القائمة
Teleport the current Claude Code session to the Everything Agent cloud for autonomous continuation. Use when a task will take a long time, the user wants to walk away, or they say "teleport this".
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | teleport |
| description | Teleport the current Claude Code session to the Everything Agent cloud for autonomous continuation. Use when a task will take a long time, the user wants to walk away, or they say "teleport this". |
You are teleporting this Claude Code session to the cloud. The Everything Agent will continue your work autonomously. Follow these steps exactly.
Write a JSON file at /tmp/teleport-briefing.json with this structure:
{
"goal": "<one sentence: what are we building/doing>",
"progress": "<summary of what's been accomplished so far>",
"decisions": ["<key decision 1 with WHY>", "..."],
"remaining": ["<specific remaining task 1>", "<specific remaining task 2>", "..."],
"context": "<any important context the cloud agent needs — blockers, gotchas, user preferences>"
}
Be thorough in remaining — list every concrete step the cloud agent should take. Be specific in decisions — include WHY each decision was made so the cloud agent doesn't re-litigate them.
git status for uncommitted changesgit add -Agit commit -m "teleport: WIP state for cloud continuation"base-branch)$CLAUDE_SESSION_IDgit checkout -b teleport/<id>git push origin teleport/<id>git checkout <original-branch>The session ID is available as $CLAUDE_SESSION_ID.
Run the teleport script:
npx tsx /Users/michael/ws/everything-monorepo/scripts/teleport.ts \
--session-id "$CLAUDE_SESSION_ID" \
--briefing /tmp/teleport-briefing.json \
--branch "teleport/<id>" \
--base-branch "<original-branch>" \
--project-dir "$(pwd)"
Required environment variables (check they're set before running):
TELEPORT_API_KEYTELEPORT_ORG_IDTELEPORT_PROJECT_IDTELEPORT_CREATOR_IDIf any are missing, tell the user which variables to set and stop.
After the script succeeds, tell the user:
If the script fails, show the error output and suggest fixes.
Remove the temporary briefing file:
rm -f /tmp/teleport-briefing.json
Michael's operating + emotional coach. Operational mode — daily startup/shutdown, weekly review, pomodoro, inbox capture, daily notes (auto-loads in ~/ws/notes). Emotional/decision mode (Joe Hudson style) — use on "coach me"/"joe coach", stuck/looping/overthinking, harsh self- or other-judgment, a binary either/or decision that won't resolve, or fear, shame, loneliness, anxiety, burnout, or grief, when Michael wants to be met in a feeling rather than handed advice. Not for clinical crises (refer out).
Use when creating or processing Todoist tasks, triaging inbox items, doing daily task review, calibrating Todoist triage behavior, or turning corrections into reusable preferences. Routes to operations (CLI actions) vs calibrated triage (policy, context recovery, preference memory, evals). Trigger this whenever the user asks what to do with Todoist items, wants better task triage, or is refining how Todoist decisions should work.
Run real Deep Research across ChatGPT, Claude, and Gemini in parallel via the user's own logged-in browser (Chrome extension, zero API cost), save each original report to Notion, then synthesize. Use whenever the user wants a "deep dive", "deep research", a thorough multi-source investigation, or to research a topic across the models and compare what each finds. Drives the paid subscription products, NOT the API. NOT for single-fact lookups or ordinary web search — use web-search for those.
Use when setting up, auditing, or improving AI agent infrastructure in a repo — AGENTS.md/CLAUDE.md files, linters, architectural constraints, feedback loops, context tiering, agent specialization, or entropy management. Also triggers on "harness engineering", "agent-friendly repo", "make my repo work well with coding agents", "set up my repo for agents", or "why is my agent struggling".
Interactive Todoist triage with preference learning. Use when the user says "triage", "process my inbox", "clean up tasks", "triage my todoist", "file these captures", or mentions inbox zero. Also use when the user has a batch of raw items (voice notes, links, ideas) that need classifying and routing to Todoist projects or Obsidian. Runs an interactive confirm/correct loop that learns your routing preferences over time.
Use when the user asks to save session context, identify the current session or thread, create a resumable handoff, or prepare a Todoist/note summary that must include the working directory and session id. Works across Codex and Claude Code by detecting runtime-specific session identifiers and normalizing them into one summary.