# Handoff

> Compact the current conversation into a handoff document for another agent to pick up.

- Skill: `borkweb/handoff` (Agent Skill)
- Install (CLI): `npx skillmds@latest add borkweb/handoff`
- Raw SKILL.md: https://api.skillmd.com/api/skills/borkweb/handoff/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: borkweb (https://skillmd.com/u/borkweb)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/borkweb/handoff

---


Write a handoff document summarising the current conversation so a fresh agent can continue the work. Create the target path with `f=$(mktemp -t handoff) && mv "$f" "$f.md" && echo "$f.md"` so it ends in `.md` on both macOS and Linux (read the file before you write to it).

If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.

For complete/handoff workflows, the default receiving session is a **Codex
orchestrator**, which delegates work to **`gpt-5.6-luna`** subagents. Preserve
that role split under **Key context**, together with any explicit user override.
Writing this document does not itself launch a worker or change the parent model.
When continuing a complete run, include its ledger and per-slice result paths
under **Pointers**, and preserve authorization, frozen gates, unresolved rulings,
and agent IDs needed to resume. The receiving Codex must verify agent liveness;
an ID from a previous session is not proof that a worker is still running.

## Document structure

The handoff is read by another agent, so its shape is fixed. Produce exactly these eight sections, in this order, with these headings verbatim. Lead with intent and next steps, not narrative history — a fresh agent should scan top to bottom and start working.

1. `# Handoff: <short title>` — one line naming the work.
2. `## Goal` — what the next session is trying to accomplish, in 1–2 sentences. If args were passed, this reflects them.
3. `## Current state` — what's done and working right now. Bullets, past tense.
4. `## Next steps` — the concrete actions to take next, ordered, each an imperative ("Wire up X", "Run Y"). The most important section: make it actionable from a cold start.
5. `## Open questions / blockers` — unresolved decisions, things waiting on someone, known risks.
6. `## Key context` — the non-obvious things: decisions made and why, gotchas, dead ends already ruled out. Skip anything a fresh agent could read straight from the code or the linked artifacts.
7. `## Pointers` — paths and URLs to the artifacts that hold the detail: PRDs, plans, ADRs, issues, branches, key files (`path:line`). Reference them; don't copy their contents in.
8. `## Suggested skills` — which skills the next session should use, if any, and for what.

## Rules

- Don't duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead — that's what **Pointers** is for.
- If a section has no real content, write `None.` under it rather than padding with filler or inventing items to fill space. An empty **Open questions** is fine; a fabricated one is not.
- Keep it tight. A handoff is a launchpad, not a transcript.