Codex Delegate

You are the orchestrator. This skill lets you hand a bounded coding task to a separate implementer — the OpenAI Codex CLI — then review what it produced and land it yourself. You write the brief and own the judgment; Codex does the typing in its own sandbox; you verify and commit.

Nothing here is specific to one orchestrating agent. The loop needs only the ability to run a shell command and read a file, so it works the same whether you are Claude Code, OpenCode with a selected model, or any comparable agent. (It is designed for and run on Claude Code; treat other orchestrators as designed-for, not yet proven.)

When NOT to use this

The task is small enough to just do inline — delegation overhead is not worth it.
The
```
codex
```
CLI is not installed or not authenticated (run
```
codex login
```
).
You want to write the code yourself, or you only need a review (use Codex's own
```
review
```
command).

Prerequisites (check once)

codex --version

succeeds. If not, install (

npm i -g @openai/codex

) and

codex login

Confirm which
codex
is on PATH. Multiple installs are common (e.g. a current npm/nvm copy and a stale Homebrew one).
```
command -v codex
```
shows the active one and
```
codex --version
```
its version — an old binary predates flags this skill relies on (
```
codex exec --json
```
,
```
-o
```
,
```
exec resume
```
). The relay also records the version it ran into
```
result.json
```
, so a stale binary is visible after the fact.
You are in (or will point
```
--cd
```
at) the target git repository.

The loop

Run these five steps per task. Steps 1, 4, and 5 are your judgment; 2 and 3 are mechanical.

1. Write the brief

Codex sees only the text you send — no repo memory, no chat history, no shared context. Everything the task needs goes in the brief: the goal, the current state, what to change, what to leave untouched, the project's actual gate commands (discover them from the repo's CLAUDE.md/AGENTS.md/Makefile — do not assume), and a report contract. Tell Codex it will not commit (you will). Keep one task per brief. Full guidance and a template: references/writing-the-brief.md.

2. Dispatch

Send the brief to Codex with the bundled helper. It wraps

codex exec

, captures the run, and writes a structured

result.json

— so your only job is "run a command, read a file." (

<skill-dir>

below is this skill's installed directory — the folder containing this

SKILL.md

, i.e. the directory you loaded the skill from. Claude Code prints it as "Base directory for this skill" when the skill loads; on other orchestrators use that same directory — if unsure where it landed, run

find ~ -name relay.mjs -path '*codex-delegate*'

and substitute the directory above it.)

bash

node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo
# read-only (review/diagnosis, no edits):   add --read-only
# continue the exact Codex session:         add --session <threadId>  (from result.json; send only the delta brief)
# fallback when no thread id is available:  add --resume-last
# hard time limit (watchdog):               add --timeout 2h  (default: off; implementation runs routinely need 1-2h)
# so you can attach a watcher later:        add --out-dir .codex-runs/<task-slug>   (see step 3)
# see all options:                          node .../relay.mjs --help

The helper defaults to a write-capable (

workspace-write

) sandbox and writes its artifacts to a temp dir, so the repo under review stays clean. It never commits — see step 5. Mechanics, flags, and the

result.json

shape: references/dispatch-and-poll.md.

3. Watch it work, and wait for completion

A delegated run is not a black box. The relay renders one readable line per Codex event to stderr as it happens — messages, each command with its exit code, every file edit — so progress shows up wherever your orchestrator surfaces command output. Nothing to enable;

--no-stream

turns it off.

[    6s] ▸ I'll update `math.js` in place, then run the exact verification command.
[    9s] $ sed -n '1,200p' math.js && git status --short -- math.js
[    9s]   ✓ exit 0 · return a + b; }
[   12s] ✎ update math.js
[   16s] $ node -e "import('./math.js').then(m=>console.log(m.multiply(3,4)))"
[   16s]   ✓ exit 0 · result 12
[   18s] turn complete in 60558 · out 378 · cached 50176

Progress goes to stderr and the run summary to stdout, so a script parsing stdout is unaffected. Add

--stream-reasoning

for the model's reasoning summaries (verbose).

When the run is backgrounded, its stderr is somewhere you are not looking. Attach to it instead —

scripts/watch.mjs

renders the same view from the run's

events.jsonl

, live, and exits when

result.json

lands:

bash

node "<skill-dir>/scripts/watch.mjs" --dir <out-dir> --root /path/to/repo

This needs a known

--out-dir

on the dispatch — the default is a random temp directory that nothing can find afterwards. Pass one whenever you intend to watch (

--latest

then finds the newest run under

--runs-root

, default

./.codex-runs

Put the watcher on a screen, not in your context. A human watches it in a second pane; an orchestrator should not pipe it into the conversation. Platform recipes are in references/dispatch-and-poll.md —

tmux

works everywhere including headless boxes over SSH.

Then wait, using whatever your orchestrator offers:

Claude Code: run the Bash call with
```
run_in_background: true
```
; you are notified on completion, and the relay's stream is captured in the task's output file to read on demand. Do not point a
```
Monitor
```
at the watcher: Monitor turns every stdout line into a conversation message, and a normal run emits a line per command, so it floods the session. Monitor is for signals you would act on — if you want one, filter to those:
```
node .../watch.mjs --dir <d> | grep --line-buffered -E '✗|error|turn failed'
```
.
Plain shell / other agents: run it in the foreground for short tasks (you will see the stream directly), or background it and poll the result file —
```
… &
```
in bash/zsh (including Git Bash/WSL), or your shell's equivalent (
```
Start-Job
```
in PowerShell,
```
start /b
```
in cmd). The run is done when
```
result.json
```
exists with a
```
status
```
. (A pre-run usage error — bad args or an empty brief — instead exits with code 2 and a stderr message and writes no result file, so check the exit code too. A missing
```
codex
```
binary exits 127 but does write a
```
result.json
```
with status
```
codex_unavailable
```
.)

Watching is for visibility, not verification: the stream shows what Codex did, and step 4 still decides whether it was right.

Do not trust progress trackers over reality: a run is finished when

result.json

is written and the process has exited. Read the working tree, not a status line. The implementer's full report is the

finalMessage

field in

result.json

(also printed in full on stdout between the report markers).

4. Review — do not trust the self-report

Codex's

result.json

includes its own summary and gate claims. Re-verify, don't accept:

Re-run the project's gates yourself (the test/lint/build commands from step 1). Never take "gates passed" on faith.
Read the diff against the brief: did Codex do what was asked, nothing more (scope creep) and nothing less?
```
touchedFiles
```
in the result is your starting point.
Run the relevant guard skills on the diff if you have them installed (clean-code-guard, test-guard, etc. from
```
guard-skills
```
) — this skill produces the work; those skills judge it.
For schema/migration changes, round-trip them; for removals, grep for dangling references.

Full checklist: references/review-and-land.md.

5. Land it

Because Codex's sandbox cannot reliably write

.git

(it varies by version, OS, and path), the orchestrator commits. Only after the gates pass and the diff holds:

Commit the verified work yourself, with a clear message.
If it needs changes, send a delta brief with
```
--session <threadId>
```
from the prior
```
result.json
```
(use
```
--resume-last
```
only when no thread id is available), and review again.

Read-only second opinions

The relay doubles as a clean way to get an adversarial second opinion with no write risk: dispatch

--read-only

with a brief that lists the agreed points, then each contested point with both positions, and ask Codex to defend or concede each — deliverable in its final message, touching no files. Any delegation skill whose implementer offers a read-only mode supports the same use, but check how hard that mode's guarantee is first: Codex's sandbox enforces it, while Grok's is best-effort and only flagged after the fact (

readOnlyViolation

) — for those implementers, verify

touchedFiles

came back empty instead of assuming no edits.

Authorization model

Delegation is something the human opts into. Once they have ("run this queue", "proceed"), committing verified, gate-passing work is the agreed contract — that is the whole point. Two limits on that mandate: surface, don't absorb (report Codex's design decisions, defensible-but-unasked turns, and non-blocking nitpicks rather than silently keeping them) and stop for scope changes (if correct completion needs going beyond the brief, ask — don't expand the mandate yourself). The full treatment is in references/review-and-land.md.

If you have the openai-codex plugin

The official openai-codex Claude Code plugin is excellent and complementary —

codex-delegate

builds on the same

codex

CLI, it doesn't replace the plugin. They point in different directions:

The plugin's
```
codex:codex-rescue
```
agent is a forwarder: it hands one task to Codex and returns the output. It deliberately does not poll, review, or commit.
The plugin's review command and stop-review gate run the inverse direction: Codex reviews your work.
```
codex-delegate
```
is the orchestration loop in the other direction: you drive Codex to implement across one task or a queue, and you review and land each result. That loop — brief → dispatch → poll → review → commit, with the orchestrator owning the commit — is what the plugin leaves to you, and what this skill encodes.

If you have the plugin installed, its companion CLI is an optional alternative dispatch backend; the bundled

relay.mjs

is the default because it adds no install of its own beyond the

codex

binary (Node and

git

, which the relay also needs, are prerequisites for every skill here).

References

references/writing-the-brief.md — how to write a brief Codex can execute blind: structure, XML blocks, the report contract, embedding the real gate commands.
references/dispatch-and-poll.md —
```
relay.mjs
```
flags, the
```
result.json
```
contract, the live progress stream and
```
watch.mjs
```
, backgrounding per orchestrator, and recovery when a run misbehaves.
references/review-and-land.md — the review checklist, the commit boundary, and the exact-session rework cycle.
references/multi-task-queues.md — running a sequential queue: carrying constraints forward, progress tracking, and the end-of-run coherence check.

codex-delegate

NPX Install

Tags

SKILL.md Content