handoff

handoff is a command for coding agents from primeline-ai/claude-code-starter-system. It costs 10 tokens per session (588 once invoked), scanned A, original, MIT.

A command that creates a handoff document summarizing the current coding session. The document records completed work, decisions, unfinished tasks, and blockers for the next session.

In plain words
What is it for?
Use it at the end of a session to document project progress and create a dated handoff file.
Why use it?
It prevents important context from being lost when work continues in a new conversation. It gives the next session a written starting point.

Command

Part of the claude-code-starter-system plugin — 1 skill, 4 commands shipped together

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.

agentmods
npx agentmods add commands/primeline-ai/claude-code-starter-system/handoff
Clone the repo
git clone --depth 1 https://github.com/primeline-ai/claude-code-starter-system

Or install claude-code-starter-system, the plugin that ships this one along with the rest of its 1 skill, 4 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/primeline-ai/claude-code-starter-system/handoff.svg)](https://agentmods.dev/commands/primeline-ai/claude-code-starter-system/handoff)
Your own site
<a href="https://agentmods.dev/commands/primeline-ai/claude-code-starter-system/handoff"><img src="https://agentmods.dev/badge/commands/primeline-ai/claude-code-starter-system/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00010 $0.00588
Opus 5 $0.00005 $0.00294
Sonnet 5 $0.00002 $0.00118
Haiku 4.5 $0.00001 $0.00059

Measured 4d ago against content hash 33a6d1c62cb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

handoff 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 4d 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.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff

Create a structured handoff document that captures what happened this session so the next session can pick up exactly where you left off.

Workflow

Step 1: Summarize the Session

From the current conversation, identify:

  • What was accomplished (concrete actions and results)
  • Key decisions made and the reasoning behind them
  • What is still open or unfinished
  • Any blockers encountered

If the conversation has limited history, note what you can observe from the context.

Step 2: Read Project Context

Read .claude/memory/projects/{active}.json to get the project name and current phase.

If the file does not exist, use "unknown" for project name and phase.

Step 3: Create the Handoff File

Determine a short topic slug from the session focus (2-3 words, kebab-case).

Create the file at:

.claude/handoffs/{YYYY-MM-DD}-{topic-slug}.md

Use this structure:

# Handoff: {YYYY-MM-DD} - {Topic}

**Project:** {name}
**Phase:** {phase}
**Date:** {YYYY-MM-DD}

## Session Summary

{2-4 sentences describing what was accomplished this session}

## Decisions Made

- **{Decision}:** {Reasoning in one sentence}
- {repeat for each key decision, or "None" if no decisions were made}

## Open Items

- {Task or question that still needs attention}
- {repeat for each open item, or "None"}

## Next Session

{One specific, concrete action to take at the start of the next session.
Be precise - "Continue building the auth flow starting with the token refresh endpoint"
is better than "Continue working on auth."}

## Blockers

{Anything currently preventing progress, or "None"}

Step 4: Update Project Memory

Read .claude/memory/projects/{active}.json.

If the file exists, add a new entry to the progress array:

{
  "date": "{YYYY-MM-DD}",
  "summary": "{one sentence from Session Summary}",
  "next": "{Next Session action}"
}

Write the updated file back.

If the file does not exist, skip this step.

Step 5: Show the Handoff

Read the full file on GitHub · 107 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. 4d ago First seen · 107 lines · 10 tokens per session scan A 33a6d1c62cb5

Subscribe to this mod's changes

handoff is a command published in the GitHub repository primeline-ai/claude-code-starter-system (5 stars, last pushed 20d ago), licensed MIT. It adds 10 tokens to every session and 588 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.