muse: Command for Claude Code

.claude/commands/handoff.md

handoff is a command for Claude Code from myths-labs/muse. It costs 52 tokens per session (1,872 once invoked), scanned A, original, MIT.

An account-transfer procedure for continuing a coding project in a new session when the current account reaches its usage limit. One command saves a snapshot and another restores it from project files.

In plain words
What is it for?
It helps save handoff snapshots, resume a named work stream, check when snapshots were last updated, and coordinate account changes across multiple sessions.
Why use it?
A new account cannot directly inherit the old conversation, so work can otherwise lose its context. Checkpoints provide the information needed to continue and show the state of each work stream.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is myths-labs/muse's own configuration. It tells Claude Code how to work on muse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything muse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to myths-labs/muse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/myths-labs/muse/main/.claude/commands/handoff.md
Clone the repo
git clone --depth 1 https://github.com/myths-labs/muse

Made for: Claude Code.

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/myths-labs/muse/handoff/github.svg)](https://agentmods.dev/commands/myths-labs/muse/handoff)
Your own site
<a href="https://agentmods.dev/commands/myths-labs/muse/handoff"><img src="https://agentmods.dev/badge/commands/myths-labs/muse/handoff/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 handoff

Your own site · 80×15
<a href="https://agentmods.dev/commands/myths-labs/muse/handoff"><img src="https://agentmods.dev/badge/commands/myths-labs/muse/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,872 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 $0.00052 $0.01872
Opus 5.5 $0.00021 $0.00749
Sonnet 5.5 $0.00010 $0.00374
Haiku 4.5 $0.00005 $0.00187

Measured 5d ago against content hash 2633ee7b237b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 5d 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/handoff.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff — 账号接力(多线编排,可选)

会话不能跨账号搬;检查点、看板、记忆目录和本机定时任务都在本机,新账号开新会话读文件就能接上。本流程把「存」和「接」固定下来。

前提:项目有 .muse/orchestration.json(模板 .agent/skills/core/muse-orchestration/templates/orchestration.example.json),登记编排者(orchestrator,即「总管」)和用户自定义的各条线:线 id、检查点文件、接手必读。没有这个文件时按单线处理:存用 /save,接用 /resume。完整规则与依据见 muse-orchestration/references/ACCOUNT_RELAY.md。

用法

  • /handoff save:在旧账号的会话里执行,写本线检查点和接力快照。
  • /handoff <线 id>:在新账号新开的会话里执行,例如 /handoff orchestrator、/handoff build。
  • /handoff status:只读,列出各线最近一条快照和距今多久。

什么时候存

  1. 谁都可以读额度:客户端的用量读数是账号级的,任何会话都能读,不必等编排者。
  2. 滚动检查点:每派出或收回一批子代理、每关一个包,就更新本线检查点的「当前态」(在跑哪些子代理与分支、下一步、在等谁)。撞墙时最多丢一批。
  3. 存档线只看周额度:用最近两次读数算「预计用完分钟数」= 剩余百分点 ÷ 每分钟消耗。预计 20 分钟内用完,或周额度 ≥95%,任一先到 → 立刻 /handoff save 并告诉编排者;编排者收到第一条就向全部线发「全局保存」。存完照常干到撞墙,撞墙才切号。
  4. 短窗(如 5 小时窗)快满时不发全局保存、不必 save:它会自己重置、不换账号,靠第 2 条的滚动检查点。每条线始终留一条「短窗重置时刻 +1 分钟」的自续定时,提示「照进度文件最后一行续」;撤停派令或提前开工时也不删它。
  5. 一次续派 ≥10 个子代理之前先写一次检查点。
  6. 新账号先看档位:额度明显更小的档位全线开会很快撞墙,先告诉用户,等他定再开其它线。
  7. 不按上下文百分比换会话:各线让客户端自动压缩后继续,上下文到 80% 时增量更新一次检查点,不停手、不开新会话。只有三种情况才 /handoff save 并换新会话:①切账号(全线一起存);②会话明显糊涂(反复读错状态、压缩后关键状态互相矛盾);③撞墙前预计要空闲 60 分钟以上、上下文又超过 30 万 token——先存,重置后由新会话从检查点接手,不叫醒旧会话。同一线里要同时做的活交给本线的子代理,不多开会话。

