Codex Exec logo

Codex Exec

Community
boshu2
codex-exec

Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.

Overview

Publisherboshu2
Repositoryagentops
Skill namecodex-exec
Stars
450
Forks
42
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by boshu2 on GitHub. Read the source before you install it.

Installation

Install the Codex Exec AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/boshu2/agentops/tree/main/plugin/skills/codex-exec
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/boshu2/agentops.git /tmp/agentops
mkdir -p .claude/skills
cp -r /tmp/agentops/plugin/skills/codex-exec .claude/skills/codex-exec
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Codex Exec in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Codex Exec on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Codex Exec is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Codex Exec — one-shot runtime adapter

Run exactly one caller-supplied Codex prompt as one process and capture its result. This skill does not choose work, retry, validate or continue. One prompt, one process, one captured artifact keeps every output byte traceable to one invocation.

Rules that change the command

  • Sandbox from declared effects. -s read-only for review or analysis, workspace-write only for authorized edits, and network or wider access only when the caller explicitly requires those effects. "In case it needs it" is not a declared effect. A permission denial inside the run (EPERM or "Operation not permitted" from a socket bind, an OS permission check or a peer-credential probe) may show only what the chosen mode blocks; inside the sandbox it cannot show whether the host or the code would fail. Quote it and report the check as sandbox-limited under not run / not_checked: neither a pass nor a failed check. A host-side observation of the same probe still stands, and a host run is the caller's decision.
  • Close stdin. codex exec reads the prompt from stdin when no prompt argument is given, and appends piped stdin to a prompt argument. A non-TTY run (CI, a script) with an open stdin can wait forever: the stdin hang. Feed the prompt on stdin and let it end, or redirect </dev/null.
  • One deadline, never renewed. Fix one absolute deadline before the first attempt. Each invocation, including any retry the caller decides to make, gets only the time left before that deadline. A retry never gets a fresh budget: a loop that gives each attempt its own new timeout has silently multiplied the caller's bound. A missing, zero, negative or malformed bound prevents launch; an expired deadline stops before dispatch.
  • No retry here. Report a timeout, error or empty output as it is. Another invocation is the caller's decision, under the same deadline.
  • Capped capture, typed exit. Capture output to a file under a byte cap and report the exit status. A timeout is not a result.

Run it

In an AgentOps source checkout, use the guarded library. It enforces the deadline, the combined output cap (10 MiB default), process-group cleanup and echo detection:

bash
# DEADLINE_EPOCH: absolute Unix time fixed once by the caller and reused by
# every invocation in its scope.
. "$AGENTOPS_ROOT/scripts/lib/codex-exec.sh"
CODEX_EXEC_DIR="$WORKSPACE" CODEX_EXEC_SANDBOX=read-only \
CODEX_EXEC_PROMPT_FILE="$PROMPT_FILE" CODEX_EXEC_DEADLINE_EPOCH="$DEADLINE_EPOCH" \
CODEX_EXEC_MAX_OUTPUT_BYTES=10485760 CODEX_EXEC_OUT_FILE="$OUTPUT" \
  codex_exec_guarded </dev/null

An installed skill ships only this file, so scripts/lib/codex-exec.sh is absent outside a source checkout. Run codex exec directly instead (flags as of codex-cli 0.156.1; confirm with codex exec --help; on macOS, Homebrew coreutils may provide timeout only as gtimeout):

bash
remaining=$(( DEADLINE_EPOCH - $(date +%s) ))
[ "$remaining" -gt 0 ] || { echo "deadline passed; not launched" >&2; exit 124; }
timeout -k 10 "$remaining" \
  codex exec -C "$WORKSPACE" -s read-only - <"$PROMPT_FILE" 2>&1 \
  | head -c 10485760 >"$OUTPUT"
rc=${PIPESTATUS[0]}  # 124 timed out, 137 killed after grace, else codex's status

Add --skip-git-repo-check outside a Git repository and -o <file> to keep the final message separately (outside the cap). An output file exactly at the cap was truncated, and its status reflects the closed pipe, not a review. The fallback has no survivor check or echo detection; report both as not enforced.

Exit codes (guarded library)

ExitMeaning
0Codex completed and produced output
2precondition: binary missing, bounds invalid or missing, capability unavailable, or cleanup unverified; not a result
122descendants survived Codex's exit; degraded run
123capture or prompt-preparation cap reached; partial evidence kept
124deadline expired, or a clean exit with empty output; a stall, not a result
125output repeats the prompt; not a result
128+Ncancelled by signal N (129 HUP, 130 INT, 143 TERM)
otherCodex's own nonzero status, preserved

Reserved codes are runtime evidence, never a semantic verdict. Codex's own status can coincide with a reserved code; the runner's stderr diagnostic tells them apart. Guarded runner internals covers inputs, host requirements, process supervision and the external sandbox wrapper.

Report, then stop

text
command:  exact argv or library call (prompt by reference)
sandbox:  -s value and the declared effect that needs it
bound:    absolute deadline and seconds remaining at launch
capture:  output path, byte cap, truncated yes/no
exit:     status and its meaning from the table
cleanup:  library result, or "not enforced" for the direct fallback

A Codex validator follows the judgment receipt convention and the agent-native model-dispatch recipe: a requested model flag or the model's own description does not prove which model ran. Siblings: one headless Claude prompt is claude-exec, AGY is agy-native, and worker batches are agent-native.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Codex Exec AI skill do?

Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.

Why use Codex Exec on TypingMind?

Because you install it once and use it with any model. Codex Exec is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Codex Exec in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/boshu2/agentops/tree/main/plugin/skills/codex-exec. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Codex Exec?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Codex Exec?

As many as you like. As long as a model supports skills, you can use Codex Exec with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Codex Exec AI skill free?

Yes. It is published on GitHub by boshu2 under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