Migrate To Codex
OpenAIOfficialPublished by OpenAI
- Skill
- Workflow
- Automation and integrations
- Apache-2.0
- Low risk
- Has scripts
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The migrate-to-codex skill provides a structured, automated procedure to migrate existing Claude Code setups into the Codex ecosystem. It handles the conversion of instruction files, slash commands, skills, agents, and MCP server configurations. The tool follows a rigorous process involving scanning, planning, dry-running, and validating the migration to ensure artifacts are correctly mapped while preserving project-specific configurations. It includes a self-healing loop to resolve manual migration requirements and ensures that generated Codex artifacts are validated against target standards.
What it does
- Converts Claude Code instruction files into Codex-compatible formats.
- Migrates slash commands and skills into the Codex skill structure.
- Updates MCP server configurations for use in Codex.
- Generates a migration report detailing added items and manual review requirements.
- Validates generated Codex artifacts to ensure configuration integrity.
- Provides a dry-run mode to preview changes before applying them.
When to use it
- When transitioning a development environment from Claude Code to Codex.
- When you need to port custom skills or agents to a new Codex project.
- When updating global or project-level configurations to align with Codex standards.
- When you need to verify the readiness of existing Claude artifacts for Codex.
Advantages
- Automates complex migration steps, reducing manual effort.
- Provides clear reporting on what was successfully migrated and what requires manual attention.
- Includes a self-healing loop to iteratively resolve migration issues.
- Ensures project-specific configurations are preserved during the transition.
- Validates targets post-migration to prevent configuration errors.
Usage examples
- “Run a scan to see what Claude artifacts are available for migration.”
- The tool lists active and inactive source surfaces from the specified Claude directory.
- “Perform a dry-run migration of my project settings to Codex.”
- The tool generates a plan and reports potential changes without modifying any files.
- “Execute the full migration of my global Claude configuration to Codex.”
- The tool migrates instructions, skills, and MCP configs, creating a report of the results.
- “Validate the Codex target after my migration.”
- The tool checks the generated Codex files for errors and reports any remaining manual fixes.
Install
Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/openai/migrate-to-codex/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip migrate-to-codex.zip -d .agents/skills
Documentation by OpenAI
Migrate to Codex
Autonomy
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.
Migration Order
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.mdor any TODO file unless the user explicitly asks. The TODO list input has aplanarray whose items each havestepandstatus; use statusespending,in_progress, andcompleted. Make the TODOs specific to the selected artifacts. Before finishing, update the TODO list so every finished step is markedcompletedand no step remainsin_progress. Use literal source → Codex target labels, for example:Inspect
.claude/commands→ Codex skills/promptsInspect
.claude/agents→.codex/agentsInspect
.mcp.json→.codex/config.tomlMCP serversInspect
.claude/settings.jsonhooks →.codex/hooks.jsonMigrate safe selected artifacts → Codex files
Validate generated
.codex/config.tomlValidate generated
.codex/agentsReport migrated artifacts and manual-review items
Read
references/differences.md(and refresh Codex docs if itsDocs last checkeddate is old).Scan and inspect before writing:
--scan-onlylists active and inactive source surfaces.--planprints staged Codex artifact paths and report rows.--doctorsummarizes readiness, manual-review work, and validation risks.
Convert surfaces in the same order the CLI uses:
instructions:
CLAUDE.md/AGENTS.mdtoAGENTS.mdplugins: report Claude plugin trees and marketplaces as manual migration work
hooks: rewrite supported Claude hooks into
.codex/hooks.jsonand enable[features].codex_hooks = trueskills and commands: write Codex skills under
.agents/skills/config: write
.codex/config.tomlfrom Claude model/sandbox settings and MCP servers, includingpersonality = "friendly"when config is generatedsubagents: write Codex custom agents under
.codex/agents/
Dry-run, then write the selected target. Use
--replaceonly when orphan generated skills or agents should be deleted.Inspect the terminal output and
.codex/migrate-to-codex-report.txtafter 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-targetagainst each target after edits.Re-run checks and
--dry-runafter 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.
