跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

codex-exec

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\".

tobihagemann · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add tobihagemann/turbo --skill codex-exec

技能说明


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.

codex exec "task description" < /dev/null

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

cat context.txt | codex exec "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. Keep backticks and $ out of the quoted argument even in text you wrote, since both stay live inside it. Write the context file with the Write tool so nothing is interpreted on the way in.

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.

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:

codex exec "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 Bash 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 -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. 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:

codex exec -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.

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.

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. 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.

Permission Levels

LevelFlagWhen to Use
Read-only--sandbox read-onlyAnalysis, code reading, generating reports
Workspace write--sandbox workspace-writeEditing files within the project
Full access--sandbox danger-full-accessInstalling packages, running tests, system operations
Full auto--full-autoCombined with a sandbox level for unattended execution

Omitting --sandbox falls back to the codex config and project trust level (trusted projects run workspace-write), so always pass the flag explicitly.

For fix or implementation tasks, default to --sandbox workspace-write --full-auto so Codex can edit files without confirmation prompts. Use --sandbox read-only for analysis or research tasks.

Options

OptionDescription
-m <model>Model for the run
--full-autoAllow file edits without confirmation prompts
--sandbox <level>Permission
阅读完整来源 ↗