# Codex Features and Practical Usage 🏛️ When you roll Codex out company-wide, leaving "which MCPs, models, and permissions are allowed" to each person is risky. Managed configuration lets admins draw the boundaries and enforce them. 🏷️ Title: Centralized Managed Configuration & Governance 🔗 URL: 📘 Overview Codex enterprise managed configuration lets IT admins control agent behavior across the whole organization from a central place. Allowed MCP servers, models, and approval/sandbox permissions are distributed as policy so that users cannot quietly step outside the approved boundaries. ⚙️ How It Works Management has two tiers: ・`requirements.toml`: admin-enforced constraints that users cannot override. ・`managed_config.toml`: starting defaults that users can still change during a session. Precedence, highest to lowest: macOS MDM preferences → cloud-managed requirements (ChatGPT Business/Enterprise) → system files (`/etc/codex/` or `%ProgramData%\OpenAI\Codex\`) → the user's `config.toml` → CLI overrides. Managed layers override CLI flags and are reapplied every session. Lockable settings include approval policies, sandbox modes (e.g. blocking `full_access`), an allowlist of permission profiles, MCP server approval (by command or URL — omitted servers are disabled), feature flags (such as `browser_use`), enforced automatic review, network domain allow/deny lists, lifecycle hooks, and command rules. 🛠️ Practical Usage For example, a `requirements.toml` can pin `allowed_approval_policies` and `allowed_sandbox_modes`, set `deny_read` for `~/.ssh` and `.env`, add a prefix rule forbidding `rm`, and register a single approved MCP server. This blocks `full_access`, denies reads of `~/.ssh` and `.env`, forbids `rm`, and enables only the approved MCP server. 💡 Use Cases You can hand every employee only the MCP servers and models you have approved, and uniformly block reading secret files or running destructive commands — governance that stays consistent without redeploying clients. ⚠️ Caveats Once `allowed_permission_profiles` is defined, it becomes the exclusive list; later sources must explicitly re-enable a profile to use it. Cloud requirements are cached locally, so offline sessions may not reflect the latest policy. Don't push custom profiles to clients running Codex 0.137.0 or earlier. For group-based rules the first matching group wins, and unset fields are not inherited from later groups — use explicit allowlists to combine policies. #Codex# #Enterprise#

Codex thread locking is a such a mess. You want to use a remote session from a computer *and* a phone? Sorry not possible. Why not let me take ownership of the thread instead of just... blocking me. This is awful UX. @Dimillian @ajambrosino @pvncher @reach_vb

Codex 🤝 AIFlow Your favorite coding agent, now powered by AIFlow. Connect through our API, access powerful AI models, and keep building without breaking the bank. No complicated setup. Just configure, code, and ship. Start building: 💜

Codex Plus plan is getting worse I came back to Codex after 2 weeks because Claude was giving me safety guardrails so I switched back to Codex to get some work done But in less than 15 minutes, I burned through: - 10% of my weekly usage - 60% of my 5-hour limit At this rate, my entire weekly allowance will be gone after just 1h hours I was using Astra Medium How is this even possible?

# Codex Features and Practical Usage ⚙️ Review the moment a PR opens, ship a scheduled report every morning — run Codex as a single workflow step and the automation lives entirely in CI. 🏷️ Title: Actions Execution (Codex GitHub Action) 🔗 URL: 📘 Overview The Codex GitHub Action (`openai/codex-action@v1`) is the official action for running Codex from GitHub Actions workflows. It installs the Codex CLI, configures API access, and runs `codex exec` for you, keeping code review, quality gates, and scheduled reports entirely inside CI. ⚙️ How It Works Store your OpenAI key as a GitHub secret (e.g. `OPENAI_API_KEY`) and check out the code before invoking the action. Key inputs: ・`prompt` / `prompt-file`: inline instructions or a prompt file in the repo (pick one). ・`model` / `effort`: choose the model and the work intensity. ・`sandbox`: `read-only` / `workspace-write` / `danger-full-access` control filesystem and network access. ・`codex-args`: extra CLI flags as a JSON array or shell string. ・`output-file`: save the final message to upload as an artifact. The `safety-strategy` input defaults to `drop-sudo` (irreversibly removes sudo); other options are `unprivileged-user` and `unsafe`, which Windows runners require. Results are exposed via the `final-message` output. 🛠️ Practical Usage A minimal review workflow triggers on `pull_request` (types `opened`, `synchronize`), checks out the code with `actions/checkout@v5`, then runs `openai/codex-action@v1` with `openai-api-key` from secrets, a `prompt-file`, and an `output-file`. To post the result as a PR comment, pass the `final-message` output to `actions/github-script` in a downstream job (which needs `pull-requests: write`). 💡 Use Cases Use `pull_request` triggers for review and quality gates, `schedule` (cron) for periodic reports, `workflow_dispatch` for manual runs, and `issue_comment` for comment-driven automation. ⚠️ Caveats You cannot supply both `prompt` and `prompt-file`. If you ingest PR titles or comments, guard against prompt injection and restrict to trusted events or explicit approvals. Keep `safety-strategy` on `drop-sudo` or an unprivileged user, and place the action at the end of the job to avoid inheriting state. After `drop-sudo` you may need to grant write access (e.g. `chmod -R g+rwX`). #Codex# #GitHubActions#

Codex 🤝 Tailscale Codex Cloud can now securely connect to resources on your tailnet with Tailscale. Useful tools should be easy to build with, combine, and turn into something even more useful. See how it works →