If only one scope has rows, render only the table with no heading. If multiple scopes have rows, render one heading before each table. Use
**User Config**for user-scope rows. For project-scope rows, use the actual project folder name as the heading, for example**northstar-support-portal**; do not useCurrent Projectas the heading. Do not add prose before or after the table output.Use exactly these columns:
northstar-support-portal
Status Item Notes AddedSlash commandpr-reviewConverted into a Codex skill AddedSubagentrelease-leadAdded as a Codex subagent Check before usingHookPreToolUseConverted, but some Claude hook behavior differs in Codex Not AddedHookNotificationCodex does not have an equivalent notification hook Not AddedPluginteam-macrosPlugin needs manual setup Statusmust beAdded,Check before using, orNot Added. UseAddedwhen a Codex-facing artifact was created or changed and needs no special review. UseCheck before usingwhen a Codex-facing artifact was created or changed but the migration changed semantics, inferred behavior, preserved tool rules as guidance, or dropped unsupported behavior. UseNot Addedwhen a source artifact was detected but no Codex-facing artifact was created.Itemcombines the artifact type and concrete item name in one cell. Artifact type must be singular:Skill,Slash command,Subagent,MCP,Hook, orPlugin. Wrap the artifact type in inline code; write the item name as plain text after it.Notesis always required; never leave it empty. Keep notes short, plain, and literal. Avoid internal implementation terms such as runtime expansion. Prefer phrases likeConverted into a Codex skill,Added as a Codex subagent,Added to Codex config,Converted into a Codex hook,Converted, but some Claude hook behavior differs in Codex,Codex does not have an equivalent notification hook,Plugin needs manual setup, orPlugin marketplace needs manual setup.
Self-Healing Loop
Keep looping until the selected migration is complete:
Run
--planor--doctor.Run the migration with
--dry-run.Run the migration for real.
Fix every generated
## MANUAL MIGRATION REQUIREDblock and everymanual_fix_requiredorskippedreport row that can be resolved inside Codex artifacts.Run
--validate-target.Re-run the migrator and validator until the report and validator have no actionable generated-artifact fixes left.
Do not edit source Claude Code files, unrelated project code, secrets, or another repository during this loop. If a report row requires source-provider changes or product judgment, leave the generated Codex artifact with clear manual guidance instead of changing the source.
Commands
Choose the migrator command.
MIGRATE_TO_CODEX='python3 .codex/skills/migrate-to-codex/scripts/migrate-to-codex.py'Inspect the migration before writing.
$MIGRATE_TO_CODEX --source ~/.claude/ --scan-only
$MIGRATE_TO_CODEX --source ~/.claude/ --target ~/.codex/ --plan
$MIGRATE_TO_CODEX --source ~/.claude/ --target ~/.codex/ --doctorDry-run, then run without --dry-run, for global and project.
$MIGRATE_TO_CODEX --source ~/.claude/ --target ~/.codex/ --dry-run
$MIGRATE_TO_CODEX --source ~/.claude/ --target ~/.codex/
$MIGRATE_TO_CODEX --source ./.claude/ --target ./.codex/ --dry-run
$MIGRATE_TO_CODEX --source ./.claude/ --target ./.codex/Run the post-migration validator against each target after edits.
$MIGRATE_TO_CODEX --validate-target ~/.codex/
$MIGRATE_TO_CODEX --validate-target ./.codex/Run $MIGRATE_TO_CODEX --help for flags (--scan-only, --plan, --doctor, --validate-target, defaults, and so on). Deep tables and more links are in references/differences.md.
