ceos-delegate

ceos-delegate is a skill for Claude Code, Codex from bradfeld/ceos. It costs 24 tokens per session (4,174 once invoked), scanned A, original, MIT.

A framework for sorting a leader's tasks by how much they enjoy them and how well they do them, then deciding what to keep or hand off.

In plain words
What is it for?
Reviewing responsibilities, identifying tasks to delegate, planning handoffs, and checking progress on delegation.
Why use it?
It shows which work fits the leader's best contribution and which work may be better owned by someone else.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/bradfeld/ceos/ceos-delegate
Any agent
npx skills add bradfeld/ceos --skill ceos-delegate
Clone the repo
git clone --depth 1 https://github.com/bradfeld/ceos

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 ceos-delegate

README.md
[![agentmods](https://agentmods.dev/badge/skills/bradfeld/ceos/ceos-delegate.svg)](https://agentmods.dev/skills/bradfeld/ceos/ceos-delegate)
Your own site
<a href="https://agentmods.dev/skills/bradfeld/ceos/ceos-delegate"><img src="https://agentmods.dev/badge/skills/bradfeld/ceos/ceos-delegate.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.04174
Opus 5 $0.00012 $0.02087
Sonnet 5 $0.00005 $0.00835
Haiku 4.5 $0.00002 $0.00417

Measured 4d ago against content hash e48416809431, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ceos-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 4d 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/ceos-delegate/SKILL.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ceos-delegate

Categorize a leader's tasks and responsibilities into the Delegate and Elevate 4-quadrant matrix based on enjoyment and competency. Identify what to keep, what to delegate, and create action plans for handing off work that doesn't belong in the leader's "Love It / Great At It" quadrant.

Not for: People evaluation (use ceos-people), organizational structure (use ceos-accountability), or performance conversations (use ceos-quarterly). Delegate and Elevate is a leadership development tool — it helps leaders focus on their highest and best use, not assess fit or performance.

When to Use

  • "Run delegate and elevate for [person]" or "delegation audit"
  • "What should I be delegating?" or "am I doing the right work?"
  • "Review delegation progress" or "how's [person]'s delegation going?"
  • "Create a delegation plan" or "help me hand off these tasks"
  • "What's in my bottom quadrants?" or "show my D&E results"
  • "Time for a delegation audit" or "let's do delegate and elevate"
  • Any discussion about task delegation, leadership focus, or highest-and-best-use

Context

Finding the CEOS Repository

Search upward from the current directory for the .ceos marker file. This file marks the root of the CEOS repository.

If .ceos is not found, stop and tell the user: "Not in a CEOS repository. Clone your CEOS repo and run setup.sh first."

Sync before use: Once you find the CEOS root, run git -C <ceos_root> pull --ff-only --quiet 2>/dev/null to get the latest data from teammates. If it fails (conflict or offline), continue silently with local data.

Key Files

File Purpose
data/delegate/ Delegate and Elevate audit files (one per person)
templates/delegate.md Template for new delegation audits
data/accountability.md Source of seat responsibilities (read-only — use ceos-accountability to modify)
data/people/ People Analyzer evaluations (read-only — reference for context)

Delegate File Format

Read the full file on GitHub · 389 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. 4d ago First seen · 389 lines · 24 tokens per session scan A e48416809431

Subscribe to this mod's changes

ceos-delegate is a skill published in the GitHub repository bradfeld/ceos (145 stars, last pushed 24d ago), licensed MIT. It adds 24 tokens to every session and 4,174 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 2026-08-30.