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-delegate.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-delegate)<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.
<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>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 | $0.00787 |
| Opus 5 | $0.00009 | $0.00394 |
| Sonnet 5 | $0.00003 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00079 |
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.
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."
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.
- 9d ago First seen · 81 lines · 17 tokens per session scan A a5d20a14497f
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.
Other commands, from other repositories
commands
A set of project-management commands for maintaining collaboration rules, documentation, plans, thoughts, and project configuration. It covers tasks such as adding commands, updating governance instructions, recording ideas, and organizing roadmap items.
issue-prd-generation
You are generating a comprehensive Product Requirements Document (PRD) for a GitHub issue. This PRD will be passed to a separate AI agent instance with ONLY THIS CONTEXT for implementation. Write with that constraint in mind.
artifact-insight-scan
Analyze the provided project artifacts for missed insights, action items, and follow-ups that should become tracked issues.
polish-repo-community
Phase 3 of polish-repo: Community infrastructure, issue templates, roadmap, contributor experience, and signs of life.
estimate-point
Phases 4-5 of estimating-tickets. Multi-agent consensus pointing per ticket + AI productivity multiplier.
estimate-scope
Phase 1-3 of estimating-tickets. Ingest the test card, validate external-domain constraints, build a structural repo map, decompose into tickets tagged by repo.