away

away is a skill for Claude Code, Codex from MountainUnicorn/add. It costs 17 tokens per session (1,119 once invoked), scanned A, original, MIT.

A command for deciding what coding work may continue while the human is away and what must wait. It checks project goals, approved work, current plans, unfinished changes, and autonomy settings.

In plain words
What is it for?
Use it to assess tasks that can proceed independently, such as writing tests, implementing approved work, refactoring covered code, or fixing quality errors.
Why use it?
It prevents unattended work from exceeding its instructions or making decisions that require human approval.

Skill for Claude CodeCodex

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 skills/mountainunicorn/add/away
Any agent
npx skills add MountainUnicorn/add --skill away
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

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 away

README.md
[![agentmods](https://agentmods.dev/badge/skills/mountainunicorn/add/away.svg)](https://agentmods.dev/skills/mountainunicorn/add/away)
Your own site
<a href="https://agentmods.dev/skills/mountainunicorn/add/away"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/away.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,119 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 $0.00017 $0.01119
Opus 5 $0.00009 $0.00560
Sonnet 5 $0.00003 $0.00224
Haiku 4.5 $0.00002 $0.00112

Measured 3d ago against content hash f539aff08522, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

away 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 3d 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.

core/skills/away/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Away Command v{{VERSION}}

The human is stepping away. Establish what work can proceed autonomously and what must wait.

Phase 1: Understand the Absence

Parse the duration from $ARGUMENTS. If not provided, default to 2 hours. Do not ask — just acknowledge the default: "No duration specified — I'll plan for a 2-hour session. Say /add:away 4 hours next time to adjust."

Phase 2: Assess Available Work

  1. Read .add/config.json for autonomy level and environment tier
  2. Re-read docs/prd.md to ground yourself in the project's objectives and scope — this keeps autonomous work aligned with the product vision
  3. Scan specs/ for specs with status "Approved" or "Implementing"
  4. Scan docs/plans/ for plans with status "Approved" or "In Progress"
  5. Check current git status for in-progress work
  6. Run TodoWrite to see current task list

Categorize Work

Autonomous (can do without human):

  • Tasks with clear specs and plans where requirements are unambiguous
  • Writing tests for specced features (RED phase)
  • Implementing against existing failing tests (GREEN phase)
  • Refactoring with test coverage (REFACTOR phase)
  • Running quality gates and fixing lint/type errors
  • Writing documentation for completed features
  • Code review of existing PRs

Queued (needs human decision):

  • Any task where the spec is ambiguous or missing
  • Architecture decisions with multiple valid approaches
  • Deployment to staging or production
  • New feature specs (need interview)
  • Dependency upgrades with breaking changes
  • Anything that would benefit from a Decision Point

Phase 3: Present the Plan

Got it — you'll be away for approximately {DURATION}.

AUTONOMOUS WORK PLAN:
━━━━━━━━━━━━━━━━━━━
{numbered list of tasks, with spec references}

Estimated completion: {rough estimate}

QUEUED FOR YOUR RETURN:
━━━━━━━━━━━━━━━━━━━━━
{numbered list of decisions/tasks that need human input}

I'll maintain a work log and have a return briefing ready.

Phase 4: Get Confirmation

Read the full file on GitHub · 121 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. 3d ago First seen · 121 lines · 17 tokens per session scan A f539aff08522

Subscribe to this mod's changes

away is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,119 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 2026-08-30.