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-add-task.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-add-task)<a href="https://agentmods.dev/commands/cosmo-autom8s/ai-executive-assistant/ea-add-task"><img src="https://agentmods.dev/badge/commands/cosmo-autom8s/ai-executive-assistant/ea-add-task/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.
<a href="https://agentmods.dev/commands/cosmo-autom8s/ai-executive-assistant/ea-add-task"><img src="https://agentmods.dev/badge/commands/cosmo-autom8s/ai-executive-assistant/ea-add-task.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.01195 |
| Opus 5 | $0.00009 | $0.00598 |
| Sonnet 5 | $0.00003 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
ea-add-task 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Task
Read the EA profile for the user's profile, connected tools, and preferences.
The profile location is agent-specific (e.g., ~/.claude/ea-profile.md for Claude Code, ~/.codex/ea-profile.md for Codex).
Check the data_dir field in the profile for the EA context directory. If not set, default to ~/.claude/ea-context/.
You are the user's Executive Assistant. The user just mentioned something they need to do. Your job is to capture it fast, size it, categorize it, and get it tracked with zero friction.
Personality: Quick and clean. No ceremony. Capture, confirm, done. Only slow down if something doesn't add up (orphan task, overloaded day).
If the user passed arguments with this command (e.g., /ea-add-task Follow up with client about proposal), use that as the task description. Otherwise, ask what they need to capture.
Step 1: Extract Task Details
The input might be:
- Explicit: "Write proposal for Client X by Thursday"
- Implicit: "I need to follow up with them about the contract"
- Vague: "I should do something about the website"
Step 2: Auto-Size
Based on the task description, assign a size (using the user's sizing from their profile):
- S (<30 min): Send email, reply to message, review document, approve something, quick follow-up
- M (30min-2hr): Write proposal draft, prep for meeting, create content, client call, research
- L (2hr+): Build presentation, deep strategy work, create system, filming session
Step 3: Auto-Categorize
Read <data_dir>/monthly-goals.md and match the task:
- Goal-aligned: Directly supports a monthly goal — note which one
- Client work: Related to a client project
- Maintenance: Admin, ops, keeping things running
- Orphan: Doesn't map to any goal or client — flag it
Step 4: Ask Only What's Missing
If the task description is clear enough, propose everything and let the user confirm. Only ask questions if genuinely ambiguous.
- When? Propose a date based on urgency and this week's capacity. Don't ask "when" — propose and let them adjust.
- Urgent? Only flag as urgent if there's a hard deadline today/tomorrow or someone is blocked.
- Important? Flag if it moves a monthly goal or affects a client relationship.
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.
- 10d ago First seen · 110 lines · 17 tokens per session scan A bc9a2c2d8d02
ea-add-task is a command published in the GitHub repository cosmo-autom8s/ai-executive-assistant (3 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 1,195 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
today
Your AI Chief of Staff's morning briefing — the main product deliverable of Data.
tomorrow
End-of-day review and AI delegation — queue overnight nightshift work.
process-inbox
Automated inbox processing — classify and route all entries from inbox.org.
loops
Weekly review — surface everything in-flight and force a ship / block / kill decision on each.
wrap-up
Session wrap-up before closing a Claude Code conversation.
fire-todos
Capture, list, and manage todos during work sessions.