handoff-create

handoff-create is a command for Claude Code from TusharKarkera22/claude-loadout. It costs 28 tokens per session (839 once invoked), scanned A, original, MIT.

A two-stage command for preparing a handoff bundle, which packages project context for a teammate. It first writes a draft summary for review and waits for explicit confirmation before bundling it.

In plain words
What is it for?
Use it when another developer needs to continue the current task. It records the goal, completed and pending work, file changes, important context, and the suggested next move.
Why use it?
It makes unfinished work, decisions, touched files, and next steps visible before the handoff is finalized. This reduces the chance of passing along an inaccurate or incomplete summary.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-loadout plugin — 1 skill, 9 commands shipped together

Good fit Use it when another developer needs to continue the current task. It records the goal, completed and pending work, file changes, important context, and the suggested next move.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add TusharKarkera22/claude-loadout
Claude Code
/plugin install claude-loadout

Made for: Claude Code.

Or install claude-loadout, the plugin that ships this one along with the rest of its 1 skill, 9 commands.

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 handoff-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/tusharkarkera22/claude-loadout/handoff-create.svg)](https://agentmods.dev/commands/tusharkarkera22/claude-loadout/handoff-create)
Your own site
<a href="https://agentmods.dev/commands/tusharkarkera22/claude-loadout/handoff-create"><img src="https://agentmods.dev/badge/commands/tusharkarkera22/claude-loadout/handoff-create.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 839 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 $0.00028 $0.00839
Opus 5 $0.00014 $0.00419
Sonnet 5 $0.00006 $0.00168
Haiku 4.5 $0.00003 $0.00084

Measured 8d ago against content hash a91e8caecc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

handoff-create 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 8d 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.

commands/handoff-create.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are helping the user prepare a handoff bundle for a teammate. This runs in two phases. Do not bundle until the user explicitly confirms the draft.

The user passed: $ARGUMENTS

Phase 1 — Draft the summary, then stop

Look at this session: what was the user trying to accomplish, what did we establish, what's still open? Write a concise handoff to the file path ${TMPDIR:-/tmp}/loadout-handoff-summary.md (use the Write tool). Use this exact structure — omit a section rather than padding it:

# What I was working on
<one paragraph: the active goal in plain language a teammate can read cold>

# What's done
- <completed work, name files/functions, one item per line>

# What's pending
- [ ] <next concrete step>
- [ ] <...>

# Files touched
<list paths with one-line descriptions of the change>

# Decisions / context
<non-obvious things: why we chose X, what didn't work, hidden constraints a teammate would otherwise miss>

# What I'd do next
<one paragraph: your suggested next move>

Be specific. Avoid generic phrasing like "improved the codebase" — name the file, the function, the change.

After writing the file, show the user the full draft (paste it back into the chat) and say verbatim:

"Draft saved to ${TMPDIR:-/tmp}/loadout-handoff-summary.md. Edit it directly in your editor if anything needs sharpening — it's plain markdown. When you're ready, say bundle to package it (with the diff + manifest), or cancel to drop it."

Stop here. Do not run the CLI in this turn. Wait for the user to reply with bundle, cancel, or feedback.


Phase 2 — Bundle (only when the user confirms)

When the user's next turn replies with bundle, looks good, ship it, go, or any clear confirmation:

  1. Re-read ${TMPDIR:-/tmp}/loadout-handoff-summary.md — the user may have edited it.

  2. Run the CLI:

    node "${CLAUDE_PLUGIN_ROOT}/bin/cli.cjs" handoff create \
      --summary "${TMPDIR:-/tmp}/loadout-handoff-summary.md" \
      --source "${PWD}" \
      $ARGUMENTS
    

Read the full file on GitHub · 70 lines

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. 8d ago First seen · 70 lines · 28 tokens per session scan A a91e8caecc7f

Subscribe to this mod's changes

handoff-create is a command published in the GitHub repository TusharKarkera22/claude-loadout (2 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 839 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.