office:onboarding

office:onboarding is a skill for Claude Code from harperreed/office-admin-claude. It costs 27 tokens per session (1,368 once invoked), scanned A, original, MIT.

A setup guide for personal productivity preferences in an office assistant. It configures how the assistant should handle email, calendars, contacts, and related work.

In plain words
What is it for?
Setting your name, timezone, work hours, email tone and signature preferences, and CRM workflow patterns.
Why use it?
It records your working hours, communication style, and workflow preferences before the assistant manages routine office tasks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the office-admin plugin — 4 skills, 3 commands, 4 MCP servers shipped together

Good fit Setting your name, timezone, work hours, email tone and signature preferences, and CRM workflow patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/harperreed/office-admin-claude/onboarding
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 harperreed/office-admin-claude --skill onboarding
Clone the repo
git clone --depth 1 https://github.com/harperreed/office-admin-claude

Made for: Claude Code.

Or install office-admin, the plugin that ships this one along with the rest of its 4 skills, 3 commands, 4 MCP servers.

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 office:onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/harperreed/office-admin-claude/onboarding.svg)](https://agentmods.dev/skills/harperreed/office-admin-claude/onboarding)
Your own site
<a href="https://agentmods.dev/skills/harperreed/office-admin-claude/onboarding"><img src="https://agentmods.dev/badge/skills/harperreed/office-admin-claude/onboarding.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,368 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 $0.00027 $0.01368
Opus 5 $0.00014 $0.00684
Sonnet 5 $0.00005 $0.00274
Haiku 4.5 $0.00003 $0.00137

Measured 8d ago against content hash ce69e2417138, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

office:onboarding 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 8d 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/onboarding/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Office Onboarding

Welcome to Office! This skill helps you set up your personal productivity style so that the assistant can help you manage email, calendar, and contacts in a way that matches YOUR preferences.

When to Use This Skill

  • First time installing office-admin
  • Want to update your productivity style preferences
  • Need to configure how email drafts should sound
  • Setting up your working hours and calendar preferences
  • Defining your CRM workflow patterns

Onboarding Process

Step 1: Introduce Yourself

Ask the user:

  1. What should I call you? (Their preferred name/nickname)
  2. What's your timezone? (Default: America/Chicago)
  3. What are your typical working hours? (Default: 9:30am - 4:30pm, lunch 12:00-1:30pm)

Step 2: Email Communication Style

Ask about their email preferences:

  1. Email Tone - How do you typically write emails?

    • Ultra-terse (1-2 lines, no fluff, get to point)
    • Conversational (casual but complete)
    • Professional (formal, structured)
    • Warm (friendly, personal touch)
  2. Email Signatures - Do you use signatures?

    • None (no signatures or sign-offs)
    • Minimal ("Best," or "Thanks,")
    • Full signature block
  3. Formality Level

    • Super casual (lowercase is fine, minimal punctuation)
    • Standard (proper grammar and capitalization)
    • Formal (perfect grammar, structured sentences)
  4. Response Length

    • Minimal (one-liners when possible)
    • Balanced (2-3 sentences typical)
    • Detailed (thorough explanations)
  5. Specific Patterns - Any phrases or patterns you always use?

    • Examples: "Does [time] work for you?", "Let's sync on this", specific greetings

Step 3: Calendar Preferences

Ask about calendar management:

  1. Default meeting duration (Default: 30 minutes)
  2. Buffer time between meetings (Default: 15 minutes)
  3. Calendar link for scheduling (If they have one)
  4. Event naming preferences (Include location? Attendee names?)
  5. Auto-add events from email? (Yes/No - should calendar skill proactively add events)

Read the full file on GitHub · 202 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. 8d ago First seen · 202 lines · 27 tokens per session scan A ce69e2417138

Subscribe to this mod's changes

office:onboarding is a skill published in the GitHub repository harperreed/office-admin-claude (5 stars, last pushed 9mo ago), licensed MIT. It adds 27 tokens to every session and 1,368 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.