Handoff claude

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

Continue a task in Claude Code through a portable Director handoff packet. Use when work started in Codex CLI or Grok Build should move to Claude, or when a fresh Claude session needs the current decisions and verification evidence.From its SKILL.md

Install

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

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 <codex|grok> --to claude --goal "..." --summary "..." --next "..."` and 1 more.

SKILL.md

1.4 KB, 305 tokens by cl100k_base, as published. Nobody here has run it

Handoff to Claude Code

Use the shared session-relay workflow. Claude starts a new native session and reads the same vendor-neutral packet used by Codex and Grok.

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 <codex|grok> --to claude \
  --goal "..." --summary "..." --next "..."

"$RELAY" continue --to claude

The second command only prints the interactive command. Add --run when the user explicitly wants to launch it, or --headless for a one-shot claude -p continuation.

Claude Code's own --continue and --resume remain the right tools for resuming a Claude-native history. Use a Director packet when the source is another CLI, when a concise checkpoint is preferable, or when the workflow may later move again.

Profiles created with CLAUDE_CONFIG_DIR can still isolate authorized Claude accounts, but profile credentials, permissions, plugins, MCP configuration, and session histories are not copied into the packet.

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 305 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 a director relay create command
Run director relay continue to resume

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.