Handoff codex

Skill claude-world/director-mode-lite/skills/handoff-codex

Continue a task in OpenAI Codex CLI through a portable Director handoff packet. Use when the user asks Codex to take over, wants an independent Codex implementation or review, or needs to preserve decisions and verification while changing CLIs.From its SKILL.md

Install

npx -y skills add claude-world/director-mode-lite --skill handoff-codex

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

runs commandsInstructs the agent to run 2 commands, including `"$RELAY" create --from <claude|grok> --to codex --goal "..." --summary "..." --next "..."` and 1 more.

SKILL.md

1.4 KB, 303 tokens by cl100k_base, as published. Nobody here has run it

Handoff to Codex CLI

Use the shared session-relay workflow. Codex starts its own native session and reads a packet containing the goal, current state, decisions, Git evidence, verification, and next steps.

ROOT="${CLAUDE_PROJECT_DIR:-${GROK_WORKSPACE_ROOT:-}}"
[[ -n "$ROOT" ]] || ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
RELAY="$ROOT/.director-mode/bin/director-relay"
[[ -x "$RELAY" ]] || RELAY="$HOME/.claude/bin/director-relay"

"$RELAY" create \
  --from <claude|grok> --to codex \
  --goal "..." --summary "..." --next "..."

"$RELAY" continue --to codex

The second command prints the interactive codex invocation. Add --run only when the user wants it launched now. Use --headless when a one-shot codex exec continuation is appropriate.

Codex reads the repository's AGENTS.md, reusable skills from .agents/skills/, and generated agents from .codex/agents/. Confirm those surfaces with the installed CLI when debugging discovery.

Do not add bypass, approval, sandbox, or network flags as part of the handoff. Those controls belong to the Codex session and remain at their current native settings.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most agent orchestration skills give in 303 tokens

Counted across 848 of the 1,300 authors here whose files we hold, read 2026-09-06

Dispatch one agent per independent problem domainin 56 of 848, across 42 files
Run full test suite after integrationin 55 of 848, across 42 files
Verify fixes do not conflictin 40 of 848, across 32 files
Review each summary when agents returnin 40 of 848, across 31 files
Write a handoff document summarising the current conversationin 30 of 848, across 25 files
Reference existing artifacts by path or URLin 26 of 848, across 24 files
Give each agent a specific scopein 19 of 848, across 10 files
Give each agent a clear goalin 19 of 848, across 10 files
Include a suggested skills section in the documentin 18 of 848, across 16 files
Tailor the doc to the user argumentsin 18 of 848, across 15 files
Issue all subagent dispatches in the same responsein 17 of 848, across 11 files
Use git worktrees for isolationin 17 of 848, across 8 files

Said here and by no other author read

Use the shared session-relay workflow
Create the handoff packet using the relay binary
Continue the session targeting Codex
Confirm discovery surfaces with the CLI

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.