Files
- ATTRIBUTION.mdAdded by AutoGineer890 B
- LICENSE.txt11.1 KiB
- SKILL.md7.8 KiB
- agents/openai.yaml144 B
- references/differences.md13.4 KiB
- scripts/cli.pyScript29.4 KiB
- scripts/migrate-to-codex.pyScript208 B
- scripts/migrate/__init__.pyScript285 B
- scripts/migrate/agents.pyScript9.8 KiB
- scripts/migrate/codex_config.pyScript3.9 KiB
- scripts/migrate/common.pyScript11.2 KiB
- scripts/migrate/hooks.pyScript8.0 KiB
- scripts/migrate/instructions.pyScript2.4 KiB
- scripts/migrate/mcps.pyScript6.9 KiB
- scripts/migrate/plugins.pyScript660 B
- scripts/migrate/settings.pyScript1.0 KiB
- scripts/migrate/skills.pyScript12.3 KiB
- scripts/utils/__init__.pyScript35 B
- scripts/utils/scan.pyScript4.3 KiB
- scripts/utils/util.pyScript9.2 KiB
scripts/migrate/hooks.py
"""Convert supported Claude Code hooks into Codex hook config."""
from __future__ import annotations
import json
from collections.abc import Mapping, Sequence
from dataclasses import dataclass
from pathlib import Path
from migrate.common import (
ConversionResult,
GeneratedText,
MigrationReportItem,
PlannedArtifact,
ScopePaths,
json_object,
json_string,
path_exists_with_exact_case,
read_json_mapping_file,
)
from migrate.settings import CLAUDE_SETTINGS_JSON_RELATIVE
CODEX_HOOKS_PATH = Path(".codex") / "hooks.json"
CODEX_HOOK_EVENTS = (
"PreToolUse",
"PostToolUse",
"SessionStart",
"UserPromptSubmit",
"Stop",
)
CODEX_HOOK_MATCHER_EVENTS = frozenset(("PreToolUse", "PostToolUse", "SessionStart"))
@dataclass(frozen=True)
class ClaudeHookCommand:
command: str
timeout_sec: int | None = None
status_message: str | None = None
@classmethod
def from_mapping(cls, hook_config: Mapping[str, object]) -> ClaudeHookCommand | None:
command = json_string(hook_config.get("command"))
if command is None or not command.strip():
return None
timeout_value = hook_config.get("timeout")
if timeout_value is None:
timeout_value = hook_config.get("timeoutSec")
return cls(
command=command,
timeout_sec=json_int(timeout_value),
status_message=json_string(hook_config.get("statusMessage")),
)
def to_mapping(self) -> dict[str, object]:
result: dict[str, object] = {
"type": "command",
"command": self.command,
}
if self.timeout_sec is not None:
result["timeout"] = self.timeout_sec
if self.status_message is not None:
result["statusMessage"] = self.status_message
return result
@dataclass(frozen=True)
class ClaudeHookMatcherGroup:
event_name: str
matcher: str | None
hooks: tuple[ClaudeHookCommand, ...]
def to_mapping(self) -> dict[str, object]:
result: dict[str, object] = {
"hooks": [hook.to_mapping() for hook in self.hooks],
}
if self.matcher is not None:
result["matcher"] = self.matcher
return result
@dataclass(frozen=True)
class ClaudeHooks:
matcher_groups: tuple[ClaudeHookMatcherGroup, ...] = ()
source_paths: tuple[Path, ...] = ()
unsupported_fields: tuple[str, ...] = ()
@classmethod
def from_scope(cls, scope_root: Path) -> ClaudeHooks:
hook_sets = [
cls.from_settings_mapping(relative_path, outcome.data)
for relative_path in CLAUDE_SETTINGS_JSON_RELATIVE
if path_exists_with_exact_case(scope_root / relative_path)
for outcome in (read_json_mapping_file(scope_root / relative_path),)
if outcome.exists and outcome.ok
]
return cls(
matcher_groups=tuple(
matcher_group
for hook_set in hook_sets
for matcher_group in hook_set.matcher_groups
),
source_paths=tuple(
source_path
for hook_set in hook_sets
for source_path in hook_set.source_paths
),
unsupported_fields=tuple(
unsupported_field
for hook_set in hook_sets
for unsupported_field in hook_set.unsupported_fields
),
)
@classmethod
def from_settings_mapping(
cls,
relative_path: Path,
settings: Mapping[str, object],
) -> ClaudeHooks:
hooks_config = json_object(settings.get("hooks"))
if not hooks_config:
return cls()
matcher_groups: list[ClaudeHookMatcherGroup] = []
unsupported_fields: list[str] = []
