agentmods.dev

handoff

handoff is a skill for Claude Code from mmr710/nightmux. It costs 77 tokens per session (393 once invoked), scanned A, original, MIT.

A repository handoff tool that gives another coding agent a written brief about the current work. It records recent actions, changes, repository status, and the next steps.

In plain words
What is it for?
Use it to pass work to Codex, Gemini CLI, OpenCode, Qwen Code, or another installed coding agent.
Why use it?
It prevents context from being lost when one agent reaches a usage limit or another agent needs to continue the task. The next agent receives both the repository state and instructions about unfinished work.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

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 nightmux plugin — 2 skills shipped together

not rated 25repo yesterday A scan 77 tokens original MIT

Good fit Use it to pass work to Codex, Gemini CLI, OpenCode, Qwen Code, or another installed coding agent.

Compare 6 skills from other repositories ↓
View source ↗ mmr710/nightmux mmr710.github.io
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 mmr710/nightmux
Claude Code
/plugin install nightmux

Made for: Claude Code.

Or install nightmux, the plugin that ships this one along with the rest of its 2 skills.

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/skills/mmr710/nightmux/handoff/github.svg)](https://agentmods.dev/skills/mmr710/nightmux/handoff)
Your own site
<a href="https://agentmods.dev/skills/mmr710/nightmux/handoff"><img src="https://agentmods.dev/badge/skills/mmr710/nightmux/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/skills/mmr710/nightmux/handoff"><img src="https://agentmods.dev/badge/skills/mmr710/nightmux/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 393 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 $0.00077 $0.00393
Opus 5.5 $0.00031 $0.00157
Sonnet 5.5 $0.00015 $0.00079
Haiku 4.5 $0.00008 $0.00039

Measured 13d ago against content hash 3b3c3370867e, 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 13d 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.

skills/handoff/SKILL.md · 18 lines

What it actually says

Request: $ARGUMENTS

  1. At the root of the repository, run python3 "${CLAUDE_PLUGIN_ROOT}/nightmux.py" handoff with the Bash tool and no other arguments: given an agent, it would start that agent's interface here, and that cannot run inside this session. It writes .nightmux/HANDOFF.md (the last instruction, recent actions, git status, the diffstat and recent commits, from the agents' own logs; the file stays out of git status), prints it, and lists the agents installed here.

  2. Append a section ## Where Claude stopped to .nightmux/HANDOFF.md: what is done, what is half done (files and functions), the next steps, and anything the next agent is likely to get wrong. Thirty lines at most; the working tree has the rest. Outside a git repository nothing was written, so put that section in your reply instead.

  3. Give the user the line that starts the next agent on it, to run in a terminal of their own:

    cd "<repository root>" && python3 "${CLAUDE_PLUGIN_ROOT}/nightmux.py" handoff <agent> "<what to do next>"

    Use the agent named in the request, or else one of the installed agents the command listed. With nightmux installed, nightmux handoff <agent> "..." does the same.

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. 13d ago First seen · 18 lines · 77 tokens per session scan A 3b3c3370867e

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository mmr710/nightmux (25 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 393 once invoked, about $0.0003 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.

Building agentsClaude CodeProject managementagentic-codingai-agentsaidercodexdeveloper-tools
Related

handoff compared with skills from other repositories

handoff next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
handoffmmr710/nightmuxSkill25yesterdayMITA77Claude Code
ralplanYeachan-Heo/oh-my-claudecodeSkill41kyesterdayMITA21Claude Code
rememberYeachan-Heo/oh-my-claudecodeSkill41kyesterdayMITA20Claude Code
handoverme2resh/apexyardSkill542yesterdayMITA25Claude Code
projectsme2resh/apexyardSkill542yesterdayMITA24Claude Code
moai-ref-ui-polishmodu-ai/moai-adkSkill1.3k4d agoApache-2.0A98Claude Code
blueprint-cloudflare-scaffoldreceptron/mulmoterminalSkill261yesterdayMITA28Claude Code, Codex