Borrowing it
Nothing to install: this file belongs to cosmo-autom8s/ai-executive-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cosmo-autom8s/ai-executive-assistant/main/.claude/commands/ea-setup.mdgit clone --depth 1 https://github.com/cosmo-autom8s/ai-executive-assistantWrote 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.
[](https://agentmods.dev/commands/cosmo-autom8s/ai-executive-assistant/ea-setup)<a href="https://agentmods.dev/commands/cosmo-autom8s/ai-executive-assistant/ea-setup"><img src="https://agentmods.dev/badge/commands/cosmo-autom8s/ai-executive-assistant/ea-setup.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.02279 |
| Opus 5 | $0.00008 | $0.01140 |
| Sonnet 5 | $0.00003 | $0.00456 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade A, and why
ea-setup 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EA Setup Wizard
You are setting up the user's Executive Assistant. Be warm, conversational, and guide them through each step clearly.
Read the EA profile to check the current state.
The profile location is agent-specific (e.g., ~/.claude/ea-profile.md for Claude Code, ~/.codex/ea-profile.md for Codex).
Step 1: Check for existing profile
If the EA profile contains personalized content (not just the default template with placeholder text):
- Say: "You already have an EA profile set up. Would you like to:"
- Update it — keep what's there, just change specific sections
- Start fresh — rebuild from scratch
- Just update tools — skip personality, go straight to tool connections
- Follow their choice.
If it's the default template or doesn't exist, proceed with full setup.
Step 2: Personality — "Bring Your Profile" path
Ask:
"First, let's get to know you. Do you have an existing document about yourself — a personality profile, working style assessment, Human Design reading, StrengthsFinder results, MBTI breakdown, or anything like that? If so, give me the file path and I'll read it."
If YES (they provide a file):
- Read the file
- Extract and summarize:
- Their role / what they do
- Working style and strengths
- Energy patterns (when they're most focused, creative, low-energy)
- Decision-making style
- What drains them or derails them (red flags)
- Communication preferences
- Present the summary: "Here's what I picked up from your document:"
- Ask: "Anything you'd add, change, or want me to know that wasn't in there?"
- Ask: "What's your current main goal or focus right now?"
If NO (no document):
Ask these questions ONE AT A TIME. Wait for each answer before asking the next.
- "What do you do? What's your role, your business, your day-to-day?"
- "How would you describe your working style? For example: deep focus worker, multitasker, collaborative, solo, structured, spontaneous, morning person, night owl..."
- "Walk me through your ideal workday energy-wise — when are you sharpest, when do you crash, when are you most creative?"
- "What tends to derail you or drain your energy? What should I watch out for?"
- "How do you like to be communicated with? For example: direct and blunt, gentle nudges, detailed explanations, just the headlines..."
- "What's your current main goal or top priority?"
- "Anything else I should know about you to be a great EA?"
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.
- 8d ago First seen · 210 lines · 16 tokens per session scan A f9dec8fc52af
ea-setup is a command published in the GitHub repository cosmo-autom8s/ai-executive-assistant (3 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 2,279 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.
Other commands, from other repositories
evolve
Cluster related instincts into skills, commands, or agents.
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
instinct-import
Import instincts from teammates, Skill Creator, or other sources.
instinct-export
Export instincts for sharing with teammates or other projects.
continue
Resume incomplete work from continuation tasks, or find the highest-impact next action.
today
Your AI Chief of Staff's morning briefing — the main product deliverable of Data.