for event_name, groups_value in hooks_config.items():
if event_name not in CODEX_HOOK_EVENTS:
unsupported_fields.append(f"hooks.{event_name}")
continue
for group_config in json_object_tuple(groups_value):
matcher = json_string(group_config.get("matcher"))
if matcher is not None and event_name not in CODEX_HOOK_MATCHER_EVENTS:
unsupported_fields.append(f"hooks.{event_name}.matcher")
matcher = None
if "if" in group_config:
unsupported_fields.append(f"hooks.{event_name}.if")
hook_commands: list[ClaudeHookCommand] = []
for hook_config in json_object_tuple(group_config.get("hooks")):
hook_type = json_string(hook_config.get("type")) or "command"
if hook_type != "command":
unsupported_fields.append(
f"hooks.{event_name}.hooks[].type:{hook_type}"
)
continue
if bool(hook_config.get("async")):
unsupported_fields.append(f"hooks.{event_name}.hooks[].async")
continue
hook_command = ClaudeHookCommand.from_mapping(hook_config)
if hook_command is None:
unsupported_fields.append(f"hooks.{event_name}.hooks[].command")
continue
hook_commands.append(hook_command)
if hook_commands:
matcher_groups.append(
ClaudeHookMatcherGroup(
event_name=event_name,
matcher=matcher,
hooks=tuple(hook_commands),
)
)
return cls(
matcher_groups=tuple(matcher_groups),
source_paths=(relative_path,),
unsupported_fields=tuple(sorted(set(unsupported_fields))),
)
def render_codex_file(self) -> str:
hooks_payload: dict[str, list[dict[str, object]]] = {}
for matcher_group in self.matcher_groups:
hooks_payload.setdefault(matcher_group.event_name, []).append(
matcher_group.to_mapping()
)
return json.dumps({"hooks": hooks_payload}, indent=2) + "\n"
def report_detail(self) -> str:
runtime_caveats = (
"Rewritten for Codex hooks; review behavior before relying on it. "
"Codex hooks require `[features].codex_hooks = true`, only execute "
"`command` handlers, skip `async` / `prompt` / `agent` handlers, ignore "
"`matcher` for `UserPromptSubmit` and `Stop`, and `PreToolUse` / "
"`PostToolUse` currently run for shell commands only."
)
if not self.unsupported_fields:
return runtime_caveats
return (
"Unsupported Claude hook fields need review: "
+ ", ".join(f"`{field_name}`" for field_name in self.unsupported_fields)
+ f". {runtime_caveats}"
)
def has_convertible_hooks(scope_root: Path) -> bool:
return bool(ClaudeHooks.from_scope(scope_root).matcher_groups)
def report_hooks(scope: ScopePaths) -> ConversionResult:
claude_hooks = ClaudeHooks.from_scope(scope.source)
if not claude_hooks.matcher_groups:
return ConversionResult()
return ConversionResult(
artifacts=[
PlannedArtifact(
relative_path=CODEX_HOOKS_PATH,
payload=GeneratedText(claude_hooks.render_codex_file()),
)
],
report_items=[
MigrationReportItem(
"rewritten",
CODEX_HOOKS_PATH,
claude_hooks.report_detail(),
)
],
)
def json_int(value: object) -> int | None:
if value is None or isinstance(value, bool):
return None
try:
return int(str(value))
except ValueError:
return None
def json_object_tuple(value: object) -> tuple[Mapping[str, object], ...]:
if isinstance(value, Sequence) and not isinstance(value, (str, bytes)):
return tuple(json_object(item) for item in value)
return ()
Requirements and compatibility
Written for: OpenAI Codex
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Needs: Needs an MCP server, Needs Python
Security
What our scanner noticed· Low risk
- Scripts that your agent may run
This skill includes scripts that your agent may run. Read them before you use it.
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Published by
- OpenAI
- Publisher
- OpenAI (Official)
- Source
- openai/skills · skills/.curated/migrate-to-codex · commit 49f948f
- Licence
- Apache License 2.0 (redistribution allowed)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by OpenAI.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download migrate-to-codex.zip