handover

handover is a command for Claude Code from Cfvillarroel/carryover. It costs 19 tokens per session (349 once invoked), scanned A, original, MIT.

A command for actively handing a task to another workspace, meaning another connected agent environment. It sends a notification and tells that workspace to execute the task when the message arrives.

In plain words
What is it for?
Use it to pass an unfinished task, summary, relevant files, decisions, and cautions to another named workspace.
Why use it?
It transfers work with its current state and instructions instead of requiring the next workspace to reconstruct the task from scratch.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the carryover plugin — 1 skill, 13 commands, 4 hooks shipped together

Good fit Use it to pass an unfinished task, summary, relevant files, decisions, and cautions to another named workspace.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cfvillarroel/carryover/handover
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Cfvillarroel/carryover

Made for: Claude Code.

Or install carryover, the plugin that ships this one along with the rest of its 1 skill, 13 commands, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for handover

README.md
[![agentmods](https://agentmods.dev/badge/commands/cfvillarroel/carryover/handover/github.svg)](https://agentmods.dev/commands/cfvillarroel/carryover/handover)
Your own site
<a href="https://agentmods.dev/commands/cfvillarroel/carryover/handover"><img src="https://agentmods.dev/badge/commands/cfvillarroel/carryover/handover/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for handover

Your own site · 80×15
<a href="https://agentmods.dev/commands/cfvillarroel/carryover/handover"><img src="https://agentmods.dev/badge/commands/cfvillarroel/carryover/handover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00349
Opus 5 $0.00010 $0.00175
Sonnet 5 $0.00004 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 9d ago against content hash b91f6398dfdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

handover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude/commands/handover.md · 31 lines

What it actually says

Like /handoff, but an active transfer: the target workspace is pinged (macOS desktop notification) and, when its inbox is delivered, the agent is told to execute the task now, not just read it.

$ARGUMENTS = the target workspace name (optionally followed by a note about what to hand over).

Write a concise handover summary yourself, from this session's context. Include:

  • what was done,
  • the current state,
  • what you're asking the other workspace to do,
  • key files, decisions, or gotchas they'll need to continue.

Then send it via Bash (resolve the headroom venv python so the write works):

PY="$HOME/.headroom/venv/bin/python"; [ -x "$PY" ] || PY="$(command -v python3)"
"$PY" "$HOME/.carryover/co-mem" handover <workspace> "<your handover summary>"

Substitute <workspace> and your summary, escaping it safely. Confirm to the user what you handed over and to whom. Address the target by its city codename or project name (stable); a renamed title may not resolve. If no workspace was given, ask which one (or run python3 "$HOME/.carryover/co-mem" connections to see connected ones).

Note: the target won't run on its own while idle — the notification tells the user to open it; the agent picks up and executes the handover on its next turn (via the inbox hook).

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 31 lines · 19 tokens per session scan A b91f6398dfdf

Subscribe to this mod's changes

handover is a command published in the GitHub repository Cfvillarroel/carryover (5 stars, last pushed 24d ago), licensed MIT. It adds 19 tokens to every session and 349 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.