .codex/agents.mcp.json → .codex/config.toml MCP servers.claude/settings.json hooks → .codex/hooks.json.codex/config.toml.codex/agentsRead references/differences.md (and refresh Codex docs if its Docs last checked date is old).
Scan and inspect before writing:
--scan-only lists active and inactive source surfaces.--plan prints staged Codex artifact paths and report rows.--doctor summarizes readiness, manual-review work, and validation risks.Convert surfaces in the same order the CLI uses:
CLAUDE.md / AGENTS.md to AGENTS.md.codex/hooks.json and enable [features].codex_hooks = true.agents/skills/.codex/config.toml from Claude model/sandbox settings and MCP servers, including personality = "friendly" when config is generated.codex/agents/Dry-run, then write the selected target. Use --replace only when orphan generated skills or agents should be deleted.
Inspect the terminal output and .codex/migrate-to-codex-report.txt after real runs.
Review generated artifacts in this order: AGENTS.md, .agents/skills/, .codex/config.toml, .codex/hooks.json, .codex/agents/, then report-only plugin items.
Run --validate-target against each target after edits.
Re-run checks and --dry-run after edits.
Return the final migration report as one markdown table per scope that has rows. The tables cover only the non-native follow-up migration work you performed, such as skills created from slash commands, subagents, MCP servers, hooks, unsupported/local plugin notes, and manual-review caveats. Include programmatic native import rows for config, instructions, skills, or supported plugins only if you personally migrated them in this follow-up run.
…
Turn Notion specs into implementation plans, tasks, and progress tracking.
Read, create, and review PDFs with layout-aware rendering and extraction tools.
Transcribe audio or video to text with optional speaker labeling.
Read, create, and update Linear issues, projects, and team workflows.
Deploy apps or websites to Vercel and generate live or preview links.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Integrate skills, MCP servers, and agent configs to strengthen coding agents.
Expose Agent Skills as MCP tools for coding agents to discover and activate instructions.
Install Codex skills from curated lists or GitHub repositories into your local environment.
Provides reusable agent skills for Codex and compatible automation workflows.
Generate or update chat customization files for AI coding agents.
Generate structured SKILL.md files on demand using a nine-phase skill guide.