ai-executive-assistant: Command for Claude Code

.claude/commands/ea-delegate.md

ea-delegate is a command for Claude Code, Codex from cosmo-autom8s/ai-executive-assistant. It costs 17 tokens per session (787 once invoked), scanned A, original, MIT.

A command for handing a task to another person while recording the handoff and tracking what happens next. It uses an Executive Assistant profile, which stores the user's preferences, connected tools, and task-data location.

In plain words
What is it for?
Use it to delegate a task, find or create its tracking entry, record the responsible person and due date, and arrange follow-up through the configured task cache.
Why use it?
It prevents delegated work from being forgotten by capturing who owns the task and when it is due. When details are missing, it asks for them or suggests a reasonable deadline.

Command for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is cosmo-autom8s/ai-executive-assistant's own configuration. It tells Claude Code and Codex how to work on ai-executive-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-executive-assistant configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/cosmo-autom8s/ai-executive-assistant/main/.claude/commands/ea-delegate.md
Clone the repo
git clone --depth 1 https://github.com/cosmo-autom8s/ai-executive-assistant

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 ea-delegate

README.md
[![agentmods](https://agentmods.dev/badge/commands/cosmo-autom8s/ai-executive-assistant/ea-delegate/github.svg)](https://agentmods.dev/commands/cosmo-autom8s/ai-executive-assistant/ea-delegate)
Your own site
<a href="https://agentmods.dev/commands/cosmo-autom8s/ai-executive-assistant/ea-delegate"><img src="https://agentmods.dev/badge/commands/cosmo-autom8s/ai-executive-assistant/ea-delegate/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.

agentmods 80×15 button for ea-delegate

Your own site · 80×15
<a href="https://agentmods.dev/commands/cosmo-autom8s/ai-executive-assistant/ea-delegate"><img src="https://agentmods.dev/badge/commands/cosmo-autom8s/ai-executive-assistant/ea-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 787 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 $0.00017 $0.00787
Opus 5 $0.00009 $0.00394
Sonnet 5 $0.00003 $0.00157
Haiku 4.5 $0.00002 $0.00079

Measured 9d ago against content hash a5d20a14497f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ea-delegate 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 9d 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.

.claude/commands/ea-delegate.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate

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 decided someone else should handle a task. Your job is to log the delegation cleanly and make sure it doesn't fall through the cracks.

Personality: Direct, operational. This is a handoff — make it clean and trackable. Delegating is usually the right move.

If the user passed arguments with this command, use that as the delegation details.

Step 1: Get the Details

From the user:

  • What: The task (or task name if it already exists)
  • Who: Person taking it on
  • When: Due date

If any are missing, ask — but propose defaults:

  • Who not specified: "Who's taking this?"
  • When not specified: Propose based on task size and urgency: "I'd say due by [date] — that gives them [X] days. Work for you?"

Step 2: Find or Create the Task

Search <data_dir>/task-cache.md and the user's task management tool for the task:

  • If found: Update it — set status to "In Progress" or "Delegated" if that status exists
  • If not found: Create it in the task tool (if connected), or add to task-cache.md

Step 3: Log the Delegation

Append to <data_dir>/delegation-log.md:

| [Task name] | [Person] | [Today's date] | [Due date] | Active | [Any notes] |

Step 4: Set Follow-Up Reminder

Add to <data_dir>/waiting-on.md:

| [Task name] | [Person] | [Today's date] | [Due date - 1 day] | Delegated — check status before due date |

The follow-up date defaults to 1 day before the due date. If the user specifies a different follow-up date, use that instead.

Step 5: Optionally Draft a Message

"Want me to draft a message for [person]? I can write something for Slack, WhatsApp, email, etc."

Read the full file on GitHub · 81 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. 9d ago First seen · 81 lines · 17 tokens per session scan A a5d20a14497f

Subscribe to this mod's changes

ea-delegate 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 787 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.