OpenAI Codex — codex OpenAI's official coding agent product consisting of CLI / IDE extension / cloud.
Covers onboarding to CLI, IDE, and cloud; agent configuration via AGENTS.md/rules/subagents; config.toml/MCP configuration;
automation via approvals, sandbox, GitHub Action, and the Codex SDK; workspace administration;
vulnerability scanning and remediation with Codex Security; switching between cloud/local/worktree environments and turning skills into reusable form via Record & Replay;
and integration with GitHub, Linear, and Slack.
This skill is a distillation of the official OpenAI Codex documentation, and is separate from the Claude Code
.claude/ system that this repository targets.AGENTS.md / rules / subagents Although some terms overlap, such as
, the configuration file format, locations, and meanings are not compatible with Claude Code's CLAUDE.md / .claude/rules/ / .claude/agents/ (for details, see references/agent-configuration/README.md the introductory note in ).
Directory structure
skills/openai-codex/
SKILL.md
references/
getting-started/
README.md
cli.md
cli-customization.md
ide.md
windows-app.md
cloud.md
cloud-internet-access.md
remote.md
remote-connections.md
models.md
codex-micro.md
best-practices.md
agent-configuration/
README.md
agents-md.md
rules.md
hooks.md
speed.md
subagents.md
prompting.md
config/
README.md
config-basics.md
config-advanced.md
config-reference.md
config-sample.md
environment-variables.md
mcp-config.md
amazon-bedrock.md
security-automation/
README.md
agent-approvals-security.md
sandbox.md
permission-profiles.md
permission-modes.md
auto-review.md
windows-sandbox.md
windows-wsl.md
non-interactive-mode.md
github-action.md
codex-sdk.md
agents-sdk-mcp-server.md
administration/
README.md
administration.md
admin-rollout-guide.md
work-admin-faq.md
usage-limits.md
groups-and-provisioning.md
roles-and-workspace-permissions.md
access-tokens.md
analytics-api.md
compliance-api.md
governance.md
workspace-analytics.md
workspace-model-availability.md
plugin-controls.md
skill-controls.md
managed-configuration.md
manage-app-updates.md
windows-deployment.md
authentication.md
security/
README.md
overview.md
cloud-setup.md
cloud-faq.md
threat-model.md
plugin-quickstart.md
workbench.md
scans.md
deep-scans.md
code-changes.md
security-review.md
triage-backlog.md
fix-findings.md
export-findings.md
vulnerability-reports.md
security-hardening.md
plugin-changelog.md
cli-quickstart.md
cli-reference.md
cli-faq.md
cli-bulk-scans.md
cli-ci.md
sdk.md
environments/
README.md
cloud-environment.md
git-worktrees.md
local-environment.md
modes.md
extend/
README.md
record-and-replay.md
third-party/
README.md
github.md
linear.md
slack.md
samples/
README.md
follow-goals.md
github-code-reviews.md
codebase-onboarding.md
automation-bug-triage.md
slack-coding-tasks.md
reusable-codex-skills.md
refactor-your-codebase.md
code-migrations.md
update-documentation.md
agent-friendly-clis.md
verified-operations-workflows.md
ai-app-evals.md
scan-code-changes-for-security.md
deep-security-scan.md
remediate-vulnerability-backlog.md
dependency-incident-audits.md
ios-simulator-bug-debugging.md
scripts/
README.md
install.md
auth.md
cli-basics.md
automation.md
config.md
Exploration procedure
Derive the category from the task, and identify the target page in the category's README.md:
- Find the category corresponding to the task in the mapping table below
- That category's
references/{category}/README.mdRefer to to identify the target page - Read the target page's
.mdto check the details
Task → Category Mapping
| Task | Category | Reference README |
|---|---|---|
| Want to know how to onboard to Codex CLI / IDE extension / cloud and how they differ | getting-started | references/getting-started/README.md |
| Want to customize CLI output and aliases, or use it from the Windows desktop app or via remote connection | getting-started | references/getting-started/README.md |
| Want to know about model selection (including Codex Micro), reasoning effort, and best practices | getting-started | references/getting-started/README.md |
| Want to configure AGENTS.md / prompting / subagents workflows | agent-configuration | references/agent-configuration/README.md |
Want to allow commands that run outside the sandbox via rules (.rules / Starlark prefix_rule), or hook into the agent lifecycle with hooks |
agent-configuration | references/agent-configuration/README.md |
| Want to know about config.toml keys, profiles, MCP server configuration, and usage via Amazon Bedrock | config | references/config/README.md |
| Want to know the list of environment variables | config | references/config/README.md |
| Want to design approvals / sandbox / permission profiles / permission modes | security-automation | references/security-automation/README.md |
| Want to run codex exec automatically from CI/GitHub Action/Codex SDK, or configure the sandbox on Windows/WSL | security-automation | references/security-automation/README.md |
| Want to manage workspace roles / provisioning / analytics / compliance | administration | references/administration/README.md |
| Want to know about Enterprise rollout and access token operations | administration | references/administration/README.md |
| Want to perform vulnerability scanning, triage, and remediation of repositories (Codex Security), or conduct security review of PRs/diffs | security | references/security/README.md |
| Want to export detection results as SARIF/CSV/JSON, integrate with CI, and tune the threat model | security | references/security/README.md |
| Want to configure and switch between Cloud / Local / Worktree environments, and separate chats with git worktree | environments | references/environments/README.md |
| Want to record workflows and turn them into skills (Record & Replay) | extend | references/extend/README.md |
| I want to invoke Codex from GitHub / Linear / Slack | third-party | references/third-party/README.md |
| I want to know typical usage | samples | samples/README.md |
| I want to know installation and CLI commands | scripts | scripts/README.md |