/handoff save 做什么

  1. date 取时间,写进检查点标题。
  2. 先写记忆再写检查点:只把本会话新出现的用户决定(引原话 + 时间)写成记忆(一条事实一个文件,并更新索引);评估结论、对比数据写进检查点即可。写前用 recall.py <词> <其它语言同义词> 查重,已有就改原文件。这里不跑 memory_audit.py --sync(见第 5 条)。
  3. 写检查点:在做什么、做到哪一步、下一步、在等谁、未提交或未落盘的东西放在哪、在跑的子代理及其进度文件。未提交的改动提交到本线自己的分支,不推主干。
  4. 在接力手册(配置 relay_runbook)的「交接快照」填本线一行;编排者另填主干提交号、线上版本、等用户定的事。
  5. 存档只写三样:本线检查点、接力快照、新的用户决定(记忆)。Obsidian 库(daily/、decisions/)、vault_coverage_check.py 与 memory_audit.py --sync 不在每次 save 里做,由编排者每天晚报统一跑一次(见 muse-orchestration/references/ORCHESTRATOR.md「Daily maintenance」与 VAULT.md)。
  6. 编排者退役前删掉自己的会话内定时(应用重启会恢复旧会话的定时,到点会把退役会话叫醒)。
  7. 最后一句告诉用户:「<线 id> 快照已写,可以切」。

/handoff <线 id> 做什么

  1. date 校时;按配置读该线的「接手必读」,不读完不说话。
  2. 读额度:记下档位、短窗与周百分比。若本线最后检查点比旧会话撞墙时间早 10 分钟以上,先跑 wall_recover.py <旧会话 id> --since <最后检查点时间>,把没跑完的子代理与各自最后进度补写进检查点,再续派。
  3. 解开上级会话:本会话若是别的会话开出来的(有上级且未解开),先解开成顶层会话;否则旧会话一归档会把本会话一起归档。
  4. 列出其它会话,把自己的新地址发给各方(第一行写「<线 id> 已在新账号接上,之后发这里」);同名会话用唯一 ref 区分。每个收件人只发一条。客户端对跨会话消息设有上限时,到上限就把没发的写成待发草稿,等用户下一句再发,不换通道绕过(见 ORCHESTRATOR.md「Cross-session message cap」)。
  5. 核对快照里「在等谁」是否已有结果(问对方或只读查),不照搬旧状态。
  6. 向编排者发第一条报告(编排者向用户):最要紧三件各到哪一步、要定的事不超过三条、每条带推荐。
  7. 编排者另做:按 muse-orchestration/references/ORCHESTRATOR_CRON.md 重设定时;核旧编排者留下的停派令,条件已过的当场撤;旧会话改名「已退役(勿发消息)」或归档,并请它删自己的定时。
  8. 按快照的「下一步」继续。权限边界不变:部署、生产数据变更、付款、对外发送、删除数据仍需用户在本会话明确同意。

Read the full file on GitHub · 52 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. 5d ago Changed 2633ee7b237b
  2. 12d ago First seen · 52 lines · 52 tokens per session scan A ce62dcd565e9

Subscribe to this mod's changes

handoff is a command published in the GitHub repository myths-labs/muse (38 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 1,872 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-25.

Related

handoff compared with commands from other repositories

handoff next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
handoffmyths-labs/museCommand386d agoMITA52Claude Code
handoffrosehgal/handoffCommand24mo agoMITA10Claude Code
dejavshulcz/deja-vuCommand1.4kyesterdayMITA17Claude Code
adhoc-flowgriddynamics/rosettaCommand370todayApache-2.0A22Claude Code
prepsuboss87/FDEOpsCommand85717d agoMITA10Claude Code
orchestrateegorfedorov/claude-context-optimizerCommand13010d agoMITA0Claude Code
budgetcukas/remembrallCommand63d agoMITA13Claude Code