A mode for telling the agent that you are temporarily away while work continues. It checks the computer's time, power, lid, and network state before proceeding.

Use it for tasks that can continue unattended, while deferring work that may use substantial battery, power, or network capacity.

It avoids stopping for routine, reversible choices when you cannot respond immediately.

afk — Skill for Claude Code by bendrucker/claude

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.

Any agent

npx skills add bendrucker/claude --skill afk

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/afk/github.svg)](https://agentmods.dev/skills/bendrucker/claude/afk)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/afk"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/afk/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bendrucker/claude/afk"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/afk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,241 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.

Model	Per session	Once invoked
Fable 5.1	$0.00074	$0.01241
Opus 5.5	$0.00030	$0.00496
Sonnet 5.5	$0.00015	$0.00248
Haiku 4.5	$0.00007	$0.00124

Measured today against content hash 2ec1fe96511f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

afk 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 today.

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.

user/skills/afk/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AFK

Ben is stepping away. Keep the current task moving without him at the keyboard. Assume he cannot answer in real time, never idle on a prompt for a reversible decision, and avoid bandwidth- or power-heavy work when the machine is constrained.

Duration argument: $0 (e.g. 30m, 2h, overnight). It is a pacing and expected-return hint, not a hard timer. With no duration, run open-ended until the task is done or fully blocked.

Read state at invocation

Ben is still present right now. Surface read-only state and let the model interpret the raw output. Interpretation and the sandbox caveat live in references/resources.md.

Local time: !date "+%A %H:%M"
Power source: !pmset -g ps
Lid / clamshell: !ioreg -r -k AppleClamshellState
Network addresses (tether): !ifconfig | grep "inet "

Classify from the output above:

AC Power is plugged in, Battery Power is on battery. No InternalBattery line means a desktop (treat as AC, no battery constraint).
A node block with "AppleClamshellState" = Yes means the lid is closed. = No means open. Empty output means no lid (desktop). Treat empty as open.
An inet address in 172.20.10.0/28 (starts 172.20.10.) means an iPhone Personal Hotspot, USB or Wi-Fi. Any other address means no tether detected. SSID is redacted in current macOS, so this subnet is the available hotspot signal.

Handshake while present

Use this moment before Ben leaves. Keep it to a few lines, then proceed.

One line of detected state: power, lid, tether, and expected return if a duration was given.
State the contract being entered: finish the current task, batch reversible decisions behind logged defaults, defer bandwidth- and power-heavy steps under the detected constraints.
Remind him to switch to a permissive mode (acceptEdits or auto) so edits and commands do not stall while he is away. This skill cannot detect or set permission mode.
Remind him that blocking questions reach his phone only if Remote Control is connected and push is enabled in /config.
If the in-flight task already has a genuinely ambiguous priority or a visible irreversible fork, ask it now with AskUserQuestion while he can answer cheaply. Otherwise proceed without ceremony.

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/resources.md 3.0 KB

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.

today Changed 2ec1fe96511f
1mo ago First seen · 79 lines · 74 tokens per session scan A d7fe7027add6

Subscribe to this mod's changes

afk is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,241 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 2026-09-03.

Claude Code Productivity claude-code-plugin

release-notes

Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.

kenryu42/cc-safety-net · 65 tokens

afk

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AFK

Read state at invocation

Handshake while present

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

release-notes

add-teams

sys-configure

recipe-front-review

relations

recipe-add-integration-tests