Agent skill

Codex Exec

by tobihagemann in tobihagemann/turbo

Run autonomous task execution using the codex CLI. An agent skill from tobihagemann/turbo.

MITAuto-check passedDevelopment

Install Codex Exec

skills CLI
$ npx skills add tobihagemann/turbo --skill codex-exec -a claude-code

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

GitHub CLI
$ gh skill install tobihagemann/turbo codex-exec --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/tobihagemann/turbo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude/skills/codex-exec .claude/skills/codex-exec && 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-exec
GitHub stars
407
Used in
1 other repo
Token cost
~2.4k tokens
SKILL.md length
1,330 words
Files
2 (incl. references)
Skills in repo
81
Repo updated
First seen
Licence
MIT

At a glance

Run autonomous task execution using the codex CLI. An agent skill from tobihagemann/turbo.

  • The user asks to codex exec
  • SKILL.md covers Sandbox, Git Repository Check, Stdin Gotcha and Synchronous Execution, plus 5 more sections
  • Calls codex
  • Execute a task with codex

What it does

Codex Exec is an agent skill from tobihagemann/turbo. Run autonomous task execution using the codex CLI. Use when the user asks to "codex exec", "run codex exec", "execute a task with codex", or "delegate to codex".

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/parallel-execution.md`).

It sits in Development. It works with Git. The repository describes itself as: Reusable workflows for planning, building, reviewing, and shipping with Claude Code and Codex. The licence is MIT.

When your agent uses it

  • The user asks to codex exec
  • Execute a task with codex
  • Delegate to codex

Example prompts

  • “codex exec”
  • “run codex exec”
  • “execute a task with codex”
  • “/codex-exec”

What it can do on your machine

Read from SKILL.md and the folder at commit 4b9f4cf. 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

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

  • Network

    No URLs in SKILL.md.

    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 Exec loads about 2.4k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 1,330 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

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

The full file from tobihagemann/turbo at commit 4b9f4cf, republished under its MIT licence (© tobihagemann). 1,330 words, ~2,381 tokens.

Download SKILL.mdSave it as .claude/skills/codex-exec/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
codex-exec
description
Run autonomous task execution using the codex CLI. Use when the user asks to "codex exec", "run codex exec", "execute a task with codex", or "delegate to codex".

Codex Exec

Autonomous task execution via the codex CLI. Runs non-interactively. Progress streams to stderr; final result on stdout.

bash
codex exec --skip-git-repo-check "task description" < /dev/null

For large context, pipe it via stdin. The prompt stays as the argument, context is passed as <stdin> automatically:

bash
cat context.txt | codex exec --skip-git-repo-check "question about the context"

Route text you did not author through this channel whatever its size — a diff, file contents, a code comment, a plan or spec, third-party feedback, command output. Write the context file with the Write tool so nothing is interpreted on the way in. Keep backticks, $, and straight double quotes out of the quoted argument even in text you wrote: the first two stay live inside it, and a double quote ends it. When the prompt itself must carry any of them, as when it quotes a title or a passage, write the whole prompt and its context to one file with the Write tool and pass -, so stdin is the entire prompt:

bash
cat prompt.txt | codex exec --skip-git-repo-check -

Sandbox

All codex Bash calls require dangerouslyDisableSandbox: true (network access to OpenAI API). Without it, codex crashes with an Operation not permitted panic from the system-configuration crate before the model runs.

Git Repository Check

Every codex exec invocation requires --skip-git-repo-check, resume turns included. Outside a git repository codex aborts before doing any work, printing Not inside a trusted directory and --skip-git-repo-check was not specified., and never writes the -o file.

Stdin Gotcha

Codex reads from stdin whenever stdin is non-TTY (per codex exec --help: "If stdin is piped and a prompt is also provided, stdin is appended as a <stdin> block"). In subagent and subprocess contexts the harness leaves stdin connected to a pipe that never EOFs, so a bare codex exec "..." hangs forever, printing only Reading additional input from stdin....

Always redirect stdin on non-piped invocations:

bash
codex exec --skip-git-repo-check "task description" < /dev/null

The piped form (cat context.txt | codex exec "...") is safe — cat closes the pipe after the file, sending EOF.

Synchronous Execution

Run codex via the Bash tool as a foreground call (do not set run_in_background). Set timeout: 600000, the foreground maximum. A larger value is not honored: the harness backgrounds the call immediately and hard-kills codex at 600s, truncating its output. Within a valid timeout, codex runs foreground and returns its result synchronously when it finishes in time.

Capture the session id: from the run's stderr chrome as it starts; it never appears in the -o file, and recovery depends on it. Do not pass --ephemeral when the run may need recovery, since it persists no session files.

Give every run its own absolute -o path, named with a random tag so that runs spawned concurrently and successive runs in an iteration loop cannot collide on a path each derived independently. Pass it absolute: a relative path resolves against a working directory that drifts over a session, so the run does its work and exits having written no final message (Failed to write last message file "<path>": No such file or directory). A reused path holds the prior run's complete output until the current run exits, so an early read returns well-formed output from the wrong run; a fresh path turns that same read into a detectable empty one. Treat content in the -o file as final only once the run has exited.

A run that outlives the timeout is normally force-backgrounded: the result carries a task ID and an output file path, and the run continues to completion. Recover it by reading the output file: Read the path, then Read it again once the <task-notification> reports completion.

Rarely the run is hard-killed instead, giving an error exit (code 143) reading Command timed out after <duration> with no task ID and no -o file. Do not re-run the prompt from scratch; that discards the work already done and hits the same ceiling. Resume the session with a fresh output path, asking for the findings as the final message rather than as a file write:

bash
codex exec --skip-git-repo-check -o <fresh-output-path> resume <session-id> \
  "Reply now with your complete findings as your final message." < /dev/null

resume inherits the original session's sandbox, so pass --sandbox only to change it. When the kill left no session id in hand, recover it from the newest ~/.codex/sessions/<YYYY>/<MM>/<DD>/rollout-<timestamp>-<session-id>.jsonl (the id is the UUID in the filename), listing a single day directory so the ordering is right. codex exec resume --last also works when no other codex run is in flight. Do not consult ~/.codex/session_index.jsonl; it lags behind the rollout files.

A run can also exit 0 within the timeout without completing the task, its final message asking for authorization to take an approach its own instructions require it to clear first. Read the final message before treating the run as finished: the exit code and the well-formed message both read as success. Resume the session with the authorization as the prompt, per the form above. Do not re-run the original prompt; it reaches the same gate.

Never wait with Monitor (it returns immediately, and events that arrive after your final text are dropped), and never return the task ID, an interim file snapshot, or "Waiting for codex to finish" as the result — each is a false-empty return.

Show full SKILL.md (503 more words)Show less

Transient Crash Retry

Re-run the command once when the Bash call returned an error exit with no stdout and no task ID. A timeout is not a crash: when the error text reads Command timed out after <duration>, resume the session per Synchronous Execution rather than re-running. An aborted git-repo check is not a crash either: when the error text reads Not inside a trusted directory and --skip-git-repo-check was not specified., add the flag per Git Repository Check and run again. Recover a force-backgrounded run per Synchronous Execution rather than retrying it. Keep the same prompt. Treat a second failure as final.

Treat models-manager and cache-TTL errors as non-fatal warnings. Read the error text for usage-limit and authentication signatures and report those without retrying.

Options

OptionDescription
-m <model>Model for the run
--sandbox read-onlyAnalysis, code reading, generating reports
--sandbox workspace-writeEditing files within the project
--sandbox danger-full-accessInstalling packages, running tests, system operations
--jsonJSON Lines output (progress + final message)
-o <path>Write final message to a file
--output-schema <path>Enforce JSON Schema on the output
--ephemeralNo persisted session files
--skip-git-repo-checkBypass git repository requirement

For fix or implementation tasks, default to --sandbox workspace-write so Codex can edit files. Use --sandbox read-only for analysis or research tasks. Pass --sandbox and no other permission flag. Omitting --sandbox falls back to the codex config and project trust level (trusted projects run workspace-write), so always pass the flag explicitly.

Omit -m, leaving the run on codex's configured model. When the user named a model for this run, add -m <model> to every codex exec command in this skill, resume turns included, and pass the name verbatim.

Prompt Shaping

Codex uses XML tags in its own context scaffolding, so the model parses them natively. Structure prompts with XML tags for clearer responses:

  • <task>: The concrete job and relevant context.
  • <structured_output_contract>: Required output shape, ordering, and format.
  • <compact_output_contract>: Same purpose but for concise prose responses.
  • <grounding_rules>: When claims must be evidence-based.
  • <dig_deeper_nudge>: Push past surface-level findings to check for second-order failures.
  • <verification_loop>: When correctness matters — ask Codex to verify before finalizing.

Instruct codex to carry out the task itself rather than delegating to a peer review or consultation skill that crosses back to Claude. The prompt has already crossed the tool boundary; a further crossing that fails mid-flight leaves this run holding a question instead of an answer.

Keep prompts compact, with tight output contracts. One clear task per exec call. For a large scope, instruct codex to report findings as it goes rather than verifying exhaustively before reporting, so a run that hits the timeout ceiling still yields usable output.

Parallel Execution

Codex supports parallel sub-agents via spawn_agent / wait_agent. The model will not fan out unless the prompt explicitly requests it. See references/parallel-execution.md for patterns and limitations.

Interpreting Results

  • Exec output is a starting point, not a guaranteed solution
  • Cross-reference suggestions with project documentation and conventions
  • Test incrementally rather than applying all changes at once
  • For file-editing tasks, always review the diff before committing

© tobihagemann, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in claude/skills/codex-exec of tobihagemann/turbo.

  • SKILL.md
  • references/parallel-execution.md

Open the folder on GitHubat commit 4b9f4cf

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in tobihagemann/turbo, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Codex Exec 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 Exec compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Exec this skilltobihagemann/turbo4071 repos~2.4kAutomated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything86k1 repos~1.2kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Codebase Knowledge Graph Q&A

    Egonex-AI/Understand-Anything

    Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.

    86k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check passed
  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • Understand Explain

    Egonex-AI/Understand-Anything

    Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.

    86k GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed

More from tobihagemann/turbo

All 81 skills in this repo
  • Consult Oracle

    tobihagemann/turbo

    Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.

    407 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Fetch PR Comments

    tobihagemann/turbo

    Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes.

    407 GitHub starsUsed in 1 repo~967 tokens
    Auto-check passed
  • Recall Rationale

    tobihagemann/turbo

    Recall why a past change was made by locating the Claude Code transcript that produced it.

    407 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Resolve PR Comments

    tobihagemann/turbo

    Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments.

    407 GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • Investigate

    tobihagemann/turbo

    Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps.

    407 GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed
  • Resolve PR Comments

    tobihagemann/turbo

    Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments.

    407 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Codex Exec

What does Codex Exec do?

Run autonomous task execution using the codex CLI. An agent skill from tobihagemann/turbo. Codex Exec is an agent skill from tobihagemann/turbo. Run autonomous task execution using the codex CLI.

When should I use Codex Exec?

Codex Exec fits situations like: the user asks to codex exec; execute a task with codex; delegate to codex.

How do I install Codex Exec in Claude Code?

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

How do I install Codex Exec in Codex?

Run `npx skills add tobihagemann/turbo --skill codex-exec -a codex`. Or copy the skill folder (claude/skills/codex-exec in tobihagemann/turbo) into .agents/skills/codex-exec in your project. Codex loads it when a task matches its description.

Can I use Codex Exec 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 tobihagemann/turbo --skill codex-exec -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-exec, .gemini/skills/codex-exec, .github/skills/codex-exec and .opencode/skills/codex-exec in your project.

What does Codex Exec need to run?

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

Does Codex Exec access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codex Exec 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 Exec use?

Codex Exec is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codex Exec use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 474 tokens, read only when the agent opens those files.

What are the alternatives to Codex Exec?

Skills that share tags, products or a category with Codex Exec: Finishing a Development Branch (obra/superpowers, 296k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 86k stars) and Code Design Rationale Investigator (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Exec?

tobihagemann (a GitHub user) maintains it in tobihagemann/turbo, which has 407 GitHub stars. The repository holds 81 skills in this directory. The repository was last updated on October 7, 2026.

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