Agent skill

Codex CLI

by kortix-ai in kortix-ai/suna

Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code.

Custom licenceAuto-check passedAgent Workflows

Install Codex CLI

skills CLI
$ npx skills add kortix-ai/suna --skill codex-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kortix-ai/suna codex-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kortix-ai/suna.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/codex-cli .claude/skills/codex-cli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codex-cli
GitHub stars
20k
Token cost
~1.6k tokens
SKILL.md length
741 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
Custom licence

At a glance

Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code.

  • Works in 5 steps: Delegate — codex exec ... -o 2>>. → Capture — read (and /--json if you need… → Verify INDEPENDENTLY — do not trust… → …
  • Tasks that involve Subagents
  • Calls codex, git and openssl
  • Tasks that involve Git worktrees

What it does

Codex CLI is an agent skill from kortix-ai/suna. Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code. Load WHENEVER you want to delegate a coding/analysis/refactor task to Codex, get a second opinion / adversarial review from another model, fan out parallel agents across files or worktrees, or run a long mechanical job while you stay the planner. Covers the exact codex exec flags, sandbox tiers, output capture, JSON/schema modes, session resume, parallel fan-out, and the mandatory "delegate → capture →…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents, Git worktrees and Refactoring. It works with OpenAI. The repository describes itself as: The open-source AI Operating System.

When your agent uses it

  • Tasks that involve Subagents
  • Tasks that involve Git worktrees
  • Tasks that involve Refactoring

Example prompts

  • “delegate → capture → independently verify, never trust the self-report”
  • “/codex-cli”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Delegate — codex exec ... -o 2>>.
  2. Capture — read (and /--json if you need detail).
  3. Verify INDEPENDENTLY — do not trust Codex's "tests pass" / "done"
  4. Iterate — if wrong, codex exec resume --last "" and repeat.
  5. Report — tell the user what changed, what you verified, and how. State

What it can do on your machine

Read from SKILL.md and the folder at commit 0d0613a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • codex
    • git
    • openssl
    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex CLI loads about 1.6k tokens when it runs. Until then it costs about 147 tokens; SKILL.md has 741 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~147
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 741 words (~1,582 tokens).

“Codex CLI is OpenAI's terminal coding agent (Rust). Its non-interactive mode, codex exec, makes it a perfect disposable sub-agent: you write the metaprompt, Codex explores/edits/runs commands on its own, and returns a final message you capture and verify. You stay…”

— opening of SKILL.md by kortix-ai, Custom licence
name
codex-cli

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/codex-cli of kortix-ai/suna.

Open the folder on GitHubat commit 0d0613a

Compare with similar skills

Codex CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codex CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex CLI this skillkortix-ai/suna20k—~1.6kAutomated safety check: PassCustom licence
Subagent Coordinatorflyxl/datazen114—~908Automated safety check: PassGPL-3.0
Batch Orchestrationrohitg00/pro-workflow2.9k—~1.2kAutomated safety check: PassNone
Codex CLIsundial-org/awesome-openclaw-skills663—~2kAutomated safety check: PassNone
Audit Depsgarfiec/Librechat-Mobile110—~2.4kAutomated safety check: NotesMIT
Local Codexdaymade/claude-code-skills1.4k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Orchestrate multi-track parallel feature development with subagents and git worktrees.

    114 GitHub stars~908 tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Batch Orchestration

    rohitg00/pro-workflow

    Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees.

    2.9k GitHub stars~1.2k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Codex CLI

    sundial-org/awesome-openclaw-skills

    Use OpenAI Codex CLI for coding tasks. An agent skill from sundial-org/awesome-openclaw-skills.

    663 GitHub stars~2k tokensUpdated 7 mo ago
    DevelopmentAuto-check passed
  • Audit Deps

    garfiec/Librechat-Mobile

    Audit open dependabot PRs in this repo. An agent skill from garfiec/Librechat-Mobile.

    110 GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check: notes
  • Local Codex

    daymade/claude-code-skills

    Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT Pro OAuth, never API keys.

    1.4k GitHub stars~1.6k tokensUpdated today
    Backend & APIsAuto-check passed
  • Antigravity Agents

    markfulton/claude-antigravity-agents

    Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work.

    130 GitHub stars~2.1k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

More from kortix-ai/suna

All 20 skills in this repo
  • Ponytail Review

    kortix-ai/suna

    Code review focused exclusively on over-engineering. An agent skill from kortix-ai/suna.

    20k GitHub starsUsed in 4 repos~593 tokens
    Auto-check passed
  • E2E

    kortix-ai/suna

    Agentic end-to-end tests with e2e, the e2e runner. An agent skill from kortix-ai/suna.

    20k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Kortix Brand

    kortix-ai/suna

    Load FIRST for anything that carries the Kortix look or voice: product or mobile UI, copy of any kind, decks, social, images, email, CLI output, anything with the logo, and reviews of these.

    20k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Testing

    kortix-ai/suna

    A skill your agent uses for every Kortix test task, behavior change, bug fix, refactor, API route change, CLI change, SDK change, browser journey, test failure, coverage question, local benchmark…

    20k GitHub stars~3.6k tokensUpdated today
    Auto-check: notes
  • Contributing

    kortix-ai/suna

    The pull request loop for this repo: branch → commit → verify in your own box (local tests + local stack) → PR into main → demo video recorded with agent-browser on the local stack → gh --attach →…

    20k GitHub stars~3k tokensUpdated today
    Auto-check: warnings
  • Claude Code

    kortix-ai/suna

    Drive Anthropic's Claude Code CLI (claude -p) as a non-interactive coding sub-agent from inside Codex.

    20k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Works with

Questions about Codex CLI

What does Codex CLI do?

Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code. Codex CLI is an agent skill from kortix-ai/suna. Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code.

When should I use Codex CLI?

Codex CLI fits situations like: tasks that involve Subagents; tasks that involve Git worktrees; tasks that involve Refactoring.

How do I install Codex CLI in Claude Code?

Run `npx skills add kortix-ai/suna --skill codex-cli -a claude-code`. Or copy the skill folder (.agents/skills/codex-cli in kortix-ai/suna) into .claude/skills/codex-cli in your project. Claude Code loads it when a task matches its description.

How do I install Codex CLI in Codex?

Run `npx skills add kortix-ai/suna --skill codex-cli -a codex`. Or copy the skill folder (.agents/skills/codex-cli in kortix-ai/suna) into .agents/skills/codex-cli in your project. Codex loads it when a task matches its description.

Can I use Codex CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kortix-ai/suna --skill codex-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-cli, .gemini/skills/codex-cli, .github/skills/codex-cli and .opencode/skills/codex-cli in your project.

What does Codex CLI need to run?

Going by SKILL.md and its folder, Codex CLI needs the command-line tools its instructions call (codex, git, openssl and pnpm).

Does Codex CLI access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Codex CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Codex CLI use?

Codex CLI has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Codex CLI use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Codex CLI?

Skills that share tags, products or a category with Codex CLI: Subagent Coordinator (flyxl/datazen, 114 stars), Batch Orchestration (rohitg00/pro-workflow, 2.9k stars), Codex CLI (sundial-org/awesome-openclaw-skills, 663 stars) and Audit Deps (garfiec/Librechat-Mobile, 110 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex CLI?

kortix-ai (a GitHub organization) maintains it in kortix-ai/suna, which has 20,256 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 7, 2026.

Source: kortix-ai/suna